MDPI - Publisher of Open Access Journals

Open AccessArticle Predicting Stem Total and Assortment Volumes in an Industrial Pinus taeda L. Forest Plantation Using Airborne Laser Scanning Data and Random Forest

by Carlos Alberto Silva, Carine Klauberg, Andrew Thomas Hudak, Lee Alexander Vierling, Wan Shafrina Wan Mohd Jaafar, Midhun Mohan, Mariano Garcia, António Ferraz, Adrián Cardil and Sassan Saatchi

Forests 2017, 8(7), 254; doi:10.3390/f8070254 (registering DOI)

Received: 27 April 2017 / Revised: 22 June 2017 / Accepted: 13 July 2017 / Published: 17 July 2017

PDF Full-text (6331 KB) | HTML Full-text | XML Full-text

Abstract

Improvements in the management of pine plantations result in multiple industrial and environmental benefits. Remote sensing techniques can dramatically increase the efficiency of plantation management by reducing or replacing time-consuming field sampling. We tested the utility and accuracy of combining field and airborne

[...] Read more.

Improvements in the management of pine plantations result in multiple industrial and environmental benefits. Remote sensing techniques can dramatically increase the efficiency of plantation management by reducing or replacing time-consuming field sampling. We tested the utility and accuracy of combining field and airborne lidar data with Random Forest, a supervised machine learning algorithm, to estimate stem total and assortment (commercial and pulpwood) volumes in an industrial Pinus taeda L. forest plantation in southern Brazil. Random Forest was populated using field and lidar-derived forest metrics from 50 sample plots with trees ranging from three to nine years old. We found that a model defined as a function of only two metrics (height of the top of the canopy and the skewness of the vertical distribution of lidar points) has a very strong and unbiased predictive power. We found that predictions of total, commercial, and pulp volume, respectively, showed an adjusted R² equal to 0.98, 0.98 and 0.96, with unbiased predictions of −0.17%, −0.12% and −0.23%, and Root Mean Square Error (RMSE) values of 7.83%, 7.71% and 8.63%. Our methodology makes use of commercially available airborne lidar and widely used mathematical tools to provide solutions for increasing the industry efficiency in monitoring and managing wood volume. Full article

► Figures

Open AccessArticle Estimation of Forest Aboveground Biomass in Changbai Mountain Region Using ICESat/GLAS and Landsat/TM Data

by Hong Chi, Guoqing Sun, Jinliang Huang, Rendong Li, Xianyou Ren, Wenjian Ni and Anmin Fu

Remote Sens. 2017, 9(7), 707; doi:10.3390/rs9070707

Received: 20 June 2017 / Revised: 4 July 2017 / Accepted: 4 July 2017 / Published: 9 July 2017

Viewed by 311 | PDF Full-text (17845 KB) | HTML Full-text | XML Full-text | Supplementary Files

Abstract

Mapping the magnitude and spatial distribution of forest aboveground biomass (AGB, in Mg·ha⁻¹) is crucial to improve our understanding of the terrestrial carbon cycle. Landsat/TM (Thematic Mapper) and ICESat/GLAS (Ice, Cloud, and land Elevation Satellite, Geoscience Laser Altimeter System) data were

[...] Read more.

Mapping the magnitude and spatial distribution of forest aboveground biomass (AGB, in Mg·ha⁻¹) is crucial to improve our understanding of the terrestrial carbon cycle. Landsat/TM (Thematic Mapper) and ICESat/GLAS (Ice, Cloud, and land Elevation Satellite, Geoscience Laser Altimeter System) data were integrated to estimate the AGB in the Changbai Mountain area. Firstly, four forest types were delineated according to TM data classification. Secondly, different models for prediction of the AGB at the GLAS footprint level were developed from GLAS waveform metrics and the AGB was derived from field observations using multiple stepwise regression. Lastly, GLAS-derived AGB, in combination with vegetation indices, leaf area index (LAI), canopy closure, and digital elevation model (DEM), were used to drive a data fusion model based on the random forest approach for extrapolating the GLAS footprint AGB to a continuous AGB map. The classification result showed that the Changbai Mountain region was characterized as forest-rich in altitudinal vegetation zones. The contribution of remote sensing variables in modeling the AGB was evaluated. Vegetation index metrics account for large amount of contribution in AGB ranges <150 Mg·ha⁻¹, while canopy closure has the largest contribution in AGB ranges ≥150 Mg·ha⁻¹. Our study revealed that spatial information from two sensors and DEM could be combined to estimate the AGB with an R² of 0.72 and an RMSE of 25.24 Mg·ha⁻¹ in validation at stand level (size varied from ~0.3 ha to ~3 ha). Full article

(This article belongs to the Section Forest Remote Sensing)

► Figures

Figure 1

Open AccessArticle Random Forest Prediction of IPO Underpricing

by David Quintana, Yago Sáez and Pedro Isasi

Appl. Sci. 2017, 7(6), 636; doi:10.3390/app7060636

Received: 2 May 2017 / Revised: 12 June 2017 / Accepted: 15 June 2017 / Published: 20 June 2017

Viewed by 330 | PDF Full-text (927 KB) | HTML Full-text | XML Full-text

Abstract

The prediction of initial returns on initial public offerings (IPOs) is a complex matter. The independent variables identified in the literature mix strong and weak predictors, their explanatory power is limited, and samples include a sizable number of outliers. In this context, we

[...] Read more.

The prediction of initial returns on initial public offerings (IPOs) is a complex matter. The independent variables identified in the literature mix strong and weak predictors, their explanatory power is limited, and samples include a sizable number of outliers. In this context, we suggest that random forests are a potentially powerful tool. In this paper, we benchmark this algorithm against a set of eight classic machine learning algorithms. The results of this comparison show that random forests outperform the alternatives in terms of mean and median predictive accuracy. The technique also provided the second smallest error variance among the stochastic algorithms. The experimental work also supports the potential of random forests for two practical applications: IPO pricing and IPO trading. Full article

(This article belongs to the Section Computer Science and Electrical Engineering)

► Figures

Open AccessArticle Compact Polarimetric Response of Rape (Brassica napus L.) at C-Band: Analysis and Growth Parameters Inversion

by Wangfei Zhang, Zengyuan Li, Erxue Chen, Yahong Zhang, Hao Yang, Lei Zhao and Yongjie Ji

Remote Sens. 2017, 9(6), 591; doi:10.3390/rs9060591

Received: 22 March 2017 / Revised: 22 May 2017 / Accepted: 6 June 2017 / Published: 11 June 2017

Viewed by 401 | PDF Full-text (5379 KB) | HTML Full-text | XML Full-text

Abstract

Growth parameters like biomass, leaf area index (LAI) and stem height play an import role for crop monitoring and yield prediction. Compact polarimetric (CP) SAR has shown great potential and similar performance to fully-polarimetric (FP) SAR in crop mapping and phenology retrieval, but

[...] Read more.

Growth parameters like biomass, leaf area index (LAI) and stem height play an import role for crop monitoring and yield prediction. Compact polarimetric (CP) SAR has shown great potential and similar performance to fully-polarimetric (FP) SAR in crop mapping and phenology retrieval, but its potential in growth parameters inversion has not been fully explored. In this paper, a time series of images of CP SAR was simulated from five FP SAR data gathered during the entire growth season of rape. CP response of 27 parameters, relying on Stokes parameters and their child parameters, decomposition parameters and backscattering coefficients, were extracted and investigated as a function of days after sowing (DAS) during the whole rape growth cycle to interpret their sensitivity to each growth parameter. Then, random forest (RF) was chosen as an automatic approach for the growth parameters inversion method, and its results were compared with traditional single-parameter regression models. Most of the CP parameters showed high sensitivity with growth parameters and great potential for growth parameters inversion. Among all of the regression models, the quadratic regression model showed the best performance for all of the growth parameters inversion, the best result for biomass inversion was the third component of the Stokes parameters (g3) with R² of 0.765 and RMSE of 73.20 g/m². For LAI and stem height was one of the Stokes child parameters, the circular polarization ratio (Uc), with R² of 0.857 and 0.923 and RMSE of 0.66 and 18.71 cm, respectively. RF showed the highest accuracy and smallest RMSE for all of three growth parameters inversion; R² for biomass, LAI and stem height were 0.93, 0.96 and 0.95, respectively; RMSE were 46.24 g/m², 0.25 and 13.5 cm, respectively. However, there are also some CP parameters, which showed low sensitivity to growth parameters, that had high importance for RF inversion. The results confirmed the potential of CP data and the RF method in growth parameters inversion, but they also confirmed that it was difficult to give a physical interpretation for the RF inversion model. Full article

► Figures

Open AccessArticle A Comparison between Spatial Econometric Models and Random Forest for Modeling Fire Occurrence

by Chao Song, Mei-Po Kwan, Weiguo Song and Jiping Zhu

Sustainability 2017, 9(5), 819; doi:10.3390/su9050819

Received: 18 February 2017 / Revised: 19 April 2017 / Accepted: 11 May 2017 / Published: 14 May 2017

Viewed by 395 | PDF Full-text (8852 KB) | HTML Full-text | XML Full-text

Abstract

Fire occurrence, which is examined in terms of fire density (number of fire/km2) in this paper, has a close correlation with multiple spatiotemporal factors that include environmental, physical, and other socioeconomic predictors. Spatial autocorrelation exists widely and should be considered seriously for modeling

[...] Read more.

Fire occurrence, which is examined in terms of fire density (number of fire/km2) in this paper, has a close correlation with multiple spatiotemporal factors that include environmental, physical, and other socioeconomic predictors. Spatial autocorrelation exists widely and should be considered seriously for modeling the occurrence of fire in urban areas. Therefore, spatial econometric models (SE) were employed for modeling fire occurrence accordingly. Moreover, Random Forest (RF), which can manage the nonlinear correlation between predictors and shows steady predictive ability, was adopted. The performance of RF and SE models is discussed. Based on historical fire records of Hefei City as a case study in China, the results indicate that SE models have better predictive ability and among which the spatial autocorrelation model (SAC) is the best. Road density influences fire occurrence the most for SAC, while network distance to fire stations is the most important predictor for RF; they are selected in both models. Semivariograms are employed to explore their abilities to explain the spatial structure of fire occurrence, and the result shows that SAC works much better than RF. We give a further explanation for the generation of residuals between fire density and the common predictors in both models. Therefore, decision makers can make use of our conclusions to manage fire safety at the city scale. Full article

► Figures

Figure 1

Open AccessArticle Land Cover Classification in an Ecuadorian Mountain Geosystem Using a Random Forest Classifier, Spectral Vegetation Indices, and Ancillary Geographic Data

by Johanna E. Ayala-Izurieta, Carmen O. Márquez, Víctor J. García, Celso G. Recalde-Moreno, Marcos V. Rodríguez-Llerena and Diego A. Damián-Carrión

Geosciences 2017, 7(2), 34; doi:10.3390/geosciences7020034

Received: 28 February 2017 / Revised: 19 April 2017 / Accepted: 21 April 2017 / Published: 3 May 2017

Viewed by 337 | PDF Full-text (4485 KB) | HTML Full-text | XML Full-text

Abstract

We presented a methodology to accurately classify mountainous regions in the tropics. These landscapes are complex in terms of their geology, ecosystems, climate and land use. Obtaining accurate maps to assess land cover change is essential. The objectives of this study were to

[...] Read more.

We presented a methodology to accurately classify mountainous regions in the tropics. These landscapes are complex in terms of their geology, ecosystems, climate and land use. Obtaining accurate maps to assess land cover change is essential. The objectives of this study were to (1) map vegetation using the Random Forest Classifier (RFC), spectral vegetation index (SVI), and ancillar geographic data (2) identify important variables that help differentiate vegetation cover, and (3) assess the accuracy of the vegetation cover classification in hard-to-reach Ecuadorian mountain region. We used Landsat 7 ETM+ satellite images of the entire scene, a RFC algorithm, and stratified random sampling. The altitude and the two band enhanced vegetation index (EVI2) provide more information on vegetation cover than the traditional and often use normalized difference vegetation index (NDVI) in other settings. We classified the vegetation cover of mountainous areas within the 1016 km² area of study, at 30 m spatial resolution, using RFC that yielded a land cover map with an overall accuracy of 95%. The user´s accuracy and the half-width of the confidence interval for 95% of the basic map units, forest (FOR), páramo (PAR), crop (CRO) and pasture (PAS) were 95.85% ± 2.86%, 97.64% ± 1.24%, 91.53% ± 3.35% and 82.82% ± 7.74%, respectively. The overall disagreement was 4.47%, which results from adding 0.43% of quantity disagreement and 4.04% of allocation disagreement. The methodological framework presented in this paper and the combined use of SVIs, ancillary geographic data, and the RFC allowed the accurate mapping of hard-to-reach mountain landscapes as well as uncovering the underlying factors that help differentiate vegetation cover in the Ecuadorian mountain geosystem. Full article

► Figures

Figure 1

Open AccessArticle Comparison of Multiple Linear Regression, Cubist Regression, and Random Forest Algorithms to Estimate Daily Air Surface Temperature from Dynamic Combinations of MODIS LST Data

by Phan Thanh Noi, Jan Degener and Martin Kappas

Remote Sens. 2017, 9(5), 398; doi:10.3390/rs9050398

Received: 7 March 2017 / Revised: 12 April 2017 / Accepted: 21 April 2017 / Published: 25 April 2017

Cited by 1 | Viewed by 643 | PDF Full-text (5484 KB) | HTML Full-text | XML Full-text

Abstract

Recently, several methods have been introduced and applied to estimate daily air surface temperature (T_a) using MODIS land surface temperature data (MODIS LST). Among these methods, the most common used method is statistical modeling, and the most applied algorithms are linear/multiple

[...] Read more.

Recently, several methods have been introduced and applied to estimate daily air surface temperature (T_a) using MODIS land surface temperature data (MODIS LST). Among these methods, the most common used method is statistical modeling, and the most applied algorithms are linear/multiple linear regression models (LM). There are only a handful of studies using machine learning algorithm models such as random forest (RF) or cubist regression (CB). In particular, there is no study comparing different combinations of four MODIS LST datasets with or without auxiliary data using different algorithms such as multiple linear regression, random forest, and cubist regression for daily T_a-max, T_a-min, and T_a-mean estimation. Our study examines the mentioned combinations of four MODIS-LST datasets and shows that different combinations and differently applied algorithms produce various T_a estimation accuracies. Additional analysis of daily data from three climate stations in the mountain area of North West of Vietnam for the period of five years (2009 to 2013) with four MODIS LST datasets (AQUA daytime, AQUA nighttime, TERRA daytime, and TERRA nighttime) and two additional auxiliary datasets (elevation and Julian day) shows that CB and LM should be applied if MODIS LST data is used solely. If MODIS LST is used together with auxiliary data, especially in mountainous areas, CB or RF is highly recommended. This study proved that the very high accuracy of T_a estimation (R² > 0.93/0.80/0.89 and RMSE ~1.5/2.0/1.6 °C of T_a-max, T_a-min, and T_a-mean, respectively) could be achieved with a simple combination of four LST data, elevation, and Julian day data using a suitable algorithm. Full article

► Figures

Open AccessFeature PaperArticle Comparison and Evaluation of Three Methods for Estimating Forest above Ground Biomass Using TM and GLAS Data

by Kaili Liu, Jindi Wang, Weisheng Zeng and Jinling Song

Remote Sens. 2017, 9(4), 341; doi:10.3390/rs9040341

Received: 21 December 2016 / Revised: 29 March 2017 / Accepted: 31 March 2017 / Published: 2 April 2017

Viewed by 470 | PDF Full-text (6426 KB) | HTML Full-text | XML Full-text

Abstract

Medium spatial resolution biomass is a crucial link from the plot to regional and global scales. Although remote-sensing data-based methods have become a primary approach in estimating forest above ground biomass (AGB), many difficulties remain in data resources and prediction approaches. Each kind

[...] Read more.

Medium spatial resolution biomass is a crucial link from the plot to regional and global scales. Although remote-sensing data-based methods have become a primary approach in estimating forest above ground biomass (AGB), many difficulties remain in data resources and prediction approaches. Each kind of sensor type and prediction method has its own merits and limitations. To select the proper estimation algorithm and remote-sensing data source, several forest AGB models were developed using different remote-sensing data sources (Geoscience Laser Altimeter System (GLAS) data and Thematic Mapper (TM) data) and 108 field measurements. Three modeling methods (stepwise regression (SR), support vector regression (SVR) and random forest (RF)) were used to estimate forest AGB over the Daxing’anling Mountains in northeastern China. The results of models using different datasets and three approaches were compared. The random forest AGB model using Landsat5/TM as input data was shown the acceptable modeling accuracy (R² = 0.95 RMSE = 17.73 Mg/ha) and it was also shown to estimate AGB reliably by cross validation (R² = 0.71 RMSE = 39.60 Mg/ha). The results also indicated that adding GLAS data significantly improved AGB predictions for the SVR and SR AGB models. In the case of the RF AGB models, including GLAS data no longer led to significant improvement. Finally, a forest biomass map with spatial resolution of 30 m over the Daxing'anling Mountains was generated using the obtained optimal model. Full article

(This article belongs to the Special Issue Remote Sensing of Above Ground Biomass)

► Figures

Open AccessArticle Object-Oriented Landslide Mapping Using ZY-3 Satellite Imagery, Random Forest and Mathematical Morphology, for the Three-Gorges Reservoir, China

by Tao Chen, John C. Trinder and Ruiqing Niu

Remote Sens. 2017, 9(4), 333; doi:10.3390/rs9040333

Received: 9 January 2017 / Revised: 27 March 2017 / Accepted: 29 March 2017 / Published: 31 March 2017

Viewed by 493 | PDF Full-text (4099 KB) | HTML Full-text | XML Full-text

Abstract

Landslide mapping (LM) has recently become an important research topic in remote sensing and geohazards. The area near the Three Gorges Reservoir (TGR) along the Yangtze River in China is one of the most landslide-prone regions in the world, and the area has

[...] Read more.

Landslide mapping (LM) has recently become an important research topic in remote sensing and geohazards. The area near the Three Gorges Reservoir (TGR) along the Yangtze River in China is one of the most landslide-prone regions in the world, and the area has suffered widespread and significant landslide events in recent years. In our study, an object-oriented landslide mapping (OOLM) framework was proposed for reliable and accurate LM from ‘ZY-3’ high spatial resolution (HSR) satellite images. The framework was based on random forests (RF) and mathematical morphology (MM). RF was first applied as an object feature information reduction tool to identify the significant features for describing landslides, and it was then combined with MM to map the landslides. Three object-feature domains were extracted from the ‘ZY-3’ HSR data: layer information, texture, and geometric features. A total group of 124 features and 24 landslides were used as inputs to determine the landslide boundaries and evaluate the landslide classification accuracy. The results showed that: (1) the feature selection (FS) method had a positive influence on effective landslide mapping; (2) by dividing the data into two sets, training sets which consisted of 20% of the landslide objects (O_LS) and non-landslide objects (O_NLS), and test sets which consisted of the remaining 80% of the O_LS and O_NLS, the selected feature subsets were combined for training to obtain an overall classification accuracy of 93.3% ± 0.12% of the test sets; (3) four MM operations based on closing and opening were used to improve the performance of the RF classification. Seven accuracy evaluation indices were used to compare the accuracies of these landslide mapping methods. Finally, the landslide inventory maps were obtained. Based on its efficiency and accuracy, the proposed approach can be employed for rapid response to natural hazards in the Three Gorges area. Full article

(This article belongs to the Special Issue Remote Sensing of Landslides)

► Figures

Open AccessArticle Combining Spectral Data and a DSM from UAS-Images for Improved Classification of Non-Submerged Aquatic Vegetation

by Eva Husson, Heather Reese and Frauke Ecke

Remote Sens. 2017, 9(3), 247; doi:10.3390/rs9030247

Received: 30 November 2016 / Revised: 17 February 2017 / Accepted: 1 March 2017 / Published: 7 March 2017

Viewed by 483 | PDF Full-text (2174 KB) | HTML Full-text | XML Full-text | Supplementary Files

Abstract

Monitoring of aquatic vegetation is an important component in the assessment of freshwater ecosystems. Remote sensing with unmanned aircraft systems (UASs) can provide sub-decimetre-resolution aerial images and is a useful tool for detailed vegetation mapping. In a previous study, non-submerged aquatic vegetation was

[...] Read more.

Monitoring of aquatic vegetation is an important component in the assessment of freshwater ecosystems. Remote sensing with unmanned aircraft systems (UASs) can provide sub-decimetre-resolution aerial images and is a useful tool for detailed vegetation mapping. In a previous study, non-submerged aquatic vegetation was successfully mapped using automated classification of spectral and textural features from a true-colour UAS-orthoimage with 5-cm pixels. In the present study, height data from a digital surface model (DSM) created from overlapping UAS-images has been incorporated together with the spectral and textural features from the UAS-orthoimage to test if classification accuracy can be improved further. We studied two levels of thematic detail: (a) Growth forms including the classes of water, nymphaeid, and helophyte; and (b) dominant taxa including seven vegetation classes. We hypothesized that the incorporation of height data together with spectral and textural features would increase classification accuracy as compared to using spectral and textural features alone, at both levels of thematic detail. We tested our hypothesis at five test sites (100 m × 100 m each) with varying vegetation complexity and image quality using automated object-based image analysis in combination with Random Forest classification. Overall accuracy at each of the five test sites ranged from 78% to 87% at the growth-form level and from 66% to 85% at the dominant-taxon level. In comparison to using spectral and textural features alone, the inclusion of height data increased the overall accuracy significantly by 4%–21% for growth-forms and 3%–30% for dominant taxa. The biggest improvement gained by adding height data was observed at the test site with the most complex vegetation. Height data derived from UAS-images has a large potential to efficiently increase the accuracy of automated classification of non-submerged aquatic vegetation, indicating good possibilities for operative mapping. Full article

(This article belongs to the Special Issue Recent Trends in UAV Remote Sensing)

► Figures

Open AccessArticle Evaluation of Feature Selection Methods for Object-Based Land Cover Mapping of Unmanned Aerial Vehicle Imagery Using Random Forest and Support Vector Machine Classifiers

by Lei Ma, Tengyu Fu, Thomas Blaschke, Manchun Li, Dirk Tiede, Zhenjin Zhou, Xiaoxue Ma and Deliang Chen

ISPRS Int. J. Geo-Inf. 2017, 6(2), 51; doi:10.3390/ijgi6020051

Received: 29 December 2016 / Revised: 10 February 2017 / Accepted: 15 February 2017 / Published: 18 February 2017

Cited by 2 | Viewed by 509 | PDF Full-text (4379 KB) | HTML Full-text | XML Full-text

Abstract

The increased feature space available in object-based classification environments (e.g., extended spectral feature sets per object, shape properties, or textural features) has a high potential of improving classifications. However, the availability of a large number of derived features per segmented object can also

[...] Read more.

The increased feature space available in object-based classification environments (e.g., extended spectral feature sets per object, shape properties, or textural features) has a high potential of improving classifications. However, the availability of a large number of derived features per segmented object can also lead to a time-consuming and subjective process of optimizing the feature subset. The objectives of this study are to evaluate the effect of the advanced feature selection methods of popular supervised classifiers (Support Vector Machines (SVM) and Random Forest (RF)) for the example of object-based mapping of an agricultural area using Unmanned Aerial Vehicle (UAV) imagery, in order to optimize their usage for object-based agriculture pattern recognition tasks. In this study, several advanced feature selection methods were divided into both types of classifiers (SVM and RF) to conduct further evaluations using five feature-importance-evaluation methods and three feature-subset-evaluation methods. A visualization method was used to measure the change pattern of mean classification accuracy with the increase of features used, and a two-tailed t-test was used to determine the difference between two population means for both repeated ten classification accuracies. This study mainly contribute to the uncertainty analysis of feature selection for object-based classification instead of the per-pixel method. The results highlight that the RF classifier is relatively insensitive to the number of input features, even for a small training set size, whereby a negative impact of feature set size on the classification accuracy of the SVM classifier was observed. Overall, the SVM Recursive Feature Elimination (SVM-RFE) seems to be an appropriate method for both groups of classifiers, while the Correlation-based Feature Selection (CFS) is the best feature-subset-evaluation method. Most importantly, this study verified that feature selection for both classifiers is crucial for the evolving field of Object-based Image Analysis (OBIA): It is highly advisable for feature selection to be performed before object-based classification, even though an adverse impact could sometimes be observed from the wrapper methods. Full article

► Figures

Figure 1

Open AccessArticle A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts

by Yalan Ye, Wenwen He, Yunfei Cheng, Wenxia Huang and Zhilin Zhang

Sensors 2017, 17(2), 385; doi:10.3390/s17020385

Received: 23 December 2016 / Revised: 4 February 2017 / Accepted: 12 February 2017 / Published: 16 February 2017

Viewed by 455 | PDF Full-text (1215 KB) | HTML Full-text | XML Full-text

Abstract

The estimation of heart rate (HR) based on wearable devices is of interest in fitness. Photoplethysmography (PPG) is a promising approach to estimate HR due to low cost; however, it is easily corrupted by motion artifacts (MA). In this work, a robust approach

[...] Read more.

The estimation of heart rate (HR) based on wearable devices is of interest in fitness. Photoplethysmography (PPG) is a promising approach to estimate HR due to low cost; however, it is easily corrupted by motion artifacts (MA). In this work, a robust approach based on random forest is proposed for accurately estimating HR from the photoplethysmography signal contaminated by intense motion artifacts, consisting of two stages. Stage 1 proposes a hybrid method to effectively remove MA with a low computation complexity, where two MA removal algorithms are combined by an accurate binary decision algorithm whose aim is to decide whether or not to adopt the second MA removal algorithm. Stage 2 proposes a random forest-based spectral peak-tracking algorithm, whose aim is to locate the spectral peak corresponding to HR, formulating the problem of spectral peak tracking into a pattern classification problem. Experiments on the PPG datasets including 22 subjects used in the 2015 IEEE Signal Processing Cup showed that the proposed approach achieved the average absolute error of 1.65 beats per minute (BPM) on the 22 PPG datasets. Compared to state-of-the-art approaches, the proposed approach has better accuracy and robustness to intense motion artifacts, indicating its potential use in wearable sensors for health monitoring and fitness tracking. Full article

(This article belongs to the Special Issue Sensing Technology for Healthcare System)

► Figures

Figure 1

Open AccessArticle Topographic Correction of Landsat TM-5 and Landsat OLI-8 Imagery to Improve the Performance of Forest Classification in the Mountainous Terrain of Northeast Thailand

by Uday Pimple, Asamaporn Sitthi, Dario Simonetti, Sukan Pungkul, Kumron Leadprathom and Amnat Chidthaisong

Sustainability 2017, 9(2), 258; doi:10.3390/su9020258

Received: 10 November 2016 / Revised: 7 February 2017 / Accepted: 9 February 2017 / Published: 12 February 2017

Viewed by 691 | PDF Full-text (17282 KB) | HTML Full-text | XML Full-text

Abstract

The accurate mapping and monitoring of forests is essential for the sustainable management of forest ecosystems. Advancements in the Landsat satellite series have been very useful for various forest mapping applications. However, the topographic shadows of irregular mountains are major obstacles to accurate

[...] Read more.

The accurate mapping and monitoring of forests is essential for the sustainable management of forest ecosystems. Advancements in the Landsat satellite series have been very useful for various forest mapping applications. However, the topographic shadows of irregular mountains are major obstacles to accurate forest classification. In this paper, we test five topographic correction methods: improved cosine correction, Minnaert, C-correction, Statistical Empirical Correction (SEC) and Variable Empirical Coefficient Algorithm (VECA), with multisource digital elevation models (DEM) to reduce the topographic relief effect in mountainous terrain produced by the Landsat Thematic Mapper (TM)-5 and Operational Land Imager (OLI)-8 sensors. The effectiveness of the topographic correction methods are assessed by visual interpretation and the reduction in standard deviation (SD), by means of the coefficient of variation (CV). Results show that the SEC performs best with the Shuttle Radar Topographic Mission (SRTM) 30 m × 30 m DEM. The random forest (RF) classifier is used for forest classification, and the overall accuracy of forest classification is evaluated to compare the performances of the topographic corrections. Our results show that the C-correction, SEC and VECA corrected imagery were able to improve the forest classification accuracy of Landsat TM-5 from 78.41% to 81.50%, 82.38%, and 81.50%, respectively, and OLI-8 from 81.06% to 81.50%, 82.38%, and 81.94%, respectively. The highest accuracy of forest type classification is obtained with the newly available high-resolution SRTM DEM and SEC method. Full article

(This article belongs to the Special Issue Sustainability in the Mountains Region)

► Figures

Figure 1

Open AccessArticle Single-Sensor Solution to Tree Species Classiﬁcation Using Multispectral Airborne Laser Scanning

by Xiaowei Yu, Juha Hyyppä, Paula Litkey, Harri Kaartinen, Mikko Vastaranta and Markus Holopainen

Remote Sens. 2017, 9(2), 108; doi:10.3390/rs9020108

Received: 20 October 2016 / Accepted: 20 January 2017 / Published: 27 January 2017

Cited by 1 | Viewed by 1017 | PDF Full-text (2475 KB) | HTML Full-text | XML Full-text

Abstract

This paper investigated the potential of multispectral airborne laser scanning (ALS) data for individual tree detection and tree species classification. The aim was to develop a single-sensorsolution for forest mapping that is capable of providing species-specific information, required for forest management and planning

[...] Read more.

This paper investigated the potential of multispectral airborne laser scanning (ALS) data for individual tree detection and tree species classification. The aim was to develop a single-sensorsolution for forest mapping that is capable of providing species-specific information, required for forest management and planning purposes. Experiments were conducted using 1903 ground measured trees from 22 sample plots and multispectral ALS data, acquired with an Optech Titan scanner over a boreal forest, mainly consisting of Scots pine (Pinus Sylvestris), Norway spruce (Picea Abies), and birch (Betula sp.), in southern Finland. ALS-features used as predictors for tree species were extracted from segmented tree objects and used in random forest classification. Different combinations of features, including point cloud features, and intensity features of single and multiple channels, were tested. Among the field-measured trees, 61.3% were correctly detected. The best overall accuracy (OA) of tree species classification achieved for correctly-detected trees was 85.9% (Kappa = 0.75), using a point cloud and single-channel intensity features combination, which was not significantly different from the ones that were obtained either using all features (OA = 85.6%, Kappa = 0.75), or single-channel intensity features alone (OA = 85.4%, Kappa = 0.75). Point cloud features alone achieved the lowest accuracy, with an OA of 76.0%. Field-measured trees were also divided into four categories. An examination of the classification accuracy for four categories of trees showed that isolated and dominant trees can be detected with a detection rate of 91.9%, and classified with a high overall accuracy of 90.5%. The corresponding detection rate and accuracy were 81.5% and 89.8% for a group of trees, 26.4% and 79.1% for trees next to a larger tree, and 7.2% and 53.9% for trees situated under a larger tree, respectively. The results suggest that Channel 2 (1064 nm) contains more information for separating pine, spruce, and birch, followed by channel 1 (1550 nm) and channel 3 (532 nm) with an overall accuracy of 81.9%, 78.3%, and 69.1%, respectively. Our results indicate that the use of multispectral ALS data has great potential to lead to a single-sensor solution for forest mapping. Full article

► Figures

Open AccessArticle Mapping Deforestation in North Korea Using Phenology-Based Multi-Index and Random Forest

by Yihua Jin, Sunyong Sung, Dong Kun Lee, Gregory S. Biging and Seunggyu Jeong

Remote Sens. 2016, 8(12), 997; doi:10.3390/rs8120997

Received: 26 August 2016 / Revised: 25 November 2016 / Accepted: 29 November 2016 / Published: 3 December 2016

Viewed by 1059 | PDF Full-text (6516 KB) | HTML Full-text | XML Full-text

Abstract

Phenology-based multi-index with the random forest (RF) algorithm can be used to overcome the shortcomings of traditional deforestation mapping that involves pixel-based classification, such as ISODATA or decision trees, and single images. The purpose of this study was to investigate methods to identify

[...] Read more.

Phenology-based multi-index with the random forest (RF) algorithm can be used to overcome the shortcomings of traditional deforestation mapping that involves pixel-based classification, such as ISODATA or decision trees, and single images. The purpose of this study was to investigate methods to identify specific types of deforestation in North Korea, and to increase the accuracy of classification, using phenological characteristics extracted with multi-index and random forest algorithms. The mapping of deforestation area based on RF was carried out by merging phenology-based multi-indices (i.e., normalized difference vegetation index (NDVI), normalized difference water index (NDWI), and normalized difference soil index (NDSI)) derived from MODIS (Moderate Resolution Imaging Spectroradiometer) products and topographical variables. Our results showed overall classification accuracy of 89.38%, with corresponding kappa coefficients of 0.87. In particular, for forest and farm land categories with similar phenological characteristic (e.g., paddy, plateau vegetation, unstocked forest, hillside field), this approach improved the classification accuracy in comparison with pixel-based methods and other classes. The deforestation types were identified by incorporating point data from high-resolution imagery, outcomes of image classification, and slope data. Our study demonstrated that the proposed methodology could be used for deciding on the restoration priority and monitoring the expansion of deforestation areas. Full article

(This article belongs to the Special Issue Land Surface Phenology and Seasonality: Novel Approaches and Applications)

► Figures

Open AccessArticle Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China

by Shaohong Tian, Xianfeng Zhang, Jie Tian and Quan Sun

Remote Sens. 2016, 8(11), 954; doi:10.3390/rs8110954

Received: 17 June 2016 / Revised: 7 November 2016 / Accepted: 8 November 2016 / Published: 16 November 2016

Viewed by 624 | PDF Full-text (4190 KB) | HTML Full-text | XML Full-text

Abstract

The wetland classification from remotely sensed data is usually difficult due to the extensive seasonal vegetation dynamics and hydrological fluctuation. This study presents a random forest classification approach for the retrieval of the wetland landcover in the arid regions by fusing the Pléiade-1B

[...] Read more.

The wetland classification from remotely sensed data is usually difficult due to the extensive seasonal vegetation dynamics and hydrological fluctuation. This study presents a random forest classification approach for the retrieval of the wetland landcover in the arid regions by fusing the Pléiade-1B data with multi-date Landsat-8 data. The segmentation of the Pléiade-1B multispectral image data was performed based on an object-oriented approach, and the geometric and spectral features were extracted for the segmented image objects. The normalized difference vegetation index (NDVI) series data were also calculated from the multi-date Landsat-8 data, reflecting vegetation phenological changes in its growth cycle. The feature set extracted from the two sensors data was optimized and employed to create the random forest model for the classification of the wetland landcovers in the Ertix River in northern Xinjiang, China. Comparison with other classification methods such as support vector machine and artificial neural network classifiers indicates that the random forest classifier can achieve accurate classification with an overall accuracy of 93% and the Kappa coefficient of 0.92. The classification accuracy of the farming lands and water bodies that have distinct boundaries with the surrounding land covers was improved 5%–10% by making use of the property of geometric shapes. To remove the difficulty in the classification that was caused by the similar spectral features of the vegetation covers, the phenological difference and the textural information of co-occurrence gray matrix were incorporated into the classification, and the main wetland vegetation covers in the study area were derived from the two sensors data. The inclusion of phenological information in the classification enables the classification errors being reduced down, and the overall accuracy was improved approximately 10%. The results show that the proposed random forest classification by fusing multi-sensor data can retrieve better wetland landcover information than the other classifiers, which is significant for the monitoring and management of the wetland ecological resources in arid areas. Full article

► Figures

Open AccessArticle Rapid Land Cover Map Updates Using Change Detection and Robust Random Forest Classifiers

by Konrad J. Wessels, Frans van den Bergh, David P. Roy, Brian P. Salmon, Karen C. Steenkamp, Bryan MacAlister, Derick Swanepoel and Debbie Jewitt

Remote Sens. 2016, 8(11), 888; doi:10.3390/rs8110888

Received: 16 August 2016 / Revised: 17 October 2016 / Accepted: 21 October 2016 / Published: 28 October 2016

Cited by 1 | Viewed by 985 | PDF Full-text (2885 KB) | HTML Full-text | XML Full-text

Abstract

The paper evaluated the Landsat Automated Land Cover Update Mapping (LALCUM) system designed to rapidly update a land cover map to a desired nominal year using a pre-existing reference land cover map. The system uses the Iteratively Reweighted Multivariate Alteration Detection (IRMAD) to

[...] Read more.

The paper evaluated the Landsat Automated Land Cover Update Mapping (LALCUM) system designed to rapidly update a land cover map to a desired nominal year using a pre-existing reference land cover map. The system uses the Iteratively Reweighted Multivariate Alteration Detection (IRMAD) to identify areas of change and no change. The system then automatically generates large amounts of training samples (n > 1 million) in the no-change areas as input to an optimized Random Forest classifier. Experiments were conducted in the KwaZulu-Natal Province of South Africa using a reference land cover map from 2008, a change mask between 2008 and 2011 and Landsat ETM+ data for 2011. The entire system took 9.5 h to process. We expected that the use of the change mask would improve classification accuracy by reducing the number of mislabeled training data caused by land cover change between 2008 and 2011. However, this was not the case due to exceptional robustness of Random Forest classifier to mislabeled training samples. The system achieved an overall accuracy of 65%–67% using 22 detailed classes and 72%–74% using 12 aggregated national classes. “Water”, “Plantations”, “Plantations—clearfelled”, “Orchards—trees”, “Sugarcane”, “Built-up/dense settlement”, “Cultivation—Irrigated” and “Forest (indigenous)” had user’s accuracies above 70%. Other detailed classes (e.g., “Low density settlements”, “Mines and Quarries”, and “Cultivation, subsistence, drylands”) which are required for operational, provincial-scale land use planning and are usually mapped using manual image interpretation, could not be mapped using Landsat spectral data alone. However, the system was able to map the 12 national classes, at a sufficiently high level of accuracy for national scale land cover monitoring. This update approach and the highly automated, scalable LALCUM system can improve the efficiency and update rate of regional land cover mapping. Full article

► Figures

Open AccessArticle A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest

by Nantian Huang, Guobo Lu and Dianguo Xu

Energies 2016, 9(10), 767; doi:10.3390/en9100767

Received: 15 June 2016 / Revised: 4 September 2016 / Accepted: 14 September 2016 / Published: 22 September 2016

Cited by 3 | Viewed by 482 | PDF Full-text (5456 KB) | HTML Full-text | XML Full-text

Abstract

The prediction accuracy of short-term load forecast (STLF) depends on prediction model choice and feature selection result. In this paper, a novel random forest (RF)-based feature selection method for STLF is proposed. First, 243 related features were extracted from historical load data and

[...] Read more.

The prediction accuracy of short-term load forecast (STLF) depends on prediction model choice and feature selection result. In this paper, a novel random forest (RF)-based feature selection method for STLF is proposed. First, 243 related features were extracted from historical load data and the time information of prediction points to form the original feature set. Subsequently, the original feature set was used to train an RF as the original model. After the training process, the prediction error of the original model on the test set was recorded and the permutation importance (PI) value of each feature was obtained. Then, an improved sequential backward search method was used to select the optimal forecasting feature subset based on the PI value of each feature. Finally, the optimal forecasting feature subset was used to train a new RF model as the final prediction model. Experiments showed that the prediction accuracy of RF trained by the optimal forecasting feature subset was higher than that of the original model and comparative models based on support vector regression and artificial neural network. Full article

(This article belongs to the Special Issue Energy Time Series Forecasting)

► Figures

Figure 1

Open AccessArticle Comparison of Manual Mapping and Automated Object-Based Image Analysis of Non-Submerged Aquatic Vegetation from Very-High-Resolution UAS Images

by Eva Husson, Frauke Ecke and Heather Reese

Remote Sens. 2016, 8(9), 724; doi:10.3390/rs8090724

Received: 3 May 2016 / Revised: 22 August 2016 / Accepted: 29 August 2016 / Published: 1 September 2016

Abstract

Aquatic vegetation has important ecological and regulatory functions and should be monitored in order to detect ecosystem changes. Field data collection is often costly and time-consuming; remote sensing with unmanned aircraft systems (UASs) provides aerial images with sub-decimetre resolution and offers a potential

[...] Read more.

Aquatic vegetation has important ecological and regulatory functions and should be monitored in order to detect ecosystem changes. Field data collection is often costly and time-consuming; remote sensing with unmanned aircraft systems (UASs) provides aerial images with sub-decimetre resolution and offers a potential data source for vegetation mapping. In a manual mapping approach, UAS true-colour images with 5-cm-resolution pixels allowed for the identification of non-submerged aquatic vegetation at the species level. However, manual mapping is labour-intensive, and while automated classification methods are available, they have rarely been evaluated for aquatic vegetation, particularly at the scale of individual vegetation stands. We evaluated classification accuracy and time-efficiency for mapping non-submerged aquatic vegetation at three levels of detail at five test sites (100 m × 100 m) differing in vegetation complexity. We used object-based image analysis and tested two classification methods (threshold classification and Random Forest) using eCognition^®. The automated classification results were compared to results from manual mapping. Using threshold classification, overall accuracy at the five test sites ranged from 93% to 99% for the water-versus-vegetation level and from 62% to 90% for the growth-form level. Using Random Forest classification, overall accuracy ranged from 56% to 94% for the growth-form level and from 52% to 75% for the dominant-taxon level. Overall classification accuracy decreased with increasing vegetation complexity. In test sites with more complex vegetation, automated classification was more time-efficient than manual mapping. This study demonstrated that automated classification of non-submerged aquatic vegetation from true-colour UAS images was feasible, indicating good potential for operative mapping of aquatic vegetation. When choosing the preferred mapping method (manual versus automated) the desired level of thematic detail and the required accuracy for the mapping task needs to be considered. Full article

(This article belongs to the Special Issue Recent Trends in UAV Remote Sensing)

► Figures

Open AccessArticle Quantifying Live Aboveground Biomass and Forest Disturbance of Mountainous Natural and Plantation Forests in Northern Guangdong, China, Based on Multi-Temporal Landsat, PALSAR and Field Plot Data

by Wenjuan Shen, Mingshi Li, Chengquan Huang and Anshi Wei

Remote Sens. 2016, 8(7), 595; doi:10.3390/rs8070595

Received: 23 May 2016 / Revised: 28 June 2016 / Accepted: 7 July 2016 / Published: 13 July 2016

Cited by 4 | Viewed by 725 | PDF Full-text (8984 KB) | HTML Full-text | XML Full-text

Abstract

Spatially explicit knowledge of aboveground biomass (AGB) in large areas is important for accurate carbon accounting and quantifying the effect of forest disturbance on the terrestrial carbon cycle. We estimated AGB from 1990 to 2011 in northern Guangdong, China, based on a spatially

[...] Read more.

Spatially explicit knowledge of aboveground biomass (AGB) in large areas is important for accurate carbon accounting and quantifying the effect of forest disturbance on the terrestrial carbon cycle. We estimated AGB from 1990 to 2011 in northern Guangdong, China, based on a spatially explicit dataset derived from six years of national forest inventory (NFI) plots, Landsat time series imagery (1986–2011) and Advanced Land Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radars (PALSAR) 25 m mosaic data (2007–2010). Four types of variables were derived for modeling and assessment. The random forest approach was used to seek the optimal variables for mapping and validation. The root mean square error (RMSE) of plot-level validation was between 6.44 and 39.49 (t/ha), the normalized root-mean-square error (NRMSE) was between 7.49% and 19.01% and mean absolute error (MAE) was between 5.06 and 23.84 t/ha. The highest coefficient of determination R² of 0.8 and the lowest NRMSE of 7.49% were reported in 2006. A clear increasing trend of mean AGB from the lowest value of 13.58 t/ha to the highest value of 66.25 t/ha was witnessed between 1988 and 2000, while after 2000 there was a fluctuating ascending change, with a peak mean AGB of 67.13 t/ha in 2004. By integrating AGB change with forest disturbance, the trend in disturbance area closely corresponded with the trend in AGB decrease. To determine the driving forces of these changes, the correlation analysis was adopted and exploratory factor analysis (EFA) method was used to find a factor rotation that maximizes this variance and represents the dominant factors of nine climate elements and nine human activities elements affecting the AGB dynamics. Overall, human activities contributed more to short-term AGB dynamics than climate data. Harvesting and human-induced fire in combination with rock desertification and global warming made a strong contribution to AGB changes. This study provides valuable information for the relationships between forest AGB and climate as well as forest disturbance in subtropical zones. Full article

(This article belongs to the Special Issue Remote Sensing of Vegetation Structure and Dynamics)

► Figures

Open AccessArticle Using Remote Sensing and Random Forest to Assess the Conservation Status of Critical Cerrado Habitats in Mato Grosso do Sul, Brazil

by Jason Reynolds, Kathryn Wesson, Arnaud L. J. Desbiez, Jose M. Ochoa-Quintero and Peter Leimgruber

Land 2016, 5(2), 12; doi:10.3390/land5020012

Received: 3 March 2016 / Revised: 10 May 2016 / Accepted: 11 May 2016 / Published: 19 May 2016

Cited by 1 | Viewed by 693 | PDF Full-text (2321 KB) | HTML Full-text | XML Full-text

Abstract

Brazil’s Cerrado is a highly diverse ecosystem and it provides critical habitat for many species. Cerrado habitats have suffered significant degradation and decline over the past decades due to expansion of cash crops and livestock farming across South America. Approximately 1,800,000 km²

[...] Read more.

Brazil’s Cerrado is a highly diverse ecosystem and it provides critical habitat for many species. Cerrado habitats have suffered significant degradation and decline over the past decades due to expansion of cash crops and livestock farming across South America. Approximately 1,800,000 km² of the Cerrado remain in Brazil, but detailed maps and conservation assessments of the Cerrado are lacking. We developed a land cover classification for the Cerrado, focusing on the state of Mato Grosso do Sul, which may also be used to map critical habitat for endangered species. We used a Random Forest algorithm to perform a supervised classification on a set of Landsat 8 images. To determine habitat fragmentation for the Cerrado, we used Fragstats. A habitat connectivity analysis was performed using Linkage Mapper. Our final classification had an overall accuracy of 88%. Our classification produced higher accuracies (72%) in predicting Cerrado than existing government maps. We found that remaining Cerrado habitats were severely fragmented. Four potential corridors were identified in the southwest of Mato Grosso do Sul, where large Cerrado patches are located. Only two large patches remain in Mato Grosso do Sul: one within the Kadiwéu Indian Reserve, and one near the southeastern edge of the Pantanal-dominated landscape. These results are alarming for rare species requiring larger tracts of habitat such as the giant armadillo (Priodontes maximus). Full article

Open AccessArticle Examining the Spectral Separability of Prosopis glandulosa from Co-Existent Species Using Field Spectral Measurement and Guided Regularized Random Forest

by Nyasha Mureriwa, Elhadi Adam, Anshuman Sahu and Solomon Tesfamichael

Remote Sens. 2016, 8(2), 144; doi:10.3390/rs8020144

Received: 10 December 2015 / Revised: 23 January 2016 / Accepted: 4 February 2016 / Published: 15 February 2016

Viewed by 999 | PDF Full-text (2622 KB) | HTML Full-text | XML Full-text

Abstract

The invasive taxa of Prosopis is rated the world’s top 100 unwanted species, and a lack of spatial data about the invasion dynamics has made the current control and monitoring methods unsuccessful. This study thus tests the use of in situ spectroscopy data

[...] Read more.

The invasive taxa of Prosopis is rated the world’s top 100 unwanted species, and a lack of spatial data about the invasion dynamics has made the current control and monitoring methods unsuccessful. This study thus tests the use of in situ spectroscopy data with a newly-developed algorithm, guided regularized random forest (GRRF), to spectrally discriminate Prosopis from coexistent acacia species (Acacia karroo, Acacia mellifera and Ziziphus mucronata) in the arid environment of South Africa. Results show that GRRF was able to reduce the high dimensionality of the spectroscopy data and select key wavelengths (n = 11) for discriminating amongst the species. These wavelengths are located at 356.3 nm, 468.5 nm, 531.1 nm, 665.2 nm, 1262.3 nm, 1354.1 nm, 1361.7 nm, 1376.9 nm, 1407.1 nm, 1410.9 nm and 1414.6 nm. The use of these selected wavelengths increases the overall classification accuracy from 79.19% and a Kappa value of 0.7201 when using all wavelengths to 88.59% and a Kappa of 0.8524 when the selected wavelengths were used. Based on our relatively high accuracies and ease of use, it is worth considering the GRRF method for reducing the high dimensionality of spectroscopy data. However, this assertion should receive considerable additional testing and comparison before it is accepted as a substitute for reliable high dimensionality reduction. Full article

(This article belongs to the Special Issue Field Spectroscopy and Radiometry)

► Figures

Open AccessArticle Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

by Nantian Huang, Guobo Lu, Guowei Cai, Dianguo Xu, Jiafeng Xu, Fuqing Li and Liying Zhang

Entropy 2016, 18(2), 44; doi:10.3390/e18020044

Received: 4 November 2015 / Revised: 3 January 2016 / Accepted: 18 January 2016 / Published: 28 January 2016

Cited by 1 | Viewed by 836 | PDF Full-text (2212 KB) | HTML Full-text | XML Full-text

Abstract

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds

[...] Read more.

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%. Full article

(This article belongs to the Special Issue Machine Learning and Entropy: Discover Unknown Unknowns in Complex Data Sets)

Open AccessArticle A Quantitative Assessment of Forest Cover Change in the Moulouya River Watershed (Morocco) by the Integration of a Subpixel-Based and Object-Based Analysis of Landsat Data

by Fernando J. Aguilar, Abderrahim Nemmaoui, Manuel A. Aguilar, Mimoun Chourak, Yassine Zarhloule and Andrés M. García Lorca

Forests 2016, 7(1), 23; doi:10.3390/f7010023

Received: 5 November 2015 / Revised: 6 January 2016 / Accepted: 7 January 2016 / Published: 15 January 2016

Viewed by 1152 | PDF Full-text (2836 KB) | HTML Full-text | XML Full-text

Abstract

A quantitative assessment of forest cover change in the Moulouya River watershed (Morocco) was carried out by means of an innovative approach from atmospherically corrected reflectance Landsat images corresponding to 1984 (Landsat 5 Thematic Mapper) and 2013 (Landsat 8 Operational Land Imager). An

[...] Read more.

A quantitative assessment of forest cover change in the Moulouya River watershed (Morocco) was carried out by means of an innovative approach from atmospherically corrected reflectance Landsat images corresponding to 1984 (Landsat 5 Thematic Mapper) and 2013 (Landsat 8 Operational Land Imager). An object-based image analysis (OBIA) was undertaken to classify segmented objects as forested or non-forested within the 2013 Landsat orthomosaic. A Random Forest classifier was applied to a set of training data based on a features vector composed of different types of object features such as vegetation indices, mean spectral values and pixel-based fractional cover derived from probabilistic spectral mixture analysis). The very high spatial resolution image data of Google Earth 2013 were employed to train/validate the Random Forest classifier, ranking the NDVI vegetation index and the corresponding pixel-based percentages of photosynthetic vegetation and bare soil as the most statistically significant object features to extract forested and non-forested areas. Regarding classification accuracy, an overall accuracy of 92.34% was achieved. The previously developed classification scheme was applied to the 1984 Landsat data to extract the forest cover change between 1984 and 2013, showing a slight net increase of 5.3% (ca. 8800 ha) in forested areas for the whole region. Full article

Open AccessArticle Random Forest-Based Recognition of Isolated Sign Language Subwords Using Data from Accelerometers and Surface Electromyographic Sensors

by Ruiliang Su, Xiang Chen, Shuai Cao and Xu Zhang

Sensors 2016, 16(1), 100; doi:10.3390/s16010100

Received: 12 November 2015 / Revised: 10 January 2016 / Accepted: 12 January 2016 / Published: 14 January 2016

Cited by 4 | Viewed by 1187 | PDF Full-text (1883 KB) | HTML Full-text | XML Full-text

Abstract

Sign language recognition (SLR) has been widely used for communication amongst the hearing-impaired and non-verbal community. This paper proposes an accurate and robust SLR framework using an improved decision tree as the base classifier of random forests. This framework was used to recognize

[...] Read more.

Sign language recognition (SLR) has been widely used for communication amongst the hearing-impaired and non-verbal community. This paper proposes an accurate and robust SLR framework using an improved decision tree as the base classifier of random forests. This framework was used to recognize Chinese sign language subwords using recordings from a pair of portable devices worn on both arms consisting of accelerometers (ACC) and surface electromyography (sEMG) sensors. The experimental results demonstrated the validity of the proposed random forest-based method for recognition of Chinese sign language (CSL) subwords. With the proposed method, 98.25% average accuracy was obtained for the classification of a list of 121 frequently used CSL subwords. Moreover, the random forests method demonstrated a superior performance in resisting the impact of bad training samples. When the proportion of bad samples in the training set reached 50%, the recognition error rate of the random forest-based method was only 10.67%, while that of a single decision tree adopted in our previous work was almost 27.5%. Our study offers a practical way of realizing a robust and wearable EMG-ACC-based SLR systems. Full article

(This article belongs to the Section Physical Sensors)

Open AccessArticle RAQ–A Random Forest Approach for Predicting Air Quality in Urban Sensing Systems

by Ruiyun Yu, Yu Yang, Leyou Yang, Guangjie Han and Oguti Ann Move

Sensors 2016, 16(1), 86; doi:10.3390/s16010086

Received: 30 September 2015 / Revised: 26 December 2015 / Accepted: 7 January 2016 / Published: 9 January 2016

Cited by 3 | Viewed by 883 | PDF Full-text (5733 KB) | HTML Full-text | XML Full-text

Abstract

Air quality information such as the concentration of PM_2.5 is of great significance for human health and city management. It affects the way of traveling, urban planning, government policies and so on. However, in major cities there is typically only a limited

[...] Read more.

Air quality information such as the concentration of PM_2.5 is of great significance for human health and city management. It affects the way of traveling, urban planning, government policies and so on. However, in major cities there is typically only a limited number of air quality monitoring stations. In the meantime, air quality varies in the urban areas and there can be large differences, even between closely neighboring regions. In this paper, a random forest approach for predicting air quality (RAQ) is proposed for urban sensing systems. The data generated by urban sensing includes meteorology data, road information, real-time traffic status and point of interest (POI) distribution. The random forest algorithm is exploited for data training and prediction. The performance of RAQ is evaluated with real city data. Compared with three other algorithms, this approach achieves better prediction precision. Exciting results are observed from the experiments that the air quality can be inferred with amazingly high accuracy from the data which are obtained from urban sensing. Full article

(This article belongs to the Section Sensor Networks)

Open AccessArticle Assessing the Potential to Operationalize Shoreline Sensitivity Mapping: Classifying Multiple Wide Fine Quadrature Polarized RADARSAT-2 and Landsat 5 Scenes with a Single Random Forest Model

by Sarah Banks, Koreen Millard, Jon Pasher, Murray Richardson, Huili Wang and Jason Duffe

Remote Sens. 2015, 7(10), 13528-13563; doi:10.3390/rs71013528

Received: 10 September 2015 / Revised: 30 September 2015 / Accepted: 10 October 2015 / Published: 19 October 2015

Cited by 2 | Viewed by 1064 | PDF Full-text (1283 KB) | HTML Full-text | XML Full-text

Abstract

The Random Forest algorithm was used to classify 86 Wide Fine Quadrature Polarized RADARSAT-2 scenes, five Landsat 5 scenes, and a Digital Elevation Model covering an area approximately 81,000 km² in size, and representing the entirety of Dease Strait, Coronation Gulf and

[...] Read more.

The Random Forest algorithm was used to classify 86 Wide Fine Quadrature Polarized RADARSAT-2 scenes, five Landsat 5 scenes, and a Digital Elevation Model covering an area approximately 81,000 km² in size, and representing the entirety of Dease Strait, Coronation Gulf and Bathurst Inlet, Nunavut. The focus of this research was to assess the potential to operationalize shoreline sensitivity mapping to inform oil spill response and contingency planning. The impact of varying the training sample size and reducing model data load were evaluated. Results showed that acceptable accuracies could be achieved with relatively few training samples, but that higher accuracies and greater probabilities of correct class assignment were observed with larger sample sizes. Additionally, the number of inputs to the model could be greatly reduced without impacting overall performance. Optimized models reached independent accuracies of 91% for seven land cover types, and classification probabilities between 0.77 and 0.98 (values for latter represent per-class averages generated from independent validation sites). Mixed results were observed when assessing the potential for remote predictive mapping by simulating transferability of the model to scenes without training data. Full article

► Figures

Open AccessArticle The Utility of AISA Eagle Hyperspectral Data and Random Forest Classifier for Flower Mapping

by Elfatih M. Abdel-Rahman, David M. Makori, Tobias Landmann, Rami Piiroinen, Seif Gasim, Petri Pellikka and Suresh K. Raina

Remote Sens. 2015, 7(10), 13298-13318; doi:10.3390/rs71013298

Received: 5 August 2015 / Revised: 18 September 2015 / Accepted: 25 September 2015 / Published: 12 October 2015

Cited by 2 | Viewed by 1022 | PDF Full-text (1167 KB) | HTML Full-text | XML Full-text

Abstract

Knowledge of the floral cycle and the spatial distribution and abundance of flowering plants is important for bee health studies to understand the relationship between landscape and bee hive productivity and honey flow. The key objective of this study was to show how

[...] Read more.

Knowledge of the floral cycle and the spatial distribution and abundance of flowering plants is important for bee health studies to understand the relationship between landscape and bee hive productivity and honey flow. The key objective of this study was to show how AISA Eagle hyperspectral data and random forest (RF) can be optimally utilized to produce flowering and spatially explicit land use/land cover (LULC) maps for a study site in Kenya. AISA Eagle imagery was captured at the early flowering period (January 2014) and at the peak flowering season (February 2013). Data on white and yellow flowering trees as well as LULC classes in the study area were collected and used as ground-truth points. We utilized all 64 AISA Eagle bands and also used variable importance in RF to identify the most important bands in both AISA Eagle data sets. The results showed that flowering was most accurately mapped using the AISA Eagle data from the peak flowering period (85.71%–88.15% overall accuracy for the peak flowering season imagery versus 80.82%–83.67% for the early flowering season). The variable optimization (i.e., variable selection) analysis showed that less than half of the AISA bands (n = 26 for the February 2013 data and n = 21 for the January 2014 data) were important to attain relatively reliable classification accuracies. Our study is an important first step towards the development of operational flower mapping routines and for understanding the relationship between flowering and bees’ foraging behavior. Full article

► Figures

Open AccessArticle Mapping Forest Canopy Height Across Large Areas by Upscaling ALS Estimates with Freely Available Satellite Data

by Phil Wilkes, Simon D. Jones, Lola Suarez, Andrew Mellor, William Woodgate, Mariela Soto-Berelov, Andrew Haywood and Andrew K. Skidmore

Remote Sens. 2015, 7(9), 12563-12587; doi:10.3390/rs70912563

Received: 29 July 2015 / Accepted: 15 September 2015 / Published: 23 September 2015

Cited by 9 | Viewed by 1082 | PDF Full-text (1193 KB) | HTML Full-text | XML Full-text

Abstract

Operational assessment of forest structure is an on-going challenge for land managers, particularly over large, remote or inaccessible areas. Here, we present an easily adopted method for generating a continuous map of canopy height at a 30 m resolution, demonstrated over 2.9 million

[...] Read more.

Operational assessment of forest structure is an on-going challenge for land managers, particularly over large, remote or inaccessible areas. Here, we present an easily adopted method for generating a continuous map of canopy height at a 30 m resolution, demonstrated over 2.9 million hectares of highly heterogeneous forest (canopy height 0–70 m) in Victoria, Australia. A two-stage approach was utilized where Airborne Laser Scanning (ALS) derived canopy height, captured over ~18% of the study area, was used to train a regression tree ensemble method; random forest. Predictor variables, which have a global coverage and are freely available, included Landsat Thematic Mapper (Tasselled Cap transformed), Moderate Resolution Imaging Spectroradiometer Normalized Difference Vegetation Index time series, Shuttle Radar Topography Mission elevation data and other ancillary datasets. Reflectance variables were further processed to extract additional spatial and temporal contextual and textural variables. Modeled canopy height was validated following two approaches; (i) random sample cross validation; and (ii) with 108 inventory plots from outside the ALS capture extent. Both the cross validation and comparison with inventory data indicate canopy height can be estimated with a Root Mean Square Error (RMSE) of ≤ 31% (~5.6 m) at the 95th percentile confidence interval. Subtraction of the systematic component of model error, estimated from training data error residuals, rescaled canopy height values to more accurately represent the response variable distribution tails e.g., tall and short forest. Two further experiments were carried out to test the applicability and scalability of the presented method. Results suggest that (a) no improvement in canopy height estimation is achieved when models were constructed and validated for smaller geographic areas, suggesting there is no upper limit to model scalability; and (b) training data can be captured over a small percentage of the study area (~6%) if response and predictor variable variance is captured within the training cohort, however RMSE is higher than when compared to a stratified random sample. Full article

► Figures

Open AccessArticle Flood Mapping Based on Multiple Endmember Spectral Mixture Analysis and Random Forest Classifier—The Case of Yuyao, China

by Quanlong Feng, Jianhua Gong, Jiantao Liu and Yi Li

Remote Sens. 2015, 7(9), 12539-12562; doi:10.3390/rs70912539

Received: 8 July 2015 / Accepted: 14 September 2015 / Published: 23 September 2015

Cited by 4 | Viewed by 894 | PDF Full-text (1663 KB) | HTML Full-text | XML Full-text

Abstract

Remote sensing is recognized as a valuable tool for flood mapping due to its synoptic view and continuous coverage of the flooding event. This paper proposed a hybrid approach based on multiple endmember spectral analysis (MESMA) and Random Forest classifier to extract inundated

[...] Read more.

Remote sensing is recognized as a valuable tool for flood mapping due to its synoptic view and continuous coverage of the flooding event. This paper proposed a hybrid approach based on multiple endmember spectral analysis (MESMA) and Random Forest classifier to extract inundated areas in Yuyao City in China using medium resolution optical imagery. MESMA was adopted to tackle the mixing pixel problem induced by medium resolution data. Specifically, 35 optimal endmembers were selected to construct a total of 3111 models in the MESMA procedure to derive accurate fraction information. A multi-dimensional feature space was constructed including the normalized difference water index (NDWI), topographical parameters of height, slope, and aspect together with the fraction maps. A Random Forest classifier consisting of 200 decision trees was adopted to classify the post-flood image based on the above multi-features. Experimental results indicated that the proposed method can extract the inundated areas precisely with a classification accuracy of 94% and a Kappa index of 0.88. The inclusion of fraction information can help improve the mapping accuracy with an increase of 2.5%. Moreover, the proposed method also outperformed the maximum likelihood classifier and the NDWI thresholding method. This research provided a useful reference for flood mapping using medium resolution optical remote sensing imagery. Full article

(This article belongs to the Special Issue Remote Sensing in Flood Monitoring and Management)

► Figures

Open AccessTechnical Note Canopy Gap Mapping from Airborne Laser Scanning: An Assessment of the Positional and Geometrical Accuracy

by Stéphanie Bonnet, Rachel Gaulton, François Lehaire and Philippe Lejeune

Remote Sens. 2015, 7(9), 11267-11294; doi:10.3390/rs70911267

Received: 21 May 2015 / Revised: 12 August 2015 / Accepted: 27 August 2015 / Published: 2 September 2015

Cited by 1 | Viewed by 806 | PDF Full-text (15574 KB) | HTML Full-text | XML Full-text

Abstract

Canopy gaps are small-scale openings in forest canopies which offer suitable micro-climatic conditions for tree regeneration. Field mapping of gaps is complex and time-consuming. Several studies have used Canopy Height Models (CHM) derived from airborne laser scanning (ALS) to delineate gaps but limited

[...] Read more.

Canopy gaps are small-scale openings in forest canopies which offer suitable micro-climatic conditions for tree regeneration. Field mapping of gaps is complex and time-consuming. Several studies have used Canopy Height Models (CHM) derived from airborne laser scanning (ALS) to delineate gaps but limited accuracy assessment has been carried out, especially regarding the gap geometry. In this study, we investigate three mapping methods based on raster layers produced from ALS leaf-off and leaf-on datasets: thresholding, per-pixel and per-object supervised classifications with Random Forest. In addition to the CHM, other metrics related to the canopy porosity are tested. The gap detection is good, with a global accuracy up to 82% and consumer’s accuracy often exceeding 90%. The Geometric Accuracy (GAc) was analyzed with the gap area, main orientation, gap shape-complexity index and a quantitative assessment index of the matching with reference gaps polygons. The GAc assessment shows difficulties in identifying a method which properly delineates gaps. The performance of CHM-based thresholding was exceeded by that of other methods, especially thresholding of canopy porosity rasters and the per-pixel supervised classification. Beyond assessing the methods performance, we argue the critical need for future ALS-based gap studies to consider the geometric accuracy of results. Full article

► Figures

Open AccessArticle Mapping Tree Canopy Cover and Aboveground Biomass in Sudano-Sahelian Woodlands Using Landsat 8 and Random Forest

by Martin Karlson, Madelene Ostwald, Heather Reese, Josias Sanou, Boalidioa Tankoano and Eskil Mattsson

Remote Sens. 2015, 7(8), 10017-10041; doi:10.3390/rs70810017

Received: 8 June 2015 / Revised: 24 July 2015 / Accepted: 29 July 2015 / Published: 6 August 2015

Cited by 20 | Viewed by 2732 | PDF Full-text (1080 KB) | HTML Full-text | XML Full-text

Abstract

Accurate and timely maps of tree cover attributes are important tools for environmental research and natural resource management. We evaluate the utility of Landsat 8 for mapping tree canopy cover (TCC) and aboveground biomass (AGB) in a woodland landscape in Burkina Faso. Field

[...] Read more.

Accurate and timely maps of tree cover attributes are important tools for environmental research and natural resource management. We evaluate the utility of Landsat 8 for mapping tree canopy cover (TCC) and aboveground biomass (AGB) in a woodland landscape in Burkina Faso. Field data and WorldView-2 imagery were used to assemble the reference dataset. Spectral, texture, and phenology predictor variables were extracted from Landsat 8 imagery and used as input to Random Forest (RF) models. RF models based on multi-temporal and single date imagery were compared to determine the influence of phenology predictor variables. The effect of reducing the number of predictor variables on the RF predictions was also investigated. The model error was assessed using 10-fold cross validation. The most accurate models were created using multi-temporal imagery and variable selection, for both TCC (five predictor variables) and AGB (four predictor variables). The coefficient of determination of predicted versus observed values was 0.77 for TCC (RMSE = 8.9%) and 0.57 for AGB (RMSE = 17.6 tons∙ha⁻¹). This mapping approach is based on freely available Landsat 8 data and relatively simple analytical methods, and is therefore applicable in woodland areas where sufficient reference data are available. Full article

► Figures

Open AccessArticle Mapping Robinia Pseudoacacia Forest Health Conditions by Using Combined Spectral, Spatial, and Textural Information Extracted from IKONOS Imagery and Random Forest Classifier

by Hong Wang, Yu Zhao, Ruiliang Pu and Zhenzhen Zhang

Remote Sens. 2015, 7(7), 9020-9044; doi:10.3390/rs70709020

Received: 22 April 2015 / Revised: 7 July 2015 / Accepted: 9 July 2015 / Published: 16 July 2015

Cited by 6 | Viewed by 1117 | PDF Full-text (3483 KB) | HTML Full-text | XML Full-text

Abstract

The textural and spatial information extracted from very high resolution (VHR) remote sensing imagery provides complementary information for applications in which the spectral information is not sufficient for identification of spectrally similar landscape features. In this study grey-level co-occurrence matrix (GLCM) textures and

[...] Read more.

The textural and spatial information extracted from very high resolution (VHR) remote sensing imagery provides complementary information for applications in which the spectral information is not sufficient for identification of spectrally similar landscape features. In this study grey-level co-occurrence matrix (GLCM) textures and a local statistical analysis Getis statistic (Gi), computed from IKONOS multispectral (MS) imagery acquired from the Yellow River Delta in China, along with a random forest (RF) classifier, were used to discriminate Robina pseudoacacia tree health levels. Specifically, eight GLCM texture features (mean, variance, homogeneity, dissimilarity, contrast, entropy, angular second moment, and correlation) were first calculated from IKONOS NIR band (Band 4) to determine an optimal window size (13 × 13) and an optimal direction (45°). Then, the optimal window size and direction were applied to the three other IKONOS MS bands (blue, green, and red) for calculating the eight GLCM textures. Next, an optimal distance value (5) and an optimal neighborhood rule (Queen’s case) were determined for calculating the four Gi features from the four IKONOS MS bands. Finally, different RF classification results of the three forest health conditions were created: (1) an overall accuracy (OA) of 79.5% produced using the four MS band reflectances only; (2) an OA of 97.1% created with the eight GLCM features calculated from IKONOS Band 4 with the optimal window size of 13 × 13 and direction 45°; (3) an OA of 93.3% created with the all 32 GLCM features calculated from the four IKONOS MS bands with a window size of 13 × 13 and direction of 45°; (4) an OA of 94.0% created using the four Gi features calculated from the four IKONOS MS bands with the optimal distance value of 5 and Queen’s neighborhood rule; and (5) an OA of 96.9% created with the combined 16 spectral (four), spatial (four), and textural (eight) features. The most important feature ranked by RF classifier was GLCM texture mean calculated from Band 4, followed by Gi feature calculated from Band 4. The experimental results demonstrate that (a) both textural and spatial information was more useful than spectral information in determining the Robina pseudoacacia forest health conditions; and (b) the IKONOS NIR band was more powerful than visible bands in quantifying varying degrees of forest crown dieback. Full article

► Figures

Open AccessArticle On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping

by Koreen Millard and Murray Richardson

Remote Sens. 2015, 7(7), 8489-8515; doi:10.3390/rs70708489

Received: 31 March 2015 / Revised: 15 June 2015 / Accepted: 23 June 2015 / Published: 6 July 2015

Abstract

Random Forest (RF) is a widely used algorithm for classification of remotely sensed data. Through a case study in peatland classification using LiDAR derivatives, we present an analysis of the effects of input data characteristics on RF classifications (including RF out-of-bag error, independent

[...] Read more.

Random Forest (RF) is a widely used algorithm for classification of remotely sensed data. Through a case study in peatland classification using LiDAR derivatives, we present an analysis of the effects of input data characteristics on RF classifications (including RF out-of-bag error, independent classification accuracy and class proportion error). Training data selection and specific input variables (i.e., image channels) have a large impact on the overall accuracy of the image classification. High-dimension datasets should be reduced so that only uncorrelated important variables are used in classifications. Despite the fact that RF is an ensemble approach, independent error assessments should be used to evaluate RF results, and iterative classifications are recommended to assess the stability of predicted classes. Results are also shown to be highly sensitive to the size of the training data set. In addition to being as large as possible, the training data sets used in RF classification should also be (a) randomly distributed or created in a manner that allows for the class proportions of the training data to be representative of actual class proportions in the landscape; and (b) should have minimal spatial autocorrelation to improve classification results and to mitigate inflated estimates of RF out-of-bag classification accuracy. Full article

(This article belongs to the Special Issue Towards Remote Long-Term Monitoring of Wetland Landscapes)

► Figures

Open AccessArticle Classification of Potential Water Bodies Using Landsat 8 OLI and a Combination of Two Boosted Random Forest Classifiers

by Byoung Chul Ko, Hyeong Hun Kim and Jae Yeal Nam

Sensors 2015, 15(6), 13763-13777; doi:10.3390/s150613763

Received: 15 April 2015 / Accepted: 9 June 2015 / Published: 11 June 2015

Cited by 10 | Viewed by 1211 | PDF Full-text (2436 KB) | HTML Full-text | XML Full-text

Abstract

This study proposes a new water body classification method using top-of-atmosphere (TOA) reflectance and water indices (WIs) of the Landsat 8 Operational Land Imager (OLI) sensor and its corresponding random forest classifiers. In this study, multispectral images from the OLI sensor are represented

[...] Read more.

This study proposes a new water body classification method using top-of-atmosphere (TOA) reflectance and water indices (WIs) of the Landsat 8 Operational Land Imager (OLI) sensor and its corresponding random forest classifiers. In this study, multispectral images from the OLI sensor are represented as TOA reflectance and WI values because a classification result using two measures is better than raw spectral images. Two types of boosted random forest (BRF) classifiers are learned using TOA reflectance and WI values, respectively, instead of the heuristic threshold or unsupervised methods. The final probability is summed linearly using the probabilities of two different BRFs to classify image pixels to water class. This study first demonstrates that the Landsat 8 OLI sensor has higher classification rate because it provides improved signal-to-ratio radiometric by using 12-bit quantization of the data instead of 8-bit as available from other sensors. In addition, we prove that the performance of the proposed combination of two BRF classifiers shows robust water body classification results, regardless of topology, river properties, and background environment. Full article

(This article belongs to the Section Remote Sensors)

Open AccessArticle Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA

by Pengyu Hao, Yulin Zhan, Li Wang, Zheng Niu and Muhammad Shakir

Remote Sens. 2015, 7(5), 5347-5369; doi:10.3390/rs70505347

Received: 29 January 2015 / Revised: 17 April 2015 / Accepted: 22 April 2015 / Published: 28 April 2015

Cited by 15 | Viewed by 1704 | PDF Full-text (16845 KB) | HTML Full-text | XML Full-text

Abstract

Currently, accurate information on crop area coverage is vital for food security and industry, and there is strong demand for timely crop mapping. In this study, we used MODIS time series data to investigate the effect of the time series length on crop

[...] Read more.

Currently, accurate information on crop area coverage is vital for food security and industry, and there is strong demand for timely crop mapping. In this study, we used MODIS time series data to investigate the effect of the time series length on crop mapping. Eight time series with different lengths (ranging from one month to eight months) were tested. For each time series, we first used the Random Forest (RF) algorithm to calculate the importance score for all features (including multi-spectral data, Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and phenological metrics). Subsequently, an extension of the Jeffries–Matusita (JM) distance was used to measure class separability for each time series. Finally, the RF algorithm was used to classify crop types, and the classification accuracy and certainty were used to analyze the influence of the time series length and the number of features on classification performance; the features were added one by one based on their importance scores. Results indicated that when the time series was longer than five months, the top ten features remained stable. These features were mainly in July and August. In addition, the NDVI features contributed the majority of the most significant features for crop mapping. The NDWI and data from multi-spectral bands also contributed to improving crop mapping. On the other hand, separability, classification accuracy, and certainty increased with the number of features used and the time series length, although these values quickly reached saturation. Five months was the optimal time series length, as longer time series provided no further improvement in the classification performance. This result shows that relatively short time series have the potential to identify crops accurately, which allows for early crop mapping over large areas. Full article

(This article belongs to the Special Issue Recent Advances in Remote Sensing for Crop Growth Monitoring) Printed Edition available

► Figures

Open AccessArticle Simulating Urban Growth Using a Random Forest-Cellular Automata (RF-CA) Model

by Courage Kamusoko and Jonah Gamba

ISPRS Int. J. Geo-Inf. 2015, 4(2), 447-470; doi:10.3390/ijgi4020447

Received: 3 October 2014 / Revised: 15 December 2014 / Accepted: 24 March 2015 / Published: 1 April 2015

Cited by 11 | Viewed by 2008 | PDF Full-text (1910 KB) | HTML Full-text | XML Full-text

Abstract

Sustainable urban planning and management require reliable land change models, which can be used to improve decision making. The objective of this study was to test a random forest-cellular automata (RF-CA) model, which combines random forest (RF) and cellular automata (CA) models. The

[...] Read more.

Sustainable urban planning and management require reliable land change models, which can be used to improve decision making. The objective of this study was to test a random forest-cellular automata (RF-CA) model, which combines random forest (RF) and cellular automata (CA) models. The Kappa simulation (KSimulation), figure of merit, and components of agreement and disagreement statistics were used to validate the RF-CA model. Furthermore, the RF-CA model was compared with support vector machine cellular automata (SVM-CA) and logistic regression cellular automata (LR-CA) models. Results show that the RF-CA model outperformed the SVM-CA and LR-CA models. The RF-CA model had a Kappa simulation (KSimulation) accuracy of 0.51 (with a figure of merit statistic of 47%), while SVM-CA and LR-CA models had a KSimulation accuracy of 0.39 and −0.22 (with figure of merit statistics of 39% and 6%), respectively. Generally, the RF-CA model was relatively accurate at allocating “non-built-up to built-up” changes as reflected by the correct “non-built-up to built-up” components of agreement of 15%. The performance of the RF-CA model was attributed to the relatively accurate RF transition potential maps. Therefore, this study highlights the potential of the RF-CA model for simulating urban growth. Full article

► Figures

Open AccessArticle Urban Flood Mapping Based on Unmanned Aerial Vehicle Remote Sensing and Random Forest Classifier—A Case of Yuyao, China

by Quanlong Feng, Jiantao Liu and Jianhua Gong

Water 2015, 7(4), 1437-1455; doi:10.3390/w7041437

Received: 30 November 2014 / Revised: 13 March 2015 / Accepted: 25 March 2015 / Published: 31 March 2015

Cited by 16 | Viewed by 2059 | PDF Full-text (11645 KB) | HTML Full-text | XML Full-text

Abstract

Flooding is a severe natural hazard, which poses a great threat to human life and property, especially in densely-populated urban areas. As one of the fastest developing fields in remote sensing applications, an unmanned aerial vehicle (UAV) can provide high-resolution data with a

[...] Read more.

Flooding is a severe natural hazard, which poses a great threat to human life and property, especially in densely-populated urban areas. As one of the fastest developing fields in remote sensing applications, an unmanned aerial vehicle (UAV) can provide high-resolution data with a great potential for fast and accurate detection of inundated areas under complex urban landscapes. In this research, optical imagery was acquired by a mini-UAV to monitor the serious urban waterlogging in Yuyao, China. Texture features derived from gray-level co-occurrence matrix were included to increase the separability of different ground objects. A Random Forest classifier, consisting of 200 decision trees, was used to extract flooded areas in the spectral-textural feature space. Confusion matrix was used to assess the accuracy of the proposed method. Results indicated the following: (1) Random Forest showed good performance in urban flood mapping with an overall accuracy of 87.3% and a Kappa coefficient of 0.746; (2) the inclusion of texture features improved classification accuracy significantly; (3) Random Forest outperformed maximum likelihood and artificial neural network, and showed a similar performance to support vector machine. The results demonstrate that UAV can provide an ideal platform for urban flood monitoring and the proposed method shows great capability for the accurate extraction of inundated areas. Full article

(This article belongs to the Special Issue Advances in Remote Sensing of Flooding)

► Figures

Open AccessArticle UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis

by Quanlong Feng, Jiantao Liu and Jianhua Gong

Remote Sens. 2015, 7(1), 1074-1094; doi:10.3390/rs70101074

Received: 31 October 2014 / Accepted: 12 January 2015 / Published: 19 January 2015

Cited by 29 | Viewed by 4504 | PDF Full-text (86113 KB) | HTML Full-text | XML Full-text

Abstract

Unmanned aerial vehicle (UAV) remote sensing has great potential for vegetation mapping in complex urban landscapes due to the ultra-high resolution imagery acquired at low altitudes. Because of payload capacity restrictions, off-the-shelf digital cameras are widely used on medium and small sized UAVs.

[...] Read more.

Unmanned aerial vehicle (UAV) remote sensing has great potential for vegetation mapping in complex urban landscapes due to the ultra-high resolution imagery acquired at low altitudes. Because of payload capacity restrictions, off-the-shelf digital cameras are widely used on medium and small sized UAVs. The limitation of low spectral resolution in digital cameras for vegetation mapping can be reduced by incorporating texture features and robust classifiers. Random Forest has been widely used in satellite remote sensing applications, but its usage in UAV image classification has not been well documented. The objectives of this paper were to propose a hybrid method using Random Forest and texture analysis to accurately differentiate land covers of urban vegetated areas, and analyze how classification accuracy changes with texture window size. Six least correlated second-order texture measures were calculated at nine different window sizes and added to original Red-Green-Blue (RGB) images as ancillary data. A Random Forest classifier consisting of 200 decision trees was used for classification in the spectral-textural feature space. Results indicated the following: (1) Random Forest outperformed traditional Maximum Likelihood classifier and showed similar performance to object-based image analysis in urban vegetation classification; (2) the inclusion of texture features improved classification accuracy significantly; (3) classification accuracy followed an inverted U relationship with texture window size. The results demonstrate that UAV provides an efficient and ideal platform for urban vegetation mapping. The hybrid method proposed in this paper shows good performance in differentiating urban vegetation mapping. The drawbacks of off-the-shelf digital cameras can be reduced by adopting Random Forest and texture analysis at the same time. Full article

(This article belongs to the Special Issue UAV-Based Remote Sensing Methods for Modeling, Mapping, and Monitoring Vegetation and Agricultural Crops)

► Figures

Open AccessArticle Canopy Height Estimation in French Guiana with LiDAR ICESat/GLAS Data Using Principal Component Analysis and Random Forest Regressions

by Ibrahim Fayad, Nicolas Baghdadi, Jean-Stéphane Bailly, Nicolas Barbier, Valéry Gond, Mahmoud El Hajj, Frédéric Fabre and Bernard Bourgine

Remote Sens. 2014, 6(12), 11883-11914; doi:10.3390/rs61211883

Received: 10 June 2014 / Revised: 11 November 2014 / Accepted: 17 November 2014 / Published: 28 November 2014

Cited by 9 | Viewed by 2571 | PDF Full-text (28167 KB) | HTML Full-text | XML Full-text

Abstract

Estimating forest canopy height from large-footprint satellite LiDAR waveforms is challenging given the complex interaction between LiDAR waveforms, terrain, and vegetation, especially in dense tropical and equatorial forests. In this study, canopy height in French Guiana was estimated using multiple linear regression models

[...] Read more.

Estimating forest canopy height from large-footprint satellite LiDAR waveforms is challenging given the complex interaction between LiDAR waveforms, terrain, and vegetation, especially in dense tropical and equatorial forests. In this study, canopy height in French Guiana was estimated using multiple linear regression models and the Random Forest technique (RF). This analysis was either based on LiDAR waveform metrics extracted from the GLAS (Geoscience Laser Altimeter System) spaceborne LiDAR data and terrain information derived from the SRTM (Shuttle Radar Topography Mission) DEM (Digital Elevation Model) or on Principal Component Analysis (PCA) of GLAS waveforms. Results show that the best statistical model for estimating forest height based on waveform metrics and digital elevation data is a linear regression of waveform extent, trailing edge extent, and terrain index (RMSE of 3.7 m). For the PCA based models, better canopy height estimation results were observed using a regression model that incorporated both the first 13 principal components (PCs) and the waveform extent (RMSE = 3.8 m). Random Forest regressions revealed that the best configuration for canopy height estimation used all the following metrics: waveform extent, leading edge, trailing edge, and terrain index (RMSE = 3.4 m). Waveform extent was the variable that best explained canopy height, with an importance factor almost three times higher than those for the other three metrics (leading edge, trailing edge, and terrain index). Furthermore, the Random Forest regression incorporating the first 13 PCs and the waveform extent had a slightly-improved canopy height estimation in comparison to the linear model, with an RMSE of 3.6 m. In conclusion, multiple linear regressions and RF regressions provided canopy height estimations with similar precision using either LiDAR metrics or PCs. However, a regression model (linear regression or RF) based on the PCA of waveform samples with waveform extent information is an interesting alternative for canopy height estimation as it does not require several metrics that are difficult to derive from GLAS waveforms in dense forests, such as those in French Guiana. Full article

► Figures

Open AccessArticle Estimation of Airborne Lidar-Derived Tropical Forest Canopy Height Using Landsat Time Series in Cambodia

by Tetsuji Ota, Oumer S. Ahmed, Steven E. Franklin, Michael A. Wulder, Tsuyoshi Kajisa, Nobuya Mizoue, Shigejiro Yoshida, Gen Takao, Yasumasa Hirata, Naoyuki Furuya, Takio Sano, Sokh Heng and Ma Vuthy

Remote Sens. 2014, 6(11), 10750-10772; doi:10.3390/rs61110750

Received: 9 July 2014 / Revised: 3 October 2014 / Accepted: 8 October 2014 / Published: 6 November 2014

Cited by 7 | Viewed by 1632 | PDF Full-text (2051 KB) | HTML Full-text | XML Full-text

Abstract

In this study, we test and demonstrate the utility of disturbance and recovery information derived from annual Landsat time series to predict current forest vertical structure (as compared to the more common approaches, that consider a sample of airborne Lidar and single-date Landsat

[...] Read more.

In this study, we test and demonstrate the utility of disturbance and recovery information derived from annual Landsat time series to predict current forest vertical structure (as compared to the more common approaches, that consider a sample of airborne Lidar and single-date Landsat derived variables). Mean Canopy Height (MCH) was estimated separately using single date, time series, and the combination of single date and time series variables in multiple regression and random forest (RF) models. The combination of single date and time series variables, which integrate disturbance history over the entire time series, overall provided better MCH prediction than using either of the two sets of variables separately. In general, the RF models resulted in improved performance in all estimates over those using multiple regression. The lowest validation error was obtained using Landsat time series variables in a RF model (R² = 0.75 and RMSE = 2.81 m). Combining single date and time series data was more effective when the RF model was used (opposed to multiple regression). The RMSE for RF mean canopy height prediction was reduced by 13.5% when combining the two sets of variables as compared to the 3.6% RMSE decline presented by multiple regression. This study demonstrates the value of airborne Lidar and long term Landsat observations to generate estimates of forest canopy height using the random forest algorithm. Full article

► Figures

Open AccessArticle Classifying Complex Mountainous Forests with L-Band SAR and Landsat Data Integration: A Comparison among Different Machine Learning Methods in the Hyrcanian Forest

by Sara Attarchi and Richard Gloaguen

Remote Sens. 2014, 6(5), 3624-3647; doi:10.3390/rs6053624

Received: 20 January 2014 / Revised: 9 April 2014 / Accepted: 15 April 2014 / Published: 25 April 2014

Cited by 9 | Viewed by 1745 | PDF Full-text (1756 KB) | HTML Full-text | XML Full-text

Abstract

Forest environment classification in mountain regions based on single-sensor remote sensing approaches is hindered by forest complexity and topographic effects. Temperate broadleaf forests in western Asia such as the Hyrcanian forest in northern Iran have already suffered from intense anthropogenic activities. In those

[...] Read more.

Forest environment classification in mountain regions based on single-sensor remote sensing approaches is hindered by forest complexity and topographic effects. Temperate broadleaf forests in western Asia such as the Hyrcanian forest in northern Iran have already suffered from intense anthropogenic activities. In those regions, forests mainly extend in rough terrain and comprise different stand structures, which are difficult to discriminate. This paper explores the joint analysis of Landsat7/ETM+, L-band SAR and their derived parameters and the effect of terrain corrections to overcome the challenges of discriminating forest stand age classes in mountain regions. We also verified the performances of three machine learning methods which have recently shown promising results using multisource data; support vector machines (SVM), neural networks (NN), random forest (RF) and one traditional classifier (i.e., maximum likelihood classification (MLC)) as a benchmark. The non-topographically corrected ETM+ data failed to differentiate among different forest stand age classes (average classification accuracy (OA) = 65%). This confirms the need to reduce relief effects prior data classification in mountain regions. SAR backscattering alone cannot properly differentiate among different forest stand age classes (OA = 62%). However, textures and PolSAR features are very efficient for the separation of forest classes (OA = 82%). The highest classification accuracy was achieved by the joint usage of SAR and ETM+ (OA = 86%). However, this shows a slight improvement compared to the ETM+ classification (OA = 84%). The machine learning classifiers proved t o be more robust and accurate compared to MLC. SVM and RF statistically produced better classification results than NN in the exploitation of the considered multi-source data. Full article

Open AccessArticle Assessing the Feasibility of Low-Density LiDAR for Stand Inventory Attribute Predictions in Complex and Managed Forests of Northern Maine, USA

by Rei Hayashi, Aaron Weiskittel and Steven Sader

Forests 2014, 5(2), 363-383; doi:10.3390/f5020363

Received: 20 December 2013 / Revised: 1 February 2014 / Accepted: 19 February 2014 / Published: 24 February 2014

Cited by 9 | Viewed by 1807 | PDF Full-text (2010 KB) | HTML Full-text | XML Full-text

Abstract

The objective of this study was to evaluate the applicability of using a low-density (1–3 points m⁻²) discrete-return LiDAR (Light Detection and Ranging) for predicting maximum tree height, stem density, basal area, quadratic mean diameter and total volume. The research was

[...] Read more.

The objective of this study was to evaluate the applicability of using a low-density (1–3 points m⁻²) discrete-return LiDAR (Light Detection and Ranging) for predicting maximum tree height, stem density, basal area, quadratic mean diameter and total volume. The research was conducted at the Penobscot Experimental Forest in central Maine, where a range of stand structures and species composition is present and generally representative of northern Maine’s forests. Prediction models were developed utilizing the random forest algorithm that was calibrated using reference data collected in fixed radius circular plots. For comparison, the volume model used two sets of reference data, with one being fixed radius circular plots and the other variable radius plots. Prediction biases were evaluated with respect to five silvicultural treatments and softwood species composition based on the coefficient of determination (R²), root mean square error and mean bias, as well as residual scatter plots. Overall, this study found that LiDAR tended to underestimate maximum tree height and volume. The maximum tree height and volume models had R² values of 86.9% and 72.1%, respectively. The accuracy of volume prediction was also sensitive to the plot type used. While it was difficult to develop models with a high R², due to the complexities of Maine’s forest structures and species composition, the results suggest that low density LiDAR can be used as a supporting tool in forest management for this region. Full article

(This article belongs to the Special Issue LiDAR and Other Remote Sensing Applications in Mapping and Monitoring of Forests Structure and Biomass)

Open AccessArticle Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota

by Jennifer M. Corcoran, Joseph F. Knight and Alisa L. Gallant

Remote Sens. 2013, 5(7), 3212-3238; doi:10.3390/rs5073212

Received: 5 April 2013 / Revised: 20 June 2013 / Accepted: 20 June 2013 / Published: 4 July 2013

Cited by 40 | Viewed by 3284 | PDF Full-text (2682 KB) | HTML Full-text | XML Full-text

Abstract

Wetland mapping at the landscape scale using remotely sensed data requires both affordable data and an efficient accurate classification method. Random forest classification offers several advantages over traditional land cover classification techniques, including a bootstrapping technique to generate robust estimations of outliers in

[...] Read more.

Wetland mapping at the landscape scale using remotely sensed data requires both affordable data and an efficient accurate classification method. Random forest classification offers several advantages over traditional land cover classification techniques, including a bootstrapping technique to generate robust estimations of outliers in the training data, as well as the capability of measuring classification confidence. Though the random forest classifier can generate complex decision trees with a multitude of input data and still not run a high risk of over fitting, there is a great need to reduce computational and operational costs by including only key input data sets without sacrificing a significant level of accuracy. Our main questions for this study site in Northern Minnesota were: (1) how does classification accuracy and confidence of mapping wetlands compare using different remote sensing platforms and sets of input data; (2) what are the key input variables for accurate differentiation of upland, water, and wetlands, including wetland type; and (3) which datasets and seasonal imagery yield the best accuracy for wetland classification. Our results show the key input variables include terrain (elevation and curvature) and soils descriptors (hydric), along with an assortment of remotely sensed data collected in the spring (satellite visible, near infrared, and thermal bands; satellite normalized vegetation index and Tasseled Cap greenness and wetness; and horizontal-horizontal (HH) and horizontal-vertical (HV) polarization using L-band satellite radar). We undertook this exploratory analysis to inform decisions by natural resource managers charged with monitoring wetland ecosystems and to aid in designing a system for consistent operational mapping of wetlands across landscapes similar to those found in Northern Minnesota. Full article

Open AccessArticle Classification of Needle Loss of Individual Scots Pine Trees by Means of Airborne Laser Scanning

by Tuula Kantola, Mikko Vastaranta, Päivi Lyytikäinen-Saarenmaa, Markus Holopainen, Ville Kankare, Mervi Talvitie and Juha Hyyppä

Forests 2013, 4(2), 386-403; doi:10.3390/f4020386

Received: 1 April 2013 / Revised: 23 May 2013 / Accepted: 27 May 2013 / Published: 14 June 2013

Cited by 8 | Viewed by 2308 | PDF Full-text (643 KB) | HTML Full-text | XML Full-text

Abstract

Forest disturbances caused by pest insects are threatening ecosystem stability, sustainable forest management and economic return in boreal forests. Climate change and increased extreme weather patterns can magnify the intensity of forest disturbances, particularly at higher latitudes. Due to rapid responses to elevating

[...] Read more.

Forest disturbances caused by pest insects are threatening ecosystem stability, sustainable forest management and economic return in boreal forests. Climate change and increased extreme weather patterns can magnify the intensity of forest disturbances, particularly at higher latitudes. Due to rapid responses to elevating temperatures, forest insect pests can flexibly change their survival, dispersal and geographic distributions. The outbreak pattern of forest pests in Finland has evidently changed during the last decade. Projection of shifts in distributions of insect-caused forest damages has become a critical issue in the field of forest research. The Common pine sawfly (Diprion pini L.) (Hymenoptera, Diprionidae) is regarded as a significant threat to boreal pine forests. Defoliation by D. pini has resulted in severe growth loss and mortality of Scots pine (Pinus sylvestris L.) (Pinaceae) in eastern Finland. In this study, tree-wise defoliation was estimated for five different needle loss category classification schemes and for 10 different simulated airborne laser scanning (ALS) pulse densities. The nearest neighbor (NN) approach, a nonparametric estimation method, was used for estimating needle loss of 701 Scots pines, using the means of individual tree features derived from ALS data. The Random Forest (RF) method was applied in NN-search. For the full dense data (~20 pulses/m²), the overall estimation accuracies for tree-wise defoliation level varied between 71.0% and 86.5% (kappa-values of 0.56 and 0.57, respectively), depending on the classification scheme. The overall classification accuracies for two class estimation with different ALS pulse densities varied between 82.8% and 83.7% (kappa-values of 0.62 and 0.67, respectively). We conclude that ALS-based estimation of needle losses may be of acceptable accuracy for individual trees. Our method did not appear sensitive to the applied pulse densities. Full article

Open AccessArticle Early Detection of Bark Beetle Green Attack Using TerraSAR-X and RapidEye Data

by Sonia M. Ortiz, Johannes Breidenbach and Gerald Kändler

Remote Sens. 2013, 5(4), 1912-1931; doi:10.3390/rs5041912

Received: 18 February 2013 / Revised: 4 April 2013 / Accepted: 4 April 2013 / Published: 16 April 2013

Cited by 18 | Viewed by 2184 | PDF Full-text (4214 KB) | HTML Full-text | XML Full-text

Abstract

Bark beetles cause widespread damages in the coniferous-dominated forests of central Europe and North America. In the future, areas affected by bark beetles may further increase due to climate change. However, the early detection of the bark beetle green attack can guide management

[...] Read more.

Bark beetles cause widespread damages in the coniferous-dominated forests of central Europe and North America. In the future, areas affected by bark beetles may further increase due to climate change. However, the early detection of the bark beetle green attack can guide management decisions to prevent larger damages. For this reason, a field-based bark beetle monitoring program is currently implemented in Germany. The combination of remote sensing and field data may help minimizing the reaction time and reducing costs of monitoring programs covering large forested areas. In this case study, RapidEye and TerraSAR-X data were analyzed separately and in combination to detect bark beetle green attack. The remote sensing data were acquired in May 2009 for a study site in south-west Germany. In order to distinguish healthy areas and areas affected by bark beetle green attack, three statistical approaches were compared: generalized linear models (GLM), maximum entropy (ME) and random forest (RF). The spatial scale (minimum mapping unit) was 78.5 m². TerraSAR-X data resulted in fair classification accuracy with a cross-validated Cohen’s Kappa Coefficient (kappa) of 0.23. RapidEye data resulted in moderate classification accuracy with a kappa of 0.51. The highest classification accuracy was obtained by combining the TerraSAR-X and RapidEye data, resulting in a kappa of 0.74. The accuracy of ME models was considerably higher than the accuracy of GLM and RF models. Full article

Open AccessArticle Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data

by Markus Immitzer, Clement Atzberger and Tatjana Koukal

Remote Sens. 2012, 4(9), 2661-2693; doi:10.3390/rs4092661

Received: 25 July 2012 / Revised: 3 September 2012 / Accepted: 4 September 2012 / Published: 14 September 2012

Abstract

Tree species diversity is a key parameter to describe forest ecosystems. It is, for example, important for issues such as wildlife habitat modeling and close-to-nature forest management. We examined the suitability of 8-band WorldView-2 satellite data for the identification of 10 tree species

[...] Read more.

Tree species diversity is a key parameter to describe forest ecosystems. It is, for example, important for issues such as wildlife habitat modeling and close-to-nature forest management. We examined the suitability of 8-band WorldView-2 satellite data for the identification of 10 tree species in a temperate forest in Austria. We performed a Random Forest (RF) classification (object-based and pixel-based) using spectra of manually delineated sunlit regions of tree crowns. The overall accuracy for classifying 10 tree species was around 82% (8 bands, object-based). The class-specific producer’s accuracies ranged between 33% (European hornbeam) and 94% (European beech) and the user’s accuracies between 57% (European hornbeam) and 92% (Lawson’s cypress). The object-based approach outperformed the pixel-based approach. We could show that the 4 new WorldView-2 bands (Coastal, Yellow, Red Edge, and Near Infrared 2) have only limited impact on classification accuracy if only the 4 main tree species (Norway spruce, Scots pine, European beech, and English oak) are to be separated. However, classification accuracy increased significantly using the full spectral resolution if further tree species were included. Beside the impact on overall classification accuracy, the importance of the spectral bands was evaluated with two measures provided by RF. An in-depth analysis of the RF output was carried out to evaluate the impact of reference data quality and the resulting reliability of final class assignments. Finally, an extensive literature review on tree species classification comprising about 20 studies is presented. Full article

(This article belongs to the Special Issue Remote Sensing of Biological Diversity)

► Figures

Open AccessArticle Classification of Defoliated Trees Using Tree-Level Airborne Laser Scanning Data Combined with Aerial Images

by Tuula Kantola, Mikko Vastaranta, Xiaowei Yu, Paivi Lyytikainen-Saarenmaa, Markus Holopainen, Mervi Talvitie, Sanna Kaasalainen, Svein Solberg and Juha Hyyppa

Remote Sens. 2010, 2(12), 2665-2679; doi:10.3390/rs2122665

Received: 12 October 2010 / Revised: 18 November 2010 / Accepted: 22 November 2010 / Published: 26 November 2010

Cited by 25 | Viewed by 4487 | PDF Full-text (626 KB) | HTML Full-text | XML Full-text

Abstract

Climate change and rising temperatures have been observed to be related to the increase of forest insect damage in the boreal zone. The common pine sawfly (Diprion pini L.) (Hymenoptera, Diprionidae) is regarded as a significant threat to boreal pine forests. Defoliation

[...] Read more.

Climate change and rising temperatures have been observed to be related to the increase of forest insect damage in the boreal zone. The common pine sawfly (Diprion pini L.) (Hymenoptera, Diprionidae) is regarded as a significant threat to boreal pine forests. Defoliation by D. pini can cause severe growth loss and tree mortality in Scots pine (Pinus sylvestris L.) (Pinaceae). In this study, logistic LASSO regression, Random Forest (RF) and Most Similar Neighbor method (MSN) were investigated for predicting the defoliation level of individual Scots pines using the features derived from airborne laser scanning (ALS) data and aerial images. Classification accuracies from 83.7% (kappa 0.67) to 88.1% (kappa 0.76) were obtained depending on the method. The most accurate result was produced using RF with a combination of data from the two sensors, while the accuracies when using ALS and image features separately were 80.7% and 87.4%, respectively. Evidently, the combination of ALS and aerial images in detecting needle losses is capable of providing satisfactory estimates for individual trees. Full article

Open AccessArticle Prediction of PKCθ Inhibitory Activity Using the Random Forest Algorithm

by Ming Hao, Yan Li, Yonghua Wang and Shuwei Zhang

Int. J. Mol. Sci. 2010, 11(9), 3413-3433; doi:10.3390/ijms11093413

Received: 19 July 2010 / Revised: 24 August 2010 / Accepted: 3 September 2010 / Published: 20 September 2010

Abstract

This work is devoted to the prediction of a series of 208 structurally diverse PKCθ inhibitors using the Random Forest (RF) based on the Mold² molecular descriptors. The RF model was established and identified as a robust predictor of the experimental pIC

[...] Read more.

This work is devoted to the prediction of a series of 208 structurally diverse PKCθ inhibitors using the Random Forest (RF) based on the Mold² molecular descriptors. The RF model was established and identified as a robust predictor of the experimental pIC₅₀ values, producing good external R²_pred of 0.72, a standard error of prediction (SEP) of 0.45, for an external prediction set of 51 inhibitors which were not used in the development of QSAR models. By using the RF built-in measure of the relative importance of the descriptors, an important predictor—the number of group donor atoms for H-bonds (with N and O)―has been identified to play a crucial role in PKCθ inhibitory activity. We hope that the developed RF model will be helpful in the screening and prediction of novel unknown PKCθ inhibitory activity. Full article

Open AccessArticle Topological Models for Prediction of Pharmacokinetic Parameters of Cephalosporins using Random Forest, Decision Tree and Moving Average Analysis

by Harish DUREJA, Sunil GUPTA and Anil Kumar MADAN

Sci. Pharm. 2008, 76(3), 377-394; doi:10.3797/scipharm.0803-30 (registering DOI)

Received: 27 March 2008 / Accepted: 24 June 2008 / Published: 30 June 2008

Cited by 16 | Viewed by 75 | PDF Full-text (198 KB)

Abstract

The topological indices were used to encode the structureal features of cephalosporins. Both topostructural and topochemical versions of a distance based descriptor, three adjacency based descriptors and five distance-cum-adjacency based descriptors were calculated. The values of 18 indices for each cephalosporin in the

[...] Read more.

The topological indices were used to encode the structureal features of cephalosporins. Both topostructural and topochemical versions of a distance based descriptor, three adjacency based descriptors and five distance-cum-adjacency based descriptors were calculated. The values of 18 indices for each cephalosporin in the dataset were computed using an in-house computer program. Multiple pharmacokinetic parameters of cephalosporins were predicted using random forest, decision tree and moving average analysis. Random forest correctly classified the pharmacokinetic parameters into low and high ranges upto 95%. A decision tree was constructed for each pharmacokinetic parameter to determine the importance of topological indices. The decision tree learned the information from the input data with an accuracy of 95% and correctly predicted the cross-validated (10 fold) data with an accuracy of upto 90%. Three independent moving average based topological models were developed using a single range for simultaneous prediction of multiple pharmacokinetic parameters. The accuracy of classification of single index based models using moving average analysis varied from 65% to 100%. Full article

MDPI Contact

Advanced Search

Search Results

MDPI Contact

Advanced Search

Search Results

Years

Subjects

Journals

Article Types

Countries