remotesensing-logo

Journal Browser

Journal Browser

Machine Learning Techniques Applied to Geosciences and Remote Sensing

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "AI Remote Sensing".

Deadline for manuscript submissions: closed (30 May 2022) | Viewed by 42357

Special Issue Editors


E-Mail Website
Guest Editor
NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal
Interests: data science; spatial data science; remote sensing; information systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The ubiquitous fields of Remote Sensing and Geosciences have contributed to significant advances in applied methods to understand socio-economic, environmental, and ecosystem dynamics. With the growing integration of machine learning methods in the geocomputational toolbox and the advances of sensor technology, we now have the fundamental components to steer towards more harmonious and sustainable development. The data collected from remote sensing and other sensors, coupled with the spatially explicit machine learning algorithms will, hopefully, lead to smarter regions and cities, cleaner oceans, productive yet sustainable agriculture, a more efficient approach to natural disasters, and the mitigation of the impact of human activities in the environment. This partnership is not new, but the ever-increasing resolution of sensors and breakthroughs in algorithms and methodologies, most notably the deep learning approaches, continue to create new opportunities to improve decision-making by making the most of the data-intensive context available. In this sense, ongoing satellite missions and spatially explicit machine learning have the potential to produce a significant change in the way we monitor, manage, and understand our socio-economic and environmental context.

Satellite inventories such as Landsat and Sentinel hold the answer to many questions and problems that we were still unable to address effectively. The extraction of knowledge, through the appropriate methods of data preprocessing, modeling, validation, and dissemination, relies increasingly on the efficiency of machine learning techniques that abridges remote sensing with applied and manageable geoscience information. The very high resolution of current sensors is of paramount importance to detect and model fine-grain interactions of spatio-temporal phenomena that characterize climate, land, and environment. The application of machine learning in geoscience has brought new findings that revolutionize the Anthroposphere's status quo and further debate limits of technological enhancement for managing the interaction between man and environment. Nevertheless, there continues to be an extensive list of technical challenges that impede assertive decision-making in many situations. Challenges such as the fusion of data from different sources, learning from highly imbalanced data, minimizing the need for costly labeled datasets, learning from low signal-to-noise ratio data, moving from correlational to causal reasoning, among many others. However, more importantly, in the context of geoscience information and remote sensing, it is essential to build spatially explicit machine learning algorithms, which make use of spatial concepts and representations to increase the accuracy and outperform general-purpose machine learning models.

This special issue aims to harness the potential of spatially explicit machine learning techniques applied to geoscience information and remote sensing through original research papers that showcase the latest advances, both in theory and empirical outcomes in the field. By adopting a multidisciplinary approach, the contributions should focus on how remote sensing and machine learning techniques can produce practical answers to tackle the challenges we face in the Anthropocene. Potential topics include, but are in no way limited to:

  • In the context of applications:
    • smart cities and regions,
    • urban metabolism,
    • urbanization and settlements,
    • land cover and land use,
    • oceans and water resources monitorization,
    • deforestation, soil erosion, and habitat loss
    • wildland fire,
    • sustainable agriculture,
    • archaeological prospection,
    • heritage preservation,
    • climate change, etc.
  • In the context of data:
    • data fusion,
    • multisource and multitemporal data,
    • efficient training sets,
    • spatial resolution,
    • feature extraction and engineering,
    • imbalanced learning and data generation, etc.
  • In the context of models and techniques:
    • supervised, unsupervised, and semi-supervised learning for image classification,
    • deep learning,
    • active learning,
    • transfer learning and domain adaptation,
    • reinforcement learning,
    • change detection,
    • outlier detection,
    • spatially-explicit machine learning methods, etc.

Assoc. Pro Fernando Bação
Prof. Dr. Eric Vaz
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Remote sensing
  • Geosciences
  • Machine learning
  • Image classification
  • Supervised classification
  • Unsupervised classification
  • Deep Learning

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

25 pages, 5423 KiB  
Article
Assessing the Impact of Neighborhood Size on Temporal Convolutional Networks for Modeling Land Cover Change
by Alysha van Duynhoven and Suzana Dragićević
Remote Sens. 2022, 14(19), 4957; https://doi.org/10.3390/rs14194957 - 4 Oct 2022
Cited by 3 | Viewed by 1461
Abstract
Land cover change (LCC) studies are increasingly using deep learning (DL) modeling techniques. Past studies have leveraged temporal or spatiotemporal sequences of historical LC data to forecast changes with DL models. However, these studies do not adequately assess the association between neighborhood size [...] Read more.
Land cover change (LCC) studies are increasingly using deep learning (DL) modeling techniques. Past studies have leveraged temporal or spatiotemporal sequences of historical LC data to forecast changes with DL models. However, these studies do not adequately assess the association between neighborhood size and DL model capability to forecast LCCs, where neighborhood size refers to the spatial extent captured by each data sample. The objectives of this research study were to: (1) evaluate the effect of neighborhood size on the capacity of DL models to forecast LCCs, specifically Temporal Convolutional Networks (TCN) and Convolutional Neural Networks (CNN-TCN), and (2) assess the effect of auxiliary spatial variables on model capacity to forecast LCCs. First, each model type and neighborhood setting configuration was assessed using data derived from multitemporal MODIS LC for the Regional District of Bulkley-Nechako, Canada, comparing subareas exhibiting different amounts of LCCs with trends obtained for the full region. Next, outcomes were compared with three other study regions. The modeling results were evaluated with three-map comparison measures, where the real-world LC for the next timestep, the real-world LC for the previous timestep, and the forecasted LC for the next year were used to calculate correctly transitioned areas. Across all regions explored, it was observed that increasing neighborhood sizes improved the DL model’s capabilities to forecast short-term LCCs. CNN–TCN models forecasted the most correct LCCs for several regions while reducing error due to quantity when provided additional spatial variables. This study contributes to the systematic exploration of neighborhood sizes on selected spatiotemporal DL techniques for geographic applications. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

21 pages, 8749 KiB  
Article
End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing
by Mohamad Dhaini, Maxime Berar, Paul Honeine and Antonin Van Exem
Remote Sens. 2022, 14(14), 3341; https://doi.org/10.3390/rs14143341 - 11 Jul 2022
Cited by 5 | Viewed by 2177
Abstract
Hyperspectral Unmixing is the process of decomposing a mixed pixel into its pure materials (endmembers) and estimating their corresponding proportions (abundances). Although linear unmixing models are more common due to their simplicity and flexibility, they suffer from many limitations in real world scenes [...] Read more.
Hyperspectral Unmixing is the process of decomposing a mixed pixel into its pure materials (endmembers) and estimating their corresponding proportions (abundances). Although linear unmixing models are more common due to their simplicity and flexibility, they suffer from many limitations in real world scenes where interactions between pure materials exist, which paved the way for nonlinear methods to emerge. However, existing methods for nonlinear unmixing require prior knowledge or an assumption about the type of nonlinearity, which can affect the results. This paper introduces a nonlinear method with a novel deep convolutional autoencoder for blind unmixing. The proposed framework consists of a deep encoder of successive small size convolutional filters along with max pooling layers, and a decoder composed of successive 2D and 1D convolutional filters. The output of the decoder is formed of a linear part and an additive non-linear one. The network is trained using the mean squared error loss function. Several experiments were conducted to evaluate the performance of the proposed method using synthetic and real airborne data. Results show a better performance in terms of abundance and endmembers estimation compared to several existing methods. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

24 pages, 1800 KiB  
Article
Parameter Flexible Wildfire Prediction Using Machine Learning Techniques: Forward and Inverse Modelling
by Sibo Cheng, Yufang Jin, Sandy P. Harrison, César Quilodrán-Casas, Iain Colin Prentice, Yi-Ke Guo and Rossella Arcucci
Remote Sens. 2022, 14(13), 3228; https://doi.org/10.3390/rs14133228 - 5 Jul 2022
Cited by 28 | Viewed by 4512
Abstract
Parameter identification for wildfire forecasting models often relies on case-by-case tuning or posterior diagnosis/analysis, which can be computationally expensive due to the complexity of the forward prediction model. In this paper, we introduce an efficient parameter flexible fire prediction algorithm based on machine [...] Read more.
Parameter identification for wildfire forecasting models often relies on case-by-case tuning or posterior diagnosis/analysis, which can be computationally expensive due to the complexity of the forward prediction model. In this paper, we introduce an efficient parameter flexible fire prediction algorithm based on machine learning and reduced order modelling techniques. Using a training dataset generated by physics-based fire simulations, the method forecasts burned area at different time steps with a low computational cost. We then address the bottleneck of efficient parameter estimation by developing a novel inverse approach relying on data assimilation techniques (latent assimilation) in the reduced order space. The forward and the inverse modellings are tested on two recent large wildfire events in California. Satellite observations are used to validate the forward prediction approach and identify the model parameters. By combining these forward and inverse approaches, the system manages to integrate real-time observations for parameter adjustment, leading to more accurate future predictions. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

20 pages, 109665 KiB  
Article
Tradeoffs between UAS Spatial Resolution and Accuracy for Deep Learning Semantic Segmentation Applied to Wetland Vegetation Species Mapping
by Troy M. Saltiel, Philip E. Dennison, Michael J. Campbell, Tom R. Thompson and Keith R. Hambrecht
Remote Sens. 2022, 14(11), 2703; https://doi.org/10.3390/rs14112703 - 4 Jun 2022
Cited by 6 | Viewed by 2974
Abstract
Recent advances in image classification of fine spatial resolution imagery from unoccupied aircraft systems (UASs) have allowed for mapping vegetation based on both multispectral reflectance and fine textural details. Convolutional neural network (CNN)-based models can take advantage of the spatial detail present in [...] Read more.
Recent advances in image classification of fine spatial resolution imagery from unoccupied aircraft systems (UASs) have allowed for mapping vegetation based on both multispectral reflectance and fine textural details. Convolutional neural network (CNN)-based models can take advantage of the spatial detail present in UAS imagery by implicitly learning shapes and textures associated with classes to produce highly accurate maps. However, the spatial resolution of UAS data is infrequently examined in CNN classification, and there are important tradeoffs between spatial resolution and classification accuracy. To improve the understanding of the relationship between spatial resolution and classification accuracy for a CNN-based model, we captured 7.6 cm imagery with a UAS in a wetland environment containing graminoid (grass-like) plant species and simulated a range of spatial resolutions up to 76.0 cm. We evaluated two methods for the simulation of coarser spatial resolution imagery, averaging before and after orthomosaic stitching, and then trained and applied a U-Net CNN model for each resolution and method. We found untuned overall accuracies exceeding 70% at the finest spatial resolutions, but classification accuracy decreased as spatial resolution coarsened, particularly beyond a 22.8 cm resolution. Coarsening the spatial resolution from 7.6 cm to 22.8 cm could permit a ninefold increase in survey area, with only a moderate reduction in classification accuracy. This study provides insight into the impact of the spatial resolution on deep learning semantic segmentation performance and information that can potentially be useful for optimizing precise UAS-based mapping projects. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

20 pages, 6378 KiB  
Article
Multi-Scale Ship Detection Algorithm Based on a Lightweight Neural Network for Spaceborne SAR Images
by Shanwei Liu, Weimin Kong, Xingfeng Chen, Mingming Xu, Muhammad Yasir, Limin Zhao and Jiaguo Li
Remote Sens. 2022, 14(5), 1149; https://doi.org/10.3390/rs14051149 - 25 Feb 2022
Cited by 46 | Viewed by 3792
Abstract
The current limited spaceborne hardware resources and the diversity of ship target scales in SAR images have led to the requirement of on-orbit real-time detection of ship targets in spaceborne synthetic aperture radar (SAR) images. In this paper, we propose a lightweight ship [...] Read more.
The current limited spaceborne hardware resources and the diversity of ship target scales in SAR images have led to the requirement of on-orbit real-time detection of ship targets in spaceborne synthetic aperture radar (SAR) images. In this paper, we propose a lightweight ship detection network based on the YOLOv4-LITE model. In order to facilitate the network migration to the satellite, the method uses MobileNetv2 as the backbone feature extraction network of the model. To solve the problem of ship target scale diversity in SAR images, an improved receptive field block (RFB) structure is introduced, enhancing the feature extraction ability of the network, and improving the accuracy of multi-scale ship target detection. A sliding window block method is designed to detect the whole SAR image, which can solve the problem of image input. Experiments on the SAR ship dataset SSDD show that the detection speed of the improved lightweight network could reach up to 47.16 FPS, with the mean average precision (mAP) of 95.03%, and the model size is only 49.34 M, which demonstrates that the proposed network can accurately and quickly detect ship targets. The proposed network model can provide a reference for constructing a spaceborne real-time lightweight ship detection network, which can balance the detection accuracy and speed of the network. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

18 pages, 3752 KiB  
Article
Analysis of Wetland Landcover Change in Great Lakes Urban Areas Using Self-Organizing Maps
by Elissa Penfound and Eric Vaz
Remote Sens. 2021, 13(24), 4960; https://doi.org/10.3390/rs13244960 - 7 Dec 2021
Cited by 7 | Viewed by 2896
Abstract
Wetland loss and subsequent reduction of wetland ecosystem services in the Great Lakes region has been driven, in part, by changing landcover and increasing urbanization. With landcover change data, digital elevation models (DEM), and self-organizing maps (SOM), this study explores changing landcover and [...] Read more.
Wetland loss and subsequent reduction of wetland ecosystem services in the Great Lakes region has been driven, in part, by changing landcover and increasing urbanization. With landcover change data, digital elevation models (DEM), and self-organizing maps (SOM), this study explores changing landcover and the flood mitigation attributes of wetland areas over a 15-year period in Toronto and Chicago. The results of this analysis show that (1) in the city of Toronto SOM clusters, the landcover change correlations with wetland volume and wetland area range between −0.1 to −0.5, indicating that a more intense landcover change tends to be correlated with small shallow wetlands, (2) in the city of Chicago SOM clusters, the landcover change correlations with wetland area range between −0.1 to −0.7, the landcover change correlations with wetland volume per area range between −0.1 to 0.8, and the landcover change correlations with elevation range between −0.2 to −0.6, indicating that more intense landcover change tends to be correlated with spatially small wetlands that have a relatively high water-storage capacity per area and are located at lower elevations. In both cities, the smallest SOM clusters represent wetland areas where increased landcover change is correlated with wetland areas that have high flood mitigation potential. This study aims to offer a new perspective on changing urban landscapes and urban wetland ecosystem services in Toronto and Chicago. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

19 pages, 5615 KiB  
Article
Automatic Detection of Impervious Surfaces from Remotely Sensed Data Using Deep Learning
by Jash R. Parekh, Ate Poortinga, Biplov Bhandari, Timothy Mayer, David Saah and Farrukh Chishtie
Remote Sens. 2021, 13(16), 3166; https://doi.org/10.3390/rs13163166 - 10 Aug 2021
Cited by 21 | Viewed by 5347
Abstract
The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by [...] Read more.
The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by computing statistical indices derived from different bands available in remotely sensed data, such as the Landsat and Sentinel series. More recently, researchers have explored classification and regression techniques to model impervious surfaces. However, these modeling efforts are limited due to lack of labeled data for training and evaluation. This in turn requires significant effort for manual labeling of data and visual interpretation of results. In this paper, we train deep learning neural networks using TensorFlow to predict impervious surfaces from Landsat 8 images. We used OpenStreetMap (OSM), a crowd-sourced map of the world with manually interpreted impervious surfaces such as roads and buildings, to programmatically generate large amounts of training and evaluation data, thus overcoming the need for manual labeling. We conducted extensive experimentation to compare the performance of different deep learning neural network architectures, optimization methods, and the set of features used to train the networks. The four model configurations labeled U-Net_SGD_Bands, U-Net_Adam_Bands, U-Net_Adam_Bands+SI, and VGG-19_Adam_Bands+SI resulted in a root mean squared error (RMSE) of 0.1582, 0.1358, 0.1375, and 0.1582 and an accuracy of 90.87%, 92.28%, 92.46%, and 90.11%, respectively, on the test set. The U-Net_Adam_Bands+SI Model, similar to the others mentioned above, is a deep learning neural network that combines Landsat 8 bands with statistical indices. This model performs the best among all four on statistical accuracy and produces qualitatively sharper and brighter predictions of impervious surfaces as compared to the other models. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

20 pages, 6011 KiB  
Article
Increasing the Effectiveness of Active Learning: Introducing Artificial Data Generation in Active Learning for Land Use/Land Cover Classification
by Joao Fonseca, Georgios Douzas and Fernando Bacao
Remote Sens. 2021, 13(13), 2619; https://doi.org/10.3390/rs13132619 - 4 Jul 2021
Cited by 7 | Viewed by 2666
Abstract
In remote sensing, Active Learning (AL) has become an important technique to collect informative ground truth data “on-demand” for supervised classification tasks. Despite its effectiveness, it is still significantly reliant on user interaction, which makes it both expensive and time consuming to implement. [...] Read more.
In remote sensing, Active Learning (AL) has become an important technique to collect informative ground truth data “on-demand” for supervised classification tasks. Despite its effectiveness, it is still significantly reliant on user interaction, which makes it both expensive and time consuming to implement. Most of the current literature focuses on the optimization of AL by modifying the selection criteria and the classifiers used. Although improvements in these areas will result in more effective data collection, the use of artificial data sources to reduce human–computer interaction remains unexplored. In this paper, we introduce a new component to the typical AL framework, the data generator, a source of artificial data to reduce the amount of user-labeled data required in AL. The implementation of the proposed AL framework is done using Geometric SMOTE as the data generator. We compare the new AL framework to the original one using similar acquisition functions and classifiers over three AL-specific performance metrics in seven benchmark datasets. We show that this modification of the AL framework significantly reduces cost and time requirements for a successful AL implementation in all of the datasets used in the experiment. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

21 pages, 8521 KiB  
Article
AI-Based Susceptibility Analysis of Shallow Landslides Induced by Heavy Rainfall in Tianshui, China
by Tianjun Qi, Yan Zhao, Xingmin Meng, Guan Chen and Tom Dijkstra
Remote Sens. 2021, 13(9), 1819; https://doi.org/10.3390/rs13091819 - 7 May 2021
Cited by 20 | Viewed by 2856
Abstract
Groups of landslides induced by heavy rainfall are widely distributed on a global basis and they usually result in major losses of human life and economic damage. However, compared with landslides induced by earthquakes, inventories of landslides induced by heavy rainfall are much [...] Read more.
Groups of landslides induced by heavy rainfall are widely distributed on a global basis and they usually result in major losses of human life and economic damage. However, compared with landslides induced by earthquakes, inventories of landslides induced by heavy rainfall are much less common. In this study we used high-precision remote sensing images before and after continuous heavy rainfall in southern Tianshui, China, from 20 June to 25 July 2013, to produce an inventory of 14,397 shallow landslides. Based on the results of landslide inventory, we utilized machine learning and the geographic information system (GIS) to map landslide susceptibility in this area and evaluated the relative weight of various factors affecting landslide development. First, 18 variables related to geomorphic conditions, slope material, geological conditions, and human activities were selected through collinearity analysis; second, 21 selected machine learning models were trained and optimized in the Python environment to evaluate the susceptibility of landslides. The results showed that the ExtraTrees model was the most effective for landslide susceptibility assessment, with an accuracy of 0.91. This predictive ability means that our landslide susceptibility results can be used in the implementation of landslide prevention and mitigation measures in the region. Analysis of the importance of the factors showed that the contribution of slope aspect (SA) was significantly higher than that of the other factors, followed by planar curvature (PLC), distance to river (DR), distance to fault (DTF), normalized difference vehicle index (NDVI), distance to road (DTR), and other factors. We conclude that factors related to geomorphic conditions are principally responsible for controlling landslide susceptibility in the study area. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

20 pages, 6169 KiB  
Article
A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction
by Weilin Wang, Wenjing Mao, Xueli Tong and Gang Xu
Remote Sens. 2021, 13(7), 1284; https://doi.org/10.3390/rs13071284 - 27 Mar 2021
Cited by 23 | Viewed by 3517
Abstract
Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less [...] Read more.
Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

11 pages, 5149 KiB  
Communication
A Machine Learning Method for Predicting Vegetation Indices in China
by Xiangqian Li, Wenping Yuan and Wenjie Dong
Remote Sens. 2021, 13(6), 1147; https://doi.org/10.3390/rs13061147 - 17 Mar 2021
Cited by 20 | Viewed by 4171
Abstract
To forecast the terrestrial carbon cycle and monitor food security, vegetation growth must be accurately predicted; however, current process-based ecosystem and crop-growth models are limited in their effectiveness. This study developed a machine learning model using the extreme gradient boosting method to predict [...] Read more.
To forecast the terrestrial carbon cycle and monitor food security, vegetation growth must be accurately predicted; however, current process-based ecosystem and crop-growth models are limited in their effectiveness. This study developed a machine learning model using the extreme gradient boosting method to predict vegetation growth throughout the growing season in China from 2001 to 2018. The model used satellite-derived vegetation data for the first month of each growing season, CO2 concentration, and several meteorological factors as data sources for the explanatory variables. Results showed that the model could reproduce the spatiotemporal distribution of vegetation growth as represented by the satellite-derived normalized difference vegetation index (NDVI). The predictive error for the growing season NDVI was less than 5% for more than 98% of vegetated areas in China; the model represented seasonal variations in NDVI well. The coefficient of determination (R2) between the monthly observed and predicted NDVI was 0.83, and more than 69% of vegetated areas had an R2 > 0.8. The effectiveness of the model was examined for a severe drought year (2009), and results showed that the model could reproduce the spatiotemporal distribution of NDVI even under extreme conditions. This model provides an alternative method for predicting vegetation growth and has great potential for monitoring vegetation dynamics and crop growth. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Graphical abstract

Other

Jump to: Research

15 pages, 6374 KiB  
Technical Note
Generating Terrain Data for Geomorphological Analysis by Integrating Topographical Features and Conditional Generative Adversarial Networks
by Sijin Li, Ke Li, Liyang Xiong and Guoan Tang
Remote Sens. 2022, 14(5), 1166; https://doi.org/10.3390/rs14051166 - 26 Feb 2022
Cited by 8 | Viewed by 3073
Abstract
With the development of artificial intelligence techniques for geographical knowledge discovery, simulated terrain generation based on deep-learning algorithms has become one practical way to construct accurate terrain data. However, it is still necessary to discuss whether the simulated topographic data contain the characteristics [...] Read more.
With the development of artificial intelligence techniques for geographical knowledge discovery, simulated terrain generation based on deep-learning algorithms has become one practical way to construct accurate terrain data. However, it is still necessary to discuss whether the simulated topographic data contain the characteristics of specific landforms and can support related geographical studies. Therefore, in this study, a deep learning-based model inspired by previous research is constructed to generate loess landform data. We analyzed the influence of inputting different topographic features on terrain generation and evaluated the similarity between the simulated and reference data. The results show that the deep learning-based model can generate simulated topographic data that include similar elevation and slope probability distributions to the reference data of the loess landform. In addition, the generated results may have inaccurate terrain details, which can be regarded as noise in some cases. This indicates that the selection of input features should be carefully considered. Finally, the simulated data can subsequently support landform and terrain research, especially with intelligence algorithms that require large sets of topographic data. Full article
(This article belongs to the Special Issue Machine Learning Techniques Applied to Geosciences and Remote Sensing)
Show Figures

Figure 1

Back to TopTop