Timely and accurate information of cotton planting areas is essential for monitoring and managing cotton fields. However, there is no large-scale and high-resolution method suitable for mapping cotton fields, and the problems associated with low resolution and poor timeliness need to be solved. Here, we proposed a new framework for mapping cotton fields based on Sentinel-1/2 data for different phenological periods, random forest classifiers, and the multi-scale image segmentation method. A cotton field map for 2019 at a spatial resolution of 10 m was generated for northern Xinjiang, a dominant cotton planting region in China. The overall accuracy and kappa coefficient of the map were 0.932 and 0.813, respectively. The results showed that the boll opening stage was the best phenological phase for mapping cotton fields and the cotton fields was identified most accurately at the early boll opening stage, about 40 days before harvest. Additionally, Sentinel-1 and the red edge bands in Sentinel-2 are important for cotton field mapping, and there is great potential for the fusion of optical images and microwave images in crop mapping. This study provides an effective approach for high-resolution and high-accuracy cotton field mapping, which is vital for sustainable monitoring and management of cotton planting. Full article

This study tested the ability of Sentinel-1 C-band to separate forest from other common land use classes (i.e., urban, low vegetation and water) at two different sites. The first site is characterized by temperate forests and rough terrain while the second by tropical forest and near-flat terrain. We trained a support vector machine classifier using increasing feature sets starting from annual backscatter statistics (average, standard deviation) and adding long-term coherence (i.e., coherence estimate for two acquisitions with a large time difference), as well as short-term (six to twelve days) coherence statistics from annual time series. Classification accuracies using all feature sets was high (>92% overall accuracy). For temperate forests the overall accuracy improved by up to 5% when coherence features were added: long-term coherence reduced misclassification of forest as urban, whereas short-term coherence statistics reduced the misclassification of low vegetation as forest. Classification accuracy for tropical forests showed little differences across feature sets, as the annual backscatter statistics sufficed to separate forest from low vegetation, the other dominant land cover. Our results show the importance of coherence for forest classification over rough terrain, where forest omission error was reduced up to 11%. Full article

Machine Learning (ML) techniques are now being used very successfully in predicting and supporting decisions in multiple areas such as environmental issues and land management. These techniques have also provided promising results in the field of natural hazard assessment and risk mapping. The aim of this work is to apply the Supervised ML technique to train a model able to classify a particular gravity-driven coastal hillslope geomorphic model (slope-over-wall) involving most of the soft rocks of Cilento (southern Italy). To train the model, only geometric data have been used, namely morphometric feature maps computed on a Digital Terrain Model (DTM) derived from Light Detection and Ranging (LiDAR) data. Morphometric maps were computed using third-order polynomials, so as to obtain products that best describe landforms. Not all morphometric parameters from literature were used to train the model, the most significant ones were chosen by applying the Neighborhood Component Analysis (NCA) method. Different models were trained and the main indicators derived from the confusion matrices were compared. The best results were obtained using the Weighted k-NN model (accuracy score = 75%). Analysis of the Receiver Operating Characteristic (ROC) curves also shows that the discriminating capacity of the test reached percentages higher than 95%. The model, resulting more accurate in the training area, will be extended to similar areas along the Tyrrhenian coastal land. Full article

Lidar data is increasingly available over large spatial extents and can also be combined with satellite imagery to provide detailed vegetation structural metrics. To fully realize the benefits of lidar data, practical and scalable processing workflows are needed. In this study, we used the lidR R software package, a custom forest metrics function in R, and a distributed cloud computing environment to process 11 TB of airborne lidar data covering ~22,900 km² into 28 height, cover, and density metrics. We combined these lidar outputs with field plot data to model basal area, trees per acre, and quadratic mean diameter. We compared lidar-only models with models informed by spectral imagery only, and lidar and spectral imagery together. We found that lidar models outperformed spectral imagery models for all three metrics, and combination models performed slightly better than lidar models in two of the three metrics. One lidar variable, the relative density of low midstory canopy, was selected in all lidar and combination models, demonstrating the importance of midstory forest structure in the study area. In general, this open-source lidar-processing workflow provides a practical, scalable option for estimating structure over large, forested landscapes. The methodology and systems used for this study offered us the capability to process large quantities of lidar data into useful forest structure metrics in compressed timeframes. Full article

We propose an innovative method with which to extract building interior structure information automatically, including ceiling, floor, and wall. Our approach outperforms previous methods in the following respects. First, we propose an approach based on principal component analysis (PCA) to find the ground plane, which is regarded as the new Cartesian plane. Second, to reduce the complexity of data processing, the data are projected into two dimensions and transformed into a binary image via the operation of an improved radius outlier removal (ROR) filter. Third, a traditional thinning algorithm is adopted to extract the image skeleton. Then, we propose a method for calculating slope through the nearest neighbor point. Moreover, the line is represented with the slopes to obtain information pertaining to the interior planes. Finally, the outline of the line is restored to a three-dimensional structure. The proposed method is evaluated in multiple scenarios, and the results show that the method is accurate (the maximum error of 0.03 m was in three scenarios) in indoor environments. Full article

Hyperspectral images (HSIs) have been widely used in many fields of application, but it is still extremely challenging to obtain higher classification accuracy, especially when facing a smaller number of training samples in practical applications. It is very time-consuming and laborious to acquire enough labeled samples. Consequently, an efficient hybrid dense network was proposed based on a dual-attention mechanism, due to limited training samples and unsatisfactory classification accuracy. The stacked autoencoder was first used to reduce the dimensions of HSIs. A hybrid dense network framework with two feature-extraction branches was then established in order to extract abundant spectral–spatial features from HSIs, based on the 3D and 2D convolutional neural network models. In addition, spatial attention and channel attention were jointly introduced in order to achieve selective learning of features derived from HSIs. The feature maps were further refined, and more important features could be retained. To improve computational efficiency and prevent the overfitting, the batch normalization layer and the dropout layer were adopted. The Indian Pines, Pavia University, and Salinas datasets were selected to evaluate the classification performance; 5%, 1%, and 1% of classes were randomly selected as training samples, respectively. In comparison with the REF-SVM, 3D-CNN, HybridSN, SSRN, and R-HybridSN, the overall accuracy of our proposed method could still reach 96.80%, 98.28%, and 98.85%, respectively. Our results show that this method can achieve a satisfactory classification performance even in the case of fewer training samples. Full article

The atmospheric humidity in the Polar Regions is an important factor for the global budget of water vapour, which is a significant indicator of Earth’s climate state and evolution. The Global Navigation Satellite System (GNSS) can make a valuable contribution in the calculation of the amount of Precipitable Water Vapour (PW). The PW values retrieved from Global Positioning System (GPS), hereafter PW_GPS, refer to 20-year observations acquired by more than 40 GNSS geodetic stations located in the polar regions. For GNSS stations co-located with radio-sounding stations (RS), which operate Vaisala radiosondes, we estimated the PW from RS observations (PW_RS). The PW values from the ERA-Interim global atmospheric reanalysis were used for validation and comparison of the results for all the selected GPS and RS stations. The correlation coefficients between times series are very high: 0.96 for RS and GPS, 0.98 for RS and ERA in the Arctic; 0.89 for RS and GPS, 0.97 for RS and ERA in Antarctica. The Root-Mean-Square of the Error (RMSE) is 0.9 mm on average for both RS vs. GPS and RS vs. ERA in the Arctic, and 0.6 mm for RS vs. GPS and 0.4 mm for RS vs. ERA in Antarctica. After validation, long-term trends, both for Arctic and Antarctic regions, were estimated using Hector scientific software. Positive PW_GPS trends dominate at Arctic sites near the borders of the Atlantic Ocean. Sites located at higher latitudes show no significant values (at 1σ level). Negative PW_GPS trends were observed in the Arctic region of Greenland and North America. A similar behaviour was found in the Arctic for PW_RS trends. The stations in the West Antarctic sector show a general positive PW_GPS trend, while the sites on the coastal area of East Antarctica exhibit some significant negative PW_GPS trends, but in most cases, no significant PW_RS trends were found. The present work confirms that GPS is able to provide reliable estimates of water vapour content in Arctic and Antarctic regions too, where data are sparse and not easy to collect. These preliminary results can give a valid contribution to climate change studies. Full article

Land use and land cover change (LUCC) modeling has continuously been a major research theme in the field of land system science, which interprets the causes and consequences of land use dynamics. In particular, models that can obtain long-term land use data with high precision are of great value in research on global environmental change and climate impact, as land use data are important model input parameters for evaluating the effect of human activity on nature. However, the accuracy of existing reconstruction and prediction models is inadequate. In this context, this study proposes an integrated convolutional neural network (CNN) LUCC reconstruction and prediction model (CLRPM), which meets the demand for fine-scale LUCC reconstruction and prediction. This model applies the deep learning method, which far exceeds the performance of traditional machine learning methods, and uses CNN to extract spatial features and provide greater proximity information. Taking Baicheng city in Northeast China as an example, we verify that CLRPM achieved high-precision annual LUCC reconstruction and prediction, with an overall accuracy rate 9.38% higher than that of the existing models. Additionally, the error rate was reduced by 49.5%. Moreover, this model can perform multilevel LUCC classification category reconstructions and predictions. This study casts light on LUCC models within the high-precision and fine-grained LUCC categories, which will aid LUCC analyses and help decision-makers better understand complex land-use systems and develop better land management strategies. Full article

Central courtyards are primary components of vernacular architecture in Iran. The directions, dimensions, ratios, and other characteristics of central courtyards are critical for studying historical passive cooling and heating solutions. Several studies on central courtyards have compared their features in different cities and climatic zones in Iran. In this study, deep learning methods for object detection and image segmentation are applied to aerial images, to extract the features of central courtyards. The case study explores aerial images of nine historical cities in Bsk, Bsh, Bwk, and Bwh Köppen climate zones. Furthermore, these features were gathered in an extensive dataset, with 26,437 samples and 76 geometric and climatic features. Additionally, the data analysis methods reveal significant correlations between various features, such as the length and width of courtyards. In all cities, the correlation coefficient between these two characteristics is approximately +0.88. Numerous mathematical equations are generated for each city and climate zone by fitting the linear regression model to these data in different cities and climate zones. These equations can be used as proposed design models to assist designers and researchers in predicting and locating the best courtyard houses in Iran’s historical regions. Full article

Nighttime light (NTL) remote sensing data can effectively reveal human activities in urban development. It has received extensive attention in recent years, owing to its advantages in monitoring urban socio-economic activities. Due to the coarse spatial resolution and blooming effect, few studies can explain the factors influencing NTL variations at a fine scale. This study explores the relationships between Luojia 1-01 NTL intensity and urban surface features at the pixel level. The Spatial Durbin model is used to measure the contributions of different urban surface features (represented by Points-of-interest (POIs), roads, water body and vegetation) to NTL intensity. The contributions of different urban surface features to NTL intensity and the Pixel Blooming Effect (PIBE) are effectively separated by direct effect and indirect effect (pseudo-R² = 0.915; Pearson correlation = 0.774; Moran’s I = 0.014). The results show that the contributions of different urban surface features to NTL intensity and PIBE are significantly different. Roads and transportation facilities are major contributors to NTL intensity and PIBE. The contribution of commercial area is much lower than that of roads in terms of PIBE. The inhibitory effect of water body is weaker than that of vegetation in terms of NTL intensity and PIBE. For each urban surface feature, the direct contribution to NTL intensity is far less than the indirect contribution (PIBE of total neighbors), but greater than the marginal indirect effect (PIBE of each neighbor). The method proposed in this study is expected to provide a reference for explaining the composition and blooming effect of NTL, as well as the application of NTL data in the urban interior. Full article

Arctic tundra landscapes are highly complex and are rapidly changing due to the warming climate. Datasets that document the spatial and temporal variability of the landscape are needed to monitor the rapid changes. Synthetic Aperture Radar (SAR) imagery is specifically suitable for monitoring the Arctic, as SAR, unlike optical remote sensing, can provide time series regardless of weather and illumination conditions. This study examines the potential of seasonal backscatter mechanisms in Arctic tundra environments for improving land cover classification purposes by using a time series of HH/HV TerraSAR-X (TSX) imagery. A Random Forest (RF) classification was applied on multi-temporal Sigma Nought intensity and multi-temporal Kennaugh matrix element data. The backscatter analysis revealed clear differences in the polarimetric response of water, soil, and vegetation, while backscatter signal variations within different vegetation classes were more nuanced. The RF models showed that land cover classes could be distinguished with 92.4% accuracy for the Kennaugh element data, compared to 57.7% accuracy for the Sigma Nought intensity data. Texture predictors, while improving the classification accuracy on the one hand, degraded the spatial resolution of the land cover product. The Kennaugh elements derived from TSX winter acquisitions were most important for the RF model, followed by the Kennaugh elements derived from summer and autumn acquisitions. The results of this study demonstrate that multi-temporal Kennaugh elements derived from dual-polarized X-band imagery are a powerful tool for Arctic tundra land cover mapping. Full article

This paper provides recommendations on how large-scale household surveys should be conducted to generate the data needed to train models for satellite-based crop type mapping in smallholder farming systems. The analysis focuses on maize cultivation in Malawi and Ethiopia, and leverages rich, georeferenced plot-level data from national household surveys that were conducted in 2018–20 and integrated with Sentinel-2 satellite imagery and complementary geospatial data. To identify the approach to survey data collection that yields optimal data for training remote sensing models, 26,250 in silico experiments are simulated within a machine learning framework. The best model is then applied to map seasonal maize cultivation from 2016 to 2019 at 10-m resolution in both countries. The analysis reveals that smallholder plots with maize cultivation can be identified with up to 75% accuracy. Collecting full plot boundaries or complete plot corner points provides the best quality of information for model training. Classification performance peaks with slightly less than 60% of the training data. Seemingly little erosion in accuracy under less preferable approaches to georeferencing plots results in the total area under maize cultivation being overestimated by 0.16–0.47 million hectares (8–24%) in Malawi. Full article

Oil tank inventory is significant for the economy and the military, as it can be used to estimate oil reserves. Traditional oil tank detection methods mainly focus on the geometrical characteristics and spectral features of remotely sensed images based on feature engineering. The methods have a limited application capability when the distribution pattern of ground objects in the image changes and the imaging condition varies largely. Therefore, we propose an end-to-end deep convolution network Res2-Unet+, to detect oil tanks in a large-scale area. The Res2-Unet+ method replaces the typical convolution block in the encoder of the original Unet method using hierarchical residual learning branches. A hierarchical branch is used to decompose the feature map into a few sub-channel features. To evaluate the generalization and transferability of the proposed model, we use high spatial resolution images from three different sensors in different areas to train the oil tank detection model. Images from yet another sensor in another area are used to evaluate the trained model. Three more widely used methods, Unet, Segnet, and PSPNet, are trained and evaluated for the same dataset. The experiments prove the effectiveness, strong generalization, and transferability of the proposed Res2-Unet+ method. Full article

Detecting newly established invasive plants is key to prevent further spread. Traditional field surveys are challenging and often insufficient to identify the presence and extent of invasions. This is particularly true for wetland ecosystems because of difficult access, and because floating and submergent plants may go undetected in the understory of emergent plants. Unpiloted aerial systems (UAS) have the potential to revolutionize how we monitor invasive vegetation in wetlands, but key components of the data collection and analysis workflow have not been defined. In this study, we conducted a rigorous comparison of different methodologies for mapping invasive Emergent (Typha × glauca (cattail)), Floating (Hydrocharis morsus-ranae (European frogbit)), and Submergent species (Chara spp. and Elodea canadensis) using the machine learning classifier, random forest, in a Great Lakes wetland. We compared accuracies using (a) different spatial resolutions (11 cm pixels vs. 3 cm pixels), (b) two classification approaches (pixel- vs. object-based), and (c) including structural measurements (e.g., surface/canopy height models and rugosity as textural metrics). Surprisingly, the coarser resolution (11 cm) data yielded the highest overall accuracy (OA) of 81.4%, 2.5% higher than the best performing model of the finer (3 cm) resolution data. Similarly, the Mean Area Under the Receiving Operations Characteristics Curve (AUROC) and F1 Score from the 11 cm data yielded 15.2%, and 6.5% higher scores, respectively, than those in the 3 cm data. At each spatial resolution, the top performing models were from pixel-based approaches and included surface model data over those with canopy height or multispectral data alone. Overall, high-resolution maps generated from UAS classifications will enable early detection and control of invasive plants. Our workflow is likely applicable to other wetland ecosystems threatened by invasive plants throughout the globe. Full article

It is estimated that, in the Brazilian Amazon, forest degradation contributes three times more than deforestation for the loss of gross above-ground biomass. Degradation, in particular those caused by selective logging, result in features whose detection is a challenge to remote sensing, due to its size, space configuration, and geographical distribution. From the available remote sensing technologies, SAR data allow monitoring even during adverse atmospheric conditions. The aim of this study was to test different pre-trained models of Convolutional Neural Networks (CNNs) for change detection associated with forest degradation in bitemporal products obtained from a pair of SAR COSMO-SkyMed images acquired before and after logging in the Jamari National Forest. This area contains areas of legal and illegal logging, and to test the influence of the speckle effect on the result of this classification by applying the classification methodology on previously filtered and unfiltered images, comparing the results. A method of cluster detections was also presented, based on density-based spatial clustering of applications with noise (DBSCAN), which would make it possible, for example, to guide inspection actions and allow the calculation of the intensity of exploitation (IEX). Although the differences between the tested models were in the order of less than 5%, the tests on the RGB composition (where R = coefficient of variation; G = minimum values; and B = gradient) presented a slightly better performance compared to the others in terms of the number of correct classifications for selective logging, in particular using the model Painters (accuracy = 92%) even in the generalization tests, which presented an overall accuracy of 87%, and in the test on RGB from the unfiltered image pair (accuracy of 90%). These results indicate that multitemporal X-band SAR data have the potential for monitoring selective logging in tropical forests, especially in combination with CNN techniques. Full article