Search

Coastal aquaculture has made an important contribution to global food security and the economic development of coastal zones in recent decades. However, it has also damaged these coastal zones' ecosystems. Moreover, coastal aquaculture is poised to play a key role in the achievement of Sustainable Development Goals (SDGs). Consequently, extracting aquaculture has become crucial and valuable. However, due to the limitations of remote sensing image spatial resolution and traditional extraction methods, most research studies focus on aquaculture areas containing dikes rather than individually separable aquaculture ponds (ISAPs). This is not an accurate estimation of these aquaculture areas' true size. In our study, we propose a rapid and effective object-based method of extracting ISAPs. We chose multi-scale segmentation to generate semantically meaningful image objects for various types of land cover, and then built a decision tree classifier according to the unique features of ISAPs. The results show that our method can remove small rivers and other easily confused features, which has thus far been difficult to accomplish with conventional methods. We obtained an overall precision value of 85.61% with a recall of 84.04%; compared to the support vector machine's (SVM) overall precision value of 78.85% and recall rate of 61.21%, our method demonstrates greater accuracy and efficiency. We used this method to test the transferability of the algorithm to nearby areas, and the obtained accuracy exceeded 80%. The method proposed in this study could provide a readily available solution for the simple and efficient extracting of ISAPs and shows high spatiotemporal transferability. [ABSTRACT FROM AUTHOR]

An extensive number of farmlands in the Poyang Lake region of China have been submerged due to the impact of flood disasters, resulting in significant agricultural economic losses. Therefore, it is of great importance to conduct the long-term temporal monitoring of flood-induced water body changes using remote sensing technology. However, the scarcity of optical images and the complex, fragmented terrain are pressing issues in the current water body extraction efforts in southern hilly regions, particularly due to difficulties in distinguishing shadows from numerous mountain and water bodies. For this purpose, this study employs Sentinel-1 synthetic aperture radar (SAR) data, complemented by water indices and terrain features, to conduct research in the Poyang Lake area. The results indicate that the proposed multi-source data water extraction method based on microwave remote sensing data can quickly and accurately extract a large range of water bodies and realize long-time monitoring, thus proving a new technical means for the accurate extraction of floodwater bodies in the Poyang Lake region. Moreover, the comparison of several methods reveals that CAU-Net, which utilizes multi-band imagery as the input and incorporates a channel attention mechanism, demonstrated the best extraction performance, achieving an impressive overall accuracy of 98.71%. This represents a 0.12% improvement compared to the original U-Net model. Moreover, compared to the thresholding, decision tree, and random forest methods, CAU-Net exhibited a significant enhancement in extracting flood-induced water bodies, making it more suitable for floodwater extraction in the hilly Poyang Lake region. During this flood monitoring period, the water extent in the Poyang Lake area rapidly expanded and subsequently declined gradually. The peak water area reached 4080 km2 at the height of the disaster. The severely affected areas were primarily concentrated in Yongxiu County, Poyang County, Xinjian District, and Yugan County. [ABSTRACT FROM AUTHOR]

Landslides are a common geodynamic phenomenon that cause substantial life and property damage worldwide. In the present study, we developed models to evaluate landslide susceptibility in forest-covered areas in Lin'an, southeastern China using logistic regression (LR), decision tree (DT), and random forest (RF) techniques. In addition to conventional landslide-related natural and human disturbance factors, factors describing forest cover, including forest type (two plantations (hickory and bamboo) and four natural forests (conifer, hardwood, shrub, and moso bamboo) and understory vegetation conditions, were included as predictors. Model performance was evaluated based on true-positive rate, Kappa value, and area under the ROC curve using a 10-fold cross-validation method. All models exhibited good performance with measures of ≥0.70, although the LR model was relatively inferior. The key predictors were forest type, understory vegetation height (UVH), normalized differential vegetation index (NDVI) in summer, distance to road (DTRD), and maximum daily rainfall (MDR). Hickory plantations yielded the highest landslide probability, while conifer and hardwood forests had the lowest values. Bamboo plantations had probability results comparable to those of natural forests. Using the RF model, areas with a shorter UVH (<1.2 m), a lower NDVI (<0.70), a heavier MDR (>115 mm), or a shorter DTRD (<500 m) were predicted to be landslide-prone. Information on forest cover is essential for predicting landslides in areas with rich forest cover, and conversion from natural forests to plantations could increase landslide risk. Across the study areas, the northwestern part was the most landslide-prone. In terms of landslide prevention, the RF model-based map produced the most accurate predictions for the "very high" category of landslide. These results will help us better understand landslide occurrences in forest-covered areas and provide valuable information for governments in designing disaster mitigation. [ABSTRACT FROM AUTHOR]

Coastal aquaculture has made an important contribution to global food security and the economic development of coastal zones in recent decades. However, it has also damaged these coastal zones’ ecosystems. Moreover, coastal aquaculture is poised to play a key role in the achievement of Sustainable Development Goals (SDGs). Consequently, extracting aquaculture has become crucial and valuable. However, due to the limitations of remote sensing image spatial resolution and traditional extraction methods, most research studies focus on aquaculture areas containing dikes rather than individually separable aquaculture ponds (ISAPs). This is not an accurate estimation of these aquaculture areas’ true size. In our study, we propose a rapid and effective object-based method of extracting ISAPs. We chose multi-scale segmentation to generate semantically meaningful image objects for various types of land cover, and then built a decision tree classifier according to the unique features of ISAPs. The results show that our method can remove small rivers and other easily confused features, which has thus far been difficult to accomplish with conventional methods. We obtained an overall precision value of 85.61% with a recall of 84.04%; compared to the support vector machine’s (SVM) overall precision value of 78.85% and recall rate of 61.21%, our method demonstrates greater accuracy and efficiency. We used this method to test the transferability of the algorithm to nearby areas, and the obtained accuracy exceeded 80%. The method proposed in this study could provide a readily available solution for the simple and efficient extracting of ISAPs and shows high spatiotemporal transferability.

Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), and support vector machine (SVM). We selected a case study region that is frequently affected by landslides, the important Kamyaran–Sarvabad road in the Kurdistan province of Iran. Altogether, 14 landslide evaluation factors were input into the MLAs including slope, aspect, elevation, river density, distance to river, distance to fault, fault density, distance to road, road density, land use, slope curvature, lithology, stream power index (SPI), and topographic wetness index (TWI). We identified 64 locations of landslides by field survey of which 70% were randomly employed for building and training the three MLAs while the remaining locations were used for validation. The area under the receiver operating characteristics (AUC) reached a value of 0.94 for the decision tree compared to 0.82 for the random forest, and 0.75 for support vector machines model. Thus, the decision tree model was most accurate in identifying the areas at risk for future landslides. The obtained results may inform geoscientists and those in decision-making roles for landslide management. [ABSTRACT FROM AUTHOR]

Airborne LiDAR is a popular measurement technology in recent years. Its feature is that it can quickly acquire high precision and high density 3D point coordinates on the surface. The reflective waveform of the radar contains the geometric structure and roughness of the surface reflector. Combined with the information from aerial photographs, it can quickly help users to interpret various surface object types and serve as a basis for land cover classification. The experiment is divided into three phases. In the phase 1, LiDAR data and decision tree classification method (DT) were used to classify the land cover and customize the geometric parameter elevation. In the phase 2, we combined aerial photographs, LiDAR data and DT method to improve the accuracy of land cover classification. In the phase 3, the support vector machine classification method (SVM) was used to compare the classification accuracy of different classification methods. The results show that customizing the geometric parameter elevation can improve the overall classification accuracy. The results of the study showed that the DT method and the SVM method had better results for the grass, building and artificial ground, and the SVM method had better results for the planted shrub and bare ground. [ABSTRACT FROM AUTHOR]

Red palm weevil (RPW) is widely considered a key pest of palms, creating extensive damages to the date palm trunk that inevitably leads to palm death if no pest eradication is done. This study evaluates the potential of a remote sensing approach for the timely and reliable detection of RPW infestation on the palm canopy. For two consecutive years, an experimental field with infested and control palms was regularly monitored by an Unmanned Aerial Vehicle (UAV) carrying RGB, multispectral, and thermal sensors. Simultaneously, detailed visual observations of the RPW effects on the palms were made to assess the evolution of infestation from the initial stage until palm death. A UAV-based image processing chain for nondestructive RPW detection was built based on segmentation and vegetation index analysis techniques. These algorithms reveal the potential of thermal data to detect RPW infestation. Maximum temperature values and standard deviations within the palm crown revealed a significant (α = 0.05) difference between infested and non-infested palms at a severe infestation stage but before any visual canopy symptoms were noticed. Furthermore, this proof-of-concept study showed that the temporal monitoring of spectral vegetation index values could contribute to the detection of infested palms before canopy symptoms are visible. The seasonal significant (α = 0.05) increase of greenness index values, as observed in non-infested trees, could not be observed in infested palms. These findings are of added value for steering management practices and future related studies, but further validation of the results is needed. The workflow and resulting maps are accessible through the Mapeo® visualization platform. [ABSTRACT FROM AUTHOR]

Forest fires are major disturbances in forest ecosystems. The rapid detection of the spatial and temporal characteristics of fires is essential for formulating targeted post-fire vegetation restoration measures and assessing fire-induced carbon emissions. We propose an accurate and efficient framework for extracting the spatiotemporal characteristics of fires using vegetation change tracker (VCT) products and the Google Earth Engine (GEE) platform. The VCT was used to extract areas of persistent forest and forest disturbance patches from Landsat images of Xichang and Muli, Liangshan prefecture, Sichuan province in southwestern China and Huma, Heilongjiang province, in northeastern China. All available Landsat images in the GEE platform in a year were normalized using the VCT-derived persisting forest mask to derive three standardized vegetation indices (normalized burn ratio (NBRr), normalized difference moisture index (NDMIr), and normalized difference vegetation index (NDVIr)). Historical forest disturbance events in Xichang were used to train two decision trees using the C4.5 data mining tool. The differenced NBRr, NDMIr, and NDVIr (dNBRr, dNDMIr, and dNDVIr) were obtained by calculating the difference in the index values between two temporally adjacent images. The occurrence time of disturbance events were extracted using the thresholds identified by decision tree 1. The use of all available images in GEE narrowed the disturbance occurrence time down to 16 days. This period was extended if images were not available or had cloud cover. Fire disturbances were distinguished from other disturbances by comparing the dNBRr, dNDMIr, and dNDVIr values with the thresholds identified by decision tree 2. The results showed that the proposed framework performed well in three study areas. The temporal accuracy for detecting disturbances in the three areas was 94.33%, 90.33%, and 89.67%, the classification accuracy of fire and non-fire disturbances was 85.33%, 89.67%, and 83.67%, and the Kappa coefficients were 0.71, 0.74, and 0.67, respectively. The proposed framework enables the efficient and rapid extraction of the spatiotemporal characteristics of forest fire disturbances using frequent Landsat time-series data, GEE, and VCT products. The results can be used in forest fire disturbance databases and to implement targeted post-disturbance vegetation restoration practices. [ABSTRACT FROM AUTHOR]

Lodging is one of the typical abiotic adversities during paddy rice growth. In addition to affecting photosynthesis, it can seriously damage crop growth and development, such as reducing rice quality and hindering automated harvesting. It is, therefore, imperative to accurately and in good time acquire crop-lodging areas for yield prediction, agricultural insurance claims, and disaster-management decisions. However, the accuracy requirements for crop-lodging monitoring remain challenging due to complicated impact factors. Aiming at identifying paddy rice lodging on Shazai Island, Guangdong, China, caused by heavy rainfall and strong wind, a decision-tree model was constructed using multiple-parameter information from Sentinel-1 SAR images and the in situ lodging samples. The model innovatively combined the five backscattering coefficients with five polarization decomposition parameters and quantified the importance of each parameter feature. It was found that the decision-tree method coupled with polarization decomposition can be used to obtain an accurate distribution of paddy rice-lodging areas. The results showed that: (1) Radar parameters can capture the changes in lodged paddy rice. The radar parameters that best distinguish paddy rice lodging are VV, VV+VH, VH/VV, and Span. (2) Span is the parameter with the strongest feature importance, which shows the necessity of adding polarization parameters to the classification model. (3) The dual-polarized Sentinel-1 database classification model can effectively extract the area of lodging paddy rice with an overall accuracy of 84.38%, and a total area precision of 93.18%. These observations can guide the future use of SAR-based information for crop-lodging assessment and post-disaster management. [ABSTRACT FROM AUTHOR]

An extensive number of farmlands in the Poyang Lake region of China have been submerged due to the impact of flood disasters, resulting in significant agricultural economic losses. Therefore, it is of great importance to conduct the long-term temporal monitoring of flood-induced water body changes using remote sensing technology. However, the scarcity of optical images and the complex, fragmented terrain are pressing issues in the current water body extraction efforts in southern hilly regions, particularly due to difficulties in distinguishing shadows from numerous mountain and water bodies. For this purpose, this study employs Sentinel-1 synthetic aperture radar (SAR) data, complemented by water indices and terrain features, to conduct research in the Poyang Lake area. The results indicate that the proposed multi-source data water extraction method based on microwave remote sensing data can quickly and accurately extract a large range of water bodies and realize long-time monitoring, thus proving a new technical means for the accurate extraction of floodwater bodies in the Poyang Lake region. Moreover, the comparison of several methods reveals that CAU-Net, which utilizes multi-band imagery as the input and incorporates a channel attention mechanism, demonstrated the best extraction performance, achieving an impressive overall accuracy of 98.71%. This represents a 0.12% improvement compared to the original U-Net model. Moreover, compared to the thresholding, decision tree, and random forest methods, CAU-Net exhibited a significant enhancement in extracting flood-induced water bodies, making it more suitable for floodwater extraction in the hilly Poyang Lake region. During this flood monitoring period, the water extent in the Poyang Lake area rapidly expanded and subsequently declined gradually. The peak water area reached 4080 km2 at the height of the disaster. The severely affected areas were primarily concentrated in Yongxiu County, Poyang County, Xinjian District, and Yugan County.

Weather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application in an operational sense still yields uncertainty in rainfall estimation at times. This study aims to explore the concept of implementing Machine Learning (ML) models in optimizing the radar-based rainfall estimations at the bin level from a group of estimator. The Canadian King City C-Band radar was used with a GEONOR T-200B rain gauge (a total of 263 sample points) to establish a group of polarimetric-based rainfall estimators (R(Z), R(Z, ZDR), R(KDP)). The estimators were used to train three ML models, namely Decision Tree, Random Forest, and Gradient Boost, to choose the optimal rainfall estimators based on radar variables (Z, ZDR, KDP). Data from the Canadian Exeter C-Band radar and a Texas Electronics TE525 tipping bucket gauge at a different location were used to verify the ML models and compare their results to the most commonly used Z-R relations. The verification process shows promising results for the ML models, specifically the Gradient Boost model. These encouraging results need to be further explored with more sample points to further refine the ML models. [ABSTRACT FROM AUTHOR]

Landslides are a common geodynamic phenomenon that cause substantial life and property damage worldwide. In the present study, we developed models to evaluate landslide susceptibility in forest-covered areas in Lin’an, southeastern China using logistic regression (LR), decision tree (DT), and random forest (RF) techniques. In addition to conventional landslide-related natural and human disturbance factors, factors describing forest cover, including forest type (two plantations (hickory and bamboo) and four natural forests (conifer, hardwood, shrub, and moso bamboo) and understory vegetation conditions, were included as predictors. Model performance was evaluated based on true-positive rate, Kappa value, and area under the ROC curve using a 10-fold cross-validation method. All models exhibited good performance with measures of ≥0.70, although the LR model was relatively inferior. The key predictors were forest type, understory vegetation height (UVH), normalized differential vegetation index (NDVI) in summer, distance to road (DTRD), and maximum daily rainfall (MDR). Hickory plantations yielded the highest landslide probability, while conifer and hardwood forests had the lowest values. Bamboo plantations had probability results comparable to those of natural forests. Using the RF model, areas with a shorter UVH (115 mm), or a shorter DTRD (

An important task in the Electronic Support Measures (ESM) field is analyzing and recognizing radar signals. Feature extraction is one of the primary key elements of radar emitter recognition algorithms. Current research mainly finds statistical features such as the mean and variance of parameters from pluses as the input features of the classifier. However, data noise in intercepted pulse signals greatly interferes with the accuracy of the extracted statistical features and seriously affects the recognition rate of radar emitters. In this paper, we proposed a method of radar emitter recognition. We first clustered parameter sets to establish a set of frequent items and their corresponding clustering centers. Next, we concatenated the clustering centers of each frequent item into a feature vector associated with the data volume dimensions. Then, we built a decision tree classification model based on the feature vector, and finally we used the learned model for the recognition of unknown radar pulse trains. The simulation results show that the proposed method has better robustness when applied to a variety of data volumes and data noise scenarios compared with long short-term memory (LSTM) and support vector machine (SVM) methods. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. Here, we propose a bidirectional flow decision tree (BFDT) module to create a reliable RS scene classification framework. Our algorithm combines BFDT and Convolutional Neural Networks (CNNs) to make the decision process easily interpretable. First, we extract multilevel feature information from the pretrained CNN model, which provides the basis for constructing the subsequent hierarchical structure. Then the model uses the discriminative nature of scene features at different levels to gradually refine similar subsets and learn the interclass hierarchy. Meanwhile, the last fully connected layer embeds decision rules for the decision tree from the bottom up. Finally, the cascading softmax loss is used to train and learn the depth features based on the hierarchical structure formed by the tree structure that contains rich remote sensing information. We also discovered that superclass results can be obtained well for unseen classes due to its unique tree structure hierarchical property, which results in our model having a good generalization effect. The experimental results align with theoretical predictions using three popular datasets. Our proposed framework provides explainable results, leading to correctable and trustworthy approaches. [ABSTRACT FROM AUTHOR]

Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), and support vector machine (SVM). We selected a case study region that is frequently affected by landslides, the important Kamyaran–Sarvabad road in the Kurdistan province of Iran. Altogether, 14 landslide evaluation factors were input into the MLAs including slope, aspect, elevation, river density, distance to river, distance to fault, fault density, distance to road, road density, land use, slope curvature, lithology, stream power index (SPI), and topographic wetness index (TWI). We identified 64 locations of landslides by field survey of which 70% were randomly employed for building and training the three MLAs while the remaining locations were used for validation. The area under the receiver operating characteristics (AUC) reached a value of 0.94 for the decision tree compared to 0.82 for the random forest, and 0.75 for support vector machines model. Thus, the decision tree model was most accurate in identifying the areas at risk for future landslides. The obtained results may inform geoscientists and those in decision-making roles for landslide management.

Airborne LiDAR is a popular measurement technology in recent years. Its feature is that it can quickly acquire high precision and high density 3D point coordinates on the surface. The reflective waveform of the radar contains the geometric structure and roughness of the surface reflector. Combined with the information from aerial photographs, it can quickly help users to interpret various surface object types and serve as a basis for land cover classification. The experiment is divided into three phases. In the phase 1, LiDAR data and decision tree classification method (DT) were used to classify the land cover and customize the geometric parameter elevation. In the phase 2, we combined aerial photographs, LiDAR data and DT method to improve the accuracy of land cover classification. In the phase 3, the support vector machine classification method (SVM) was used to compare the classification accuracy of different classification methods. The results show that customizing the geometric parameter elevation can improve the overall classification accuracy. The results of the study showed that the DT method and the SVM method had better results for the grass, building and artificial ground, and the SVM method had better results for the planted shrub and bare ground.

Red palm weevil (RPW) is widely considered a key pest of palms, creating extensive damages to the date palm trunk that inevitably leads to palm death if no pest eradication is done. This study evaluates the potential of a remote sensing approach for the timely and reliable detection of RPW infestation on the palm canopy. For two consecutive years, an experimental field with infested and control palms was regularly monitored by an Unmanned Aerial Vehicle (UAV) carrying RGB, multispectral, and thermal sensors. Simultaneously, detailed visual observations of the RPW effects on the palms were made to assess the evolution of infestation from the initial stage until palm death. A UAV-based image processing chain for nondestructive RPW detection was built based on segmentation and vegetation index analysis techniques. These algorithms reveal the potential of thermal data to detect RPW infestation. Maximum temperature values and standard deviations within the palm crown revealed a significant (α = 0.05) difference between infested and non-infested palms at a severe infestation stage but before any visual canopy symptoms were noticed. Furthermore, this proof-of-concept study showed that the temporal monitoring of spectral vegetation index values could contribute to the detection of infested palms before canopy symptoms are visible. The seasonal significant (α = 0.05) increase of greenness index values, as observed in non-infested trees, could not be observed in infested palms. These findings are of added value for steering management practices and future related studies, but further validation of the results is needed. The workflow and resulting maps are accessible through the Mapeo® visualization platform.

Forest fires are major disturbances in forest ecosystems. The rapid detection of the spatial and temporal characteristics of fires is essential for formulating targeted post-fire vegetation restoration measures and assessing fire-induced carbon emissions. We propose an accurate and efficient framework for extracting the spatiotemporal characteristics of fires using vegetation change tracker (VCT) products and the Google Earth Engine (GEE) platform. The VCT was used to extract areas of persistent forest and forest disturbance patches from Landsat images of Xichang and Muli, Liangshan prefecture, Sichuan province in southwestern China and Huma, Heilongjiang province, in northeastern China. All available Landsat images in the GEE platform in a year were normalized using the VCT-derived persisting forest mask to derive three standardized vegetation indices (normalized burn ratio (NBRr), normalized difference moisture index (NDMIr), and normalized difference vegetation index (NDVIr)). Historical forest disturbance events in Xichang were used to train two decision trees using the C4.5 data mining tool. The differenced NBRr, NDMIr, and NDVIr (dNBRr, dNDMIr, and dNDVIr) were obtained by calculating the difference in the index values between two temporally adjacent images. The occurrence time of disturbance events were extracted using the thresholds identified by decision tree 1. The use of all available images in GEE narrowed the disturbance occurrence time down to 16 days. This period was extended if images were not available or had cloud cover. Fire disturbances were distinguished from other disturbances by comparing the dNBRr, dNDMIr, and dNDVIr values with the thresholds identified by decision tree 2. The results showed that the proposed framework performed well in three study areas. The temporal accuracy for detecting disturbances in the three areas was 94.33%, 90.33%, and 89.67%, the classification accuracy of fire and non-fire disturbances was 85.33%, 89.67%, and 83.67%, and the Kappa coefficients were 0.71, 0.74, and 0.67, respectively. The proposed framework enables the efficient and rapid extraction of the spatiotemporal characteristics of forest fire disturbances using frequent Landsat time-series data, GEE, and VCT products. The results can be used in forest fire disturbance databases and to implement targeted post-disturbance vegetation restoration practices.

Lodging is one of the typical abiotic adversities during paddy rice growth. In addition to affecting photosynthesis, it can seriously damage crop growth and development, such as reducing rice quality and hindering automated harvesting. It is, therefore, imperative to accurately and in good time acquire crop-lodging areas for yield prediction, agricultural insurance claims, and disaster-management decisions. However, the accuracy requirements for crop-lodging monitoring remain challenging due to complicated impact factors. Aiming at identifying paddy rice lodging on Shazai Island, Guangdong, China, caused by heavy rainfall and strong wind, a decision-tree model was constructed using multiple-parameter information from Sentinel-1 SAR images and the in situ lodging samples. The model innovatively combined the five backscattering coefficients with five polarization decomposition parameters and quantified the importance of each parameter feature. It was found that the decision-tree method coupled with polarization decomposition can be used to obtain an accurate distribution of paddy rice-lodging areas. The results showed that: (1) Radar parameters can capture the changes in lodged paddy rice. The radar parameters that best distinguish paddy rice lodging are VV, VV+VH, VH/VV, and Span. (2) Span is the parameter with the strongest feature importance, which shows the necessity of adding polarization parameters to the classification model. (3) The dual-polarized Sentinel-1 database classification model can effectively extract the area of lodging paddy rice with an overall accuracy of 84.38%, and a total area precision of 93.18%. These observations can guide the future use of SAR-based information for crop-lodging assessment and post-disaster management.

Weather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application in an operational sense still yields uncertainty in rainfall estimation at times. This study aims to explore the concept of implementing Machine Learning (ML) models in optimizing the radar-based rainfall estimations at the bin level from a group of estimator. The Canadian King City C-Band radar was used with a GEONOR T-200B rain gauge (a total of 263 sample points) to establish a group of polarimetric-based rainfall estimators (R(Z), R(Z, ZDR), R(KDP)). The estimators were used to train three ML models, namely Decision Tree, Random Forest, and Gradient Boost, to choose the optimal rainfall estimators based on radar variables (Z, ZDR, KDP). Data from the Canadian Exeter C-Band radar and a Texas Electronics TE525 tipping bucket gauge at a different location were used to verify the ML models and compare their results to the most commonly used Z-R relations. The verification process shows promising results for the ML models, specifically the Gradient Boost model. These encouraging results need to be further explored with more sample points to further refine the ML models.

An important task in the Electronic Support Measures (ESM) field is analyzing and recognizing radar signals. Feature extraction is one of the primary key elements of radar emitter recognition algorithms. Current research mainly finds statistical features such as the mean and variance of parameters from pluses as the input features of the classifier. However, data noise in intercepted pulse signals greatly interferes with the accuracy of the extracted statistical features and seriously affects the recognition rate of radar emitters. In this paper, we proposed a method of radar emitter recognition. We first clustered parameter sets to establish a set of frequent items and their corresponding clustering centers. Next, we concatenated the clustering centers of each frequent item into a feature vector associated with the data volume dimensions. Then, we built a decision tree classification model based on the feature vector, and finally we used the learned model for the recognition of unknown radar pulse trains. The simulation results show that the proposed method has better robustness when applied to a variety of data volumes and data noise scenarios compared with long short-term memory (LSTM) and support vector machine (SVM) methods.

Remote sensing image scene classification (RSISC), which aims to classify scene categories for remote sensing imagery, has broad applications in various fields. Recent deep learning (DL) successes have led to a new wave of RSISC applications; however, they lack explainability and trustworthiness. Here, we propose a bidirectional flow decision tree (BFDT) module to create a reliable RS scene classification framework. Our algorithm combines BFDT and Convolutional Neural Networks (CNNs) to make the decision process easily interpretable. First, we extract multilevel feature information from the pretrained CNN model, which provides the basis for constructing the subsequent hierarchical structure. Then the model uses the discriminative nature of scene features at different levels to gradually refine similar subsets and learn the interclass hierarchy. Meanwhile, the last fully connected layer embeds decision rules for the decision tree from the bottom up. Finally, the cascading softmax loss is used to train and learn the depth features based on the hierarchical structure formed by the tree structure that contains rich remote sensing information. We also discovered that superclass results can be obtained well for unseen classes due to its unique tree structure hierarchical property, which results in our model having a good generalization effect. The experimental results align with theoretical predictions using three popular datasets. Our proposed framework provides explainable results, leading to correctable and trustworthy approaches.

Disturbances are key processes in the carbon cycle of forests and other ecosystems. In recent decades, mountain pine beetle (MPB; Dendroctonus ponderosae) outbreaks have become more frequent and extensive in western North America. Remote sensing has the ability to fill the data gaps of long-term infestation monitoring, but the elimination of observational noise and attributing changes quantitatively are two main challenges in its effective application. Here, we present a forest growth trend analysis method that integrates Landsat temporal trajectories and decision tree techniques to derive annual forest disturbance maps over an 11-year period. The temporal trajectory component successfully captures the disturbance events as represented by spectral segments, whereas decision tree modeling efficiently recognizes and attributes events based upon the characteristics of the segments. Validated against a point set sampled across a gradient of MPB mortality, 86.74% to 94.00% overall accuracy was achieved with small variability in accuracy among years. In contrast, the overall accuracies of single-date classifications ranged from 37.20% to 75.20% and only become comparable with our approach when the training sample size was increased at least four-fold. This demonstrates that the advantages of this time series work flow exist in its small training sample size requirement. The easily understandable, interpretable and modifiable characteristics of our approach suggest that it could be applicable to other ecoregions.

With the rapid modernization, many remote-sensing sensors were developed for classifying urban land and environmental monitoring. Multispectral LiDAR, which serves as a new technology, has exhibited potential in remote-sensing monitoring due to the synchronous acquisition of three-dimension point cloud and spectral information. This study confirmed the potential of multispectral LiDAR for complex urban land cover classification through three comparative methods. Firstly, the Optech Titan LiDAR point cloud was pre-processed and ground filtered. Then, three methods were analyzed: (1) Channel 1, based on Titan data to simulate the classification of a single-band LiDAR; (2) three-channel information and the digital surface model (DSM); and (3) three-channel information and DSM combined with the calculated three normalized difference vegetation indices (NDVIs) for urban land classification. A decision tree was subsequently used in classification based on the combination of intensity information, elevation information, and spectral information. The overall classification accuracies of the point cloud using the single-channel classification and the multispectral LiDAR were 64.66% and 93.82%, respectively. The results show that multispectral LiDAR has excellent potential for classifying land use in complex urban areas due to the availability of spectral information and that the addition of elevation information to the classification process could boost classification accuracy.

Coastal reclamation in Guangdong Province is highly concentrated and is growing rapidly. However, intensive reclamation use has resulted in serious influence on the coastal ecosystem, directly and indirectly. The current conditions and spatial distribution of reclamations must be detected for coastal preservation and management using efficient technology. This study aims to find a suitable method and data to map reclamations accurately at a large scale. Pixel-based and object-oriented classification methods were applied in extracting the three typical types of coastal reclamation, namely, ports, aquaculture ponds, and salt pans, in Guangdong Province from Landsat 8 and Sentinel 2 images. The algorithms of a support vector machine, random forest, decision tree, and rule-based algorithm were performed. Classification results were compared with statistical measures to assess the performance of different algorithms. The results indicated that all of the algorithms could obtain classification results with high accuracy, whereas the object-oriented algorithm showed less efficiency than other algorithms in classifying ports with complicated features. High-resolution data were not always superior to lower-resolution data in the reclamation classification. Generally speaking, applying the rule-based object-oriented algorithm in Sentinel 2A MSI images is relatively efficient at detecting the reclamation use in coastal Guangdong considering its actual situation. The mapping of reclamations in the whole of coastal Guangdong shows that they present obvious agglomeration characteristics in the space. The aquaculture ponds are mainly distributed in the coastal zones of western Guangdong and eastern Guangdong, with the largest area of 77,963 ha. The other types of ports are mainly distributed in the coastal zones of the Pearl River Delta, with an area of 8146 ha, while salt pans are mainly distributed in the coastal zones of Jiangmen, Zhuhai, and Zhongshan, with a total area of 4072 ha. The results can provide key supporting data for decision making in coastal management and preservation.

Forest degradation in the Brazilian Amazon due to selective logging and forest fires may greatly increase the human footprint beyond outright deforestation. We demonstrate a method to quantify annual deforestation and degradation simultaneously across the entire region for the years 2000-2010 using high-resolution Landsat satellite imagery. Combining spectral mixture analysis, normalized difference fraction index, and knowledge-based decision tree classification, we mapped and assessed the accuracy to quantify forest (0.97), deforestation (0.85) and forest degradation (0.82) with an overall accuracy of 0.92. We show that 169,074 km2 of Amazonian forest was converted to human-dominated land uses, such as agriculture, from 2000 to 2010. In that same time frame, an additional 50,815 km2 of forest was directly altered by timber harvesting and/or fire, equivalent to 30% of the area converted by deforestation. While average annual outright deforestation declined by 46% between the first and second halves of the study period, annual forest degradation increased by 20%. Existing operational monitoring systems (PRODES: Monitoramento da Florestal Amazônica Brasileira por Satélite) report deforestation area to within 2% of our results, but do not account for the extensive forest degradation occurring throughout the region due to selective logging and forest fire. Annual monitoring of forest degradation across tropical forests is critical for developing land management policies as well as the monitoring of carbon stocks/emissions and protected areas.. © 2013 by the authors.

Over the last 18 years, Indonesia has experienced significant deforestation due to the expansion of oil palm and rubber plantations. Accurate land cover maps are essential for policymakers to track and manage land change to support sustainable forest management and investment decisions. An automatic digital processing (ADP) method is currently used to develop land cover change maps for Indonesia, based on optical imaging (Landsat). Such maps produce only forest and non-forest classes, and often oil palm and rubber plantations are misclassified as native forests. To improve accuracy of these land cover maps, this study developed oil palm and rubber plantation discrimination indices using the integration of Landsat-8 and synthetic aperture radar Sentinel-1 images. Sentinel-1 VH and VV difference (>7.5 dB) and VH backscatter intensity were used to discriminate oil palm plantations. A combination of Landsat-8 NDVI, NDMI with Sentinel-1 VV and VH were used to discriminate rubber plantations. The improved map produced four land cover classes: native forest, oil palm plantation, rubber plantation, and non-forest. High-resolution SPOT 6/7 imagery and ground truth data were used for validation of the new classified maps. The map had an overall accuracy of 92%; producer’s accuracy for all classes was higher than 90%, except for rubber (65%), and user’s accuracy was over 80% for all classes. These results demonstrate that indices developed from a combination of optical and radar images can improve our ability to discriminate between native forest and oil palm and rubber plantations in the tropics. The new mapping method will help to support Indonesia’s national forest monitoring system and inform monitoring of plantation expansion.

Building function labelling plays an important role in understanding human activities inside buildings. This study develops a method of function label classification using integrated features derived from remote sensing and crowdsensing data with an extreme gradient boosting tree (XGBoost). The classification framework is verified based on a dataset from Shenzhen, China. An extended label system for six building types (residential, commercial, office, industrial, public facilities, and others) was applied, and various social functions were considered. The overall classification accuracies were 88.15% (kappa index = 0.72) and 85.56% (kappa index = 0.69). The importance of features was evaluated using the occurrence frequency of features at decision nodes. In the six-category classification system, the basic building attributes (22.99%) and POIs (46.74%) contributed most to the classification process; moreover, the building footprint (7.40%) and distance to roads (11.76%) also made notable contributions. The result shows that it is feasible to extract building environments from POI labels and building footprint geometry with a dimensional reduction model using an autoencoder. Additionally, crowdsensing data (e.g., POI and distance to roads) will become increasingly important as classification tasks become more complicated and the importance of basic building attributes declines.

The intensive industrial development in special economic zones, such as Thailand’s Eastern Economic Corridor, increases energy consumption, leading to an imbalance of energy supply and a challenge for energy management. Electricity consumption at a local level is crucial for utility planners to manage and invest in the electrical grid. With this study, we propose an electricity consumption estimation model at the district level using machine learning with publicly available statistical data and built-up area (BU), area of lit (AL), and sum of light intensity (SL) data extracted from Landsat 8 and Suomi NPP satellite nighttime light images. The models created from three machine learning algorithms, which included Multiple Linear Regression (MR), Decision Tree (DT), and Support Vector Regression (SVR), were compared. The results show that (1) electricity consumption is highly correlated with SL, AL, and BU; and (2) the DT model demonstrated a better performance in predicting local electricity consumption when compared to MR and SVR with the lowest error rate and highest R2. The local government in developing countries with limited data and financial resources can adopt the proposed approach to benefit from utilizing commonly available remote sensing and statistical data with simple machine learning models such as DT (regression method) for sustainable electricity management.

This study presents a new ensemble framework to predict landslide susceptibility by integrating decision trees (DTs) with the rotation forest (RF) ensemble technique. The proposed framework mainly includes four steps. First, training and validation sets are randomly selected according to historical landslide locations. Then, landslide conditioning factors are selected and screened by the gain ratio method. Next, several training subsets are produced from the training set and a series of trained DTs are obtained by using a DT as a base classifier couple with different training subsets. Finally, the resultant landslide susceptibility map is produced by combining all the DT classification results using the RF ensemble technique. Experimental results demonstrate that the performance of all the DTs can be effectively improved by integrating them with the RF ensemble technique. Specifically, the proposed ensemble methods achieved the predictive values of 0.012–0.121 higher than the DTs in terms of area under the curve (AUC). Furthermore, the proposed ensemble methods are better than the most popular ensemble methods with the predictive values of 0.005–0.083 in terms of AUC. Therefore, the proposed ensemble framework is effective to further improve the spatial prediction of landslides.

Riparian zones consist of important environmental regions, specifically to maintain the quality of water resources. Accurately mapping forest vegetation in riparian zones is an important issue, since it may provide information about numerous surface processes that occur in these areas. Recently, machine learning algorithms have gained attention as an innovative approach to extract information from remote sensing imagery, including to support the mapping task of vegetation areas. Nonetheless, studies related to machine learning application for forest vegetation mapping in the riparian zones exclusively is still limited. Therefore, this paper presents a framework for forest vegetation mapping in riparian zones based on machine learning models using orbital multispectral images. A total of 14 Sentinel-2 images registered throughout the year, covering a large riparian zone of a portion of a wide river in the Pontal do Paranapanema region, São Paulo state, Brazil, was adopted as the dataset. This area is mainly composed of the Atlantic Biome vegetation, and it is near to the last primary fragment of its biome, being an important region from the environmental planning point of view. We compared the performance of multiple machine learning algorithms like decision tree (DT), random forest (RF), support vector machine (SVM), and normal Bayes (NB). We evaluated different dates and locations with all models. Our results demonstrated that the DT learner has, overall, the highest accuracy in this task. The DT algorithm also showed high accuracy when applied on different dates and in the riparian zone of another river. We conclude that the proposed approach is appropriated to accurately map forest vegetation in riparian zones, including temporal context.

Two effective machine learning-aided sea ice monitoring methods are investigated using 42 months of spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data collected by the TechDemoSat-1 (TDS-1). The two-dimensional delay waveforms with different Doppler spread characteristics are applied to extract six features, which are combined to monitor sea ice using the decision tree (DT) and random forest (RF) algorithms. Firstly, the feature sequences are used as input variables and sea ice concentration (SIC) data from the Advanced Microwave Space Radiometer-2 (AMSR-2) are applied as targeted output to train the sea ice monitoring model. Hereafter, the performance of the proposed method is evaluated through comparing with the sea ice edge (SIE) data from the Special Sensor Microwave Imager Sounder (SSMIS) data. The DT- and RF-based methods achieve an overall accuracy of 97.51% and 98.03%, respectively, in the Arctic region and 95.46% and 95.96%, respectively, in the Antarctic region. The DT- and RF-based methods achieve similar accuracies, while the Kappa coefficient of RF-based approach is slightly larger than that of the DT-based approach, which indicates that the RF-based method outperforms the DT-based method. The results show the potential of monitoring sea ice using machine learning-aided GNSS-R approaches.

Cropland mapping via remote sensing can provide crucial information for agri-ecological studies. Time series of remote sensing imagery is particularly useful for agricultural land classification. This study investigated the synergistic use of feature selection, Object-Based Image Analysis (OBIA) segmentation and decision tree classification for cropland mapping using a finer temporal-resolution Landsat-MODIS Enhanced time series in 2007. The enhanced time series extracted 26 layers of Normalized Difference Vegetation Index (NDVI) and five NDVI Time Series Indices (TSI) in a subset of agricultural land of Southwest Missouri. A feature selection procedure using the Stepwise Discriminant Analysis (SDA) was performed, and 10 optimal features were selected as input data for OBIA segmentation, with an optimal scale parameter obtained by quantification assessment of topological and geometric object differences. Using the segmented metrics in a decision tree classifier, an overall classification accuracy of 90.87% was achieved. Our study highlights the advantage of OBIA segmentation and classification in reducing noise from in-field heterogeneity and spectral variation. The crop classification map produced at 30 m resolution provides spatial distributions of annual and perennial crops, which are valuable for agricultural monitoring and environmental assessment studies.

Remote sensing technology serves as a powerful tool for analyzing geospatial characteristics of flood inundation events at various scales. However, the performance of remote sensing methods depends heavily on the flood characteristics and landscape settings. Difficulties might be encountered in mapping the extent of localized flooding with shallow water on riverine floodplain areas, where patches of herbaceous vegetation are interspersed with open water surfaces. To address the difficulties in mapping inundation on areas with complex water and vegetation compositions, a high spatial resolution dataset has to be used to reduce the problem of mixed pixels. The main objective of our study was to investigate the possibilities of using a single date WorldView-2 image of very high spatial resolution and supporting data to analyze spatial patterns of localized flooding on a riverine floodplain. We used a decision tree algorithm with various combinations of input variables including spectral bands of the WorldView-2 image, selected spectral indices dedicated to mapping water surfaces and vegetation, and topographic data. The overall accuracies of the twelve flood extent maps derived with the decision tree method and performed on both pixels and image objects ranged between 77% and 95%. The highest mapping overall accuracy was achieved with a method that utilized all available input data and the object-based image analysis. Our study demonstrates the possibility of using single date WorldView-2 data for analyzing flooding events at high spatial detail despite the absence of spectral bands from the short-waveform region that are frequently used in water related studies. Our study also highlights the importance of topographic data in inundation analyses. The greatest difficulties were met in mapping water surfaces under dense canopy herbaceous vegetation, due to limited water surface exposure and the dominance of vegetation reflectance.

The present work aims to assess the usefulness of five vegetation indices (VI) derived from multispectral UAS imagery to capture the effects of deficit irrigation on the canopy structure of sweet cherry trees (Prunus avium L.) in southeastern Spain. Three irrigation treatments were assayed, a control treatment and two regulated deficit irrigation treatments. Four airborne flights were carried out during two consecutive seasons; to compare the results of the remote sensing VI, the conventional and continuous water status indicators commonly used to manage sweet cherry tree irrigation were measured, including midday stem water potential (Ψs) and maximum daily shrinkage (MDS). Simple regression between individual VIs and Ψs or MDS found stronger relationships in postharvest than in preharvest. Thus, the normalized difference vegetation index (NDVI), resulted in the strongest relationship with Ψs (r2 = 0.67) and MDS (r2 = 0.45), followed by the normalized difference red edge (NDRE). The sensitivity analysis identified the optimal soil adjusted vegetation index (OSAVI) as the VI with the highest coefficient of variation in postharvest and the difference vegetation index (DVI) in preharvest. A new index is proposed, the transformed red range vegetation index (TRRVI), which was the only VI able to statistically identify a slight water deficit applied in preharvest. The combination of the VIs studied was used in two machine learning models, decision tree and artificial neural networks, to estimate the extra labor needed for harvesting and the sweet cherry yield.

Paddy fields play very important environmental roles in food security, water resource management, biodiversity conservation, and climate change. Therefore, reliable broad-scale paddy field maps are essential for understanding these issues related to rice and paddy fields. Here, we propose a novel paddy field mapping method that uses Sentinel-1 synthetic aperture radar (SAR) time series that are robust for cloud cover, supplemented by Sentinel-2 optical images that are more reliable than SAR data for extracting irrigated paddy fields. Paddy fields were provisionally specified by using the Sentinel-1 SAR data and a conventional decision tree method. Then, an additional mask using water and vegetation indexes based on Sentinel-2 optical images was overlaid to remove non-paddy field areas. We used the proposed method to develop a paddy field map for Japan in 2018 with a 30 m spatial resolution. The producer’s accuracy of this map (92.4%) for non-paddy reference agricultural fields was much higher than that of a map developed by the conventional method (57.0%) using only Sentinel-1 data. Our proposed method also reproduced paddy field areas at the prefecture scale better than existing paddy field maps developed by a remote sensing approach.

Geostationary Ocean Color Imager (GOCI) observations are applied to marine fog (MF) detection in combination with Himawari-8 data based on the decision tree (DT) approach. Training and validation of the DT algorithm were conducted using match-ups between satellite observations and in situ visibility data for three Korean islands. Training using different sets of two satellite variables for fog and nonfog in 2016 finally results in an optimal algorithm that primarily uses the GOCI 412-nm Rayleigh-corrected reflectance (Rrc) and its spatial variability index. The algorithm suitably reflects the optical properties of fog by adopting lower Rrc and spatial variability levels, which results in a clear distinction from clouds. Then, cloud removal and fog edge detection in combination with Himawari-8 data enhance the performance of the algorithm, increasing the hit rate (HR) of 0.66 to 1.00 and slightly decreasing the false alarm rate (FAR) of 0.33 to 0.31 for the cloudless samples among the 2017 validation cases. Further evaluation of Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation data reveals the reliability of the GOCI MF algorithm under optically complex atmospheric conditions for classifying marine fog. Currently, the high-resolution (500 m) GOCI MF product is provided to decision-makers in governments and the public sector, which is beneficial to marine traffic management.

A large variety of sound sources in the ocean, including biological, geophysical, and man-made, can be simultaneously monitored over instantaneous continental-shelf scale regions via the passive ocean acoustic waveguide remote sensing (POAWRS) technique by employing a large-aperture densely-populated coherent hydrophone array system. Millions of acoustic signals received on the POAWRS system per day can make it challenging to identify individual sound sources. An automated classification system is necessary to enable sound sources to be recognized. Here, the objectives are to (i) gather a large training and test data set of fin whale vocalization and other acoustic signal detections; (ii) build multiple fin whale vocalization classifiers, including a logistic regression, support vector machine (SVM), decision tree, convolutional neural network (CNN), and long short-term memory (LSTM) network; (iii) evaluate and compare performance of these classifiers using multiple metrics including accuracy, precision, recall and F1-score; and (iv) integrate one of the classifiers into the existing POAWRS array and signal processing software. The findings presented here will (1) provide an automatic classifier for near real-time fin whale vocalization detection and recognition, useful in marine mammal monitoring applications; and (2) lay the foundation for building an automatic classifier applied for near real-time detection and recognition of a wide variety of biological, geophysical, and man-made sound sources typically detected by the POAWRS system in the ocean.

Disasters are an unpredictable way to change land use and land cover. Improving the accuracy of mapping a disaster area at different time is an essential step to analyze the relationship between human activity and environment. The goals of this study were to test the performance of different processing procedures and examine the effect of adding normalized difference vegetation index (NDVI) as an additional classification feature for mapping land cover changes due to a disaster. Using Landsat ETM+ and OLI images of the Bento Rodrigues mine tailing disaster area, we created two datasets, one with six bands, and the other one with six bands plus the NDVI. We used support vector machine (SVM) and decision tree (DT) algorithms to build classifier models and validated models performance using 10-fold cross-validation, resulting in accuracies higher than 90%. The processed results indicated that the accuracy could reach or exceed 80%, and the support vector machine had a better performance than the decision tree. We also calculated each land cover type’s sensitivity (true positive rate) and found that Agriculture, Forest and Mine sites had higher values but Bareland and Water had lower values. Then, we visualized land cover maps in 2000 and 2017 and found out the Mine sites areas have been expanded about twice of the size, but Forest decreased 12.43%. Our findings showed that it is feasible to create a training data pool and use machine learning algorithms to classify a different year’s Landsat products and NDVI can improve the vegetation covered land classification. Furthermore, this approach can provide a venue to analyze land pattern change in a disaster area over time.

Soil salinization is one of the most widespread soil degradation processes on Earth, especially in arid and semi-arid areas. The salinized soil in arid to semi-arid Xinjiang Uyghur Autonomous Region in China accounts for 31% of the area of cultivated land, and thus it is pivotal for the sustainable agricultural development of the area to identify reliable and cost-effective methodologies to monitor the spatial and temporal variations in soil salinity. This objective was accomplished over the study area (Keriya River Basin, northwestern China) by adopting technologies that heavily rely on, and integrate information contained in, a readily available suite of remote sensing datasets. The following procedures were conducted: (1) a selective principle component analysis (S-PCA) fusion image was generated using Phased Array Type L-band SAR (PALSAR) backscattering coefficient (σ°) and Landsat Enhanced Thematic Mapper Plus (ETM+) multispectral image of Keriya River Basin; and (2) a support vector machines (SVM) classification method was employed to classify land cover types with a focus on mapping salinized soils; (3) a cross-validation method was adopted to identify the optimum classification parameters, and obtain an optimal SVM classification model; (4) Radarsat-2 (C band) and PALSAR polarimetric images were used to analyze polarimetric backscattering behaviors in relation to the variation in soil salinization; (5) a decision tree (DT) scheme for multi-source optical and polarimetric SAR data integration was proposed to improve the estimation and monitoring accuracies of soil salinization; and (6) detailed field observations and ground truthing were used for validation of the adopted methodology, and quantity and allocation disagreement measures were applied to assess classification outcome. Results showed that the fusion of passive reflective and active microwave remote sensing data provided an effective tool in detecting soil salinization. Overall accuracy of the adopted SVM classifier with optimal parameters for fused image of ETM+ and PALSAR data was 91.25% with a Kappa coefficient of 0.89, which was further improved by the DT data integration and classification method yielding an accuracy of 93.01% with a Kappa coefficient of 0.92 and lower disagreement of quantity and allocation.

Greenhouse detection and mapping via remote sensing is a complex task, which has already been addressed in numerous studies. In this research, the innovative goal relies on the identification of greenhouse horticultural crops that were growing under plastic coverings on 30 September 2013. To this end, object-based image analysis (OBIA) and a decision tree classifier (DT) were applied to a set consisting of eight Landsat 8 OLI images collected from May to November 2013. Moreover, a single WorldView-2 satellite image acquired on 30 September 2013, was also used as a data source. In this approach, basic spectral information, textural features and several vegetation indices (VIs) derived from Landsat 8 and WorldView-2 multi-temporal satellite data were computed on previously segmented image objects in order to identify four of the most popular autumn crops cultivated under greenhouse in Almería, Spain (i.e., tomato, pepper, cucumber and aubergine). The best classification accuracy (81.3% overall accuracy) was achieved by using the full set of Landsat 8 time series. These results were considered good in the case of tomato and pepper crops, being significantly worse for cucumber and aubergine. These results were hardly improved by adding the information of the WorldView-2 image. The most important information for correct classification of different crops under greenhouses was related to the greenhouse management practices and not the spectral properties of the crops themselves.

Polarimetric SAR (POLSAR) provides a rich set of information about objects on land surfaces. However, not all information works on land surface classification. This study proposes a new, integrated algorithm for optimal urban classification using POLSAR data. Both polarimetric decomposition and time-frequency (TF) decomposition were used to mine the hidden information of objects in POLSAR data, which was then applied in the C5.0 decision tree algorithm for optimal feature selection and classification. Using a NASA/JPL AIRSAR POLSAR scene as an example, the overall accuracy and kappa coefficient of the proposed method reached 91.17% and 0.90 in the L-band, much higher than those achieved by the commonly applied Wishart supervised classification that were 45.65% and 0.41. Meantime, the overall accuracy of the proposed method performed well in both C- and P-bands. Polarimetric decomposition and TF decomposition all proved useful in the process. TF information played a great role in delineation between urban/built-up areas and vegetation. Three polarimetric features (entropy, Shannon entropy, T11 Coherency Matrix element) and one TF feature (HH intensity of coherence) were found most helpful in urban areas classification. This study indicates that the integrated use of polarimetric decomposition and TF decomposition of POLSAR data may provide improved feature extraction in heterogeneous urban areas.

Oil palm plantations have expanded rapidly. Estimating either positive effects on the economy, or negative effects on the environment, requires accurate maps. In this paper, three classification algorithms (Support Vector Machine (SVM), Decision Tree and K-Means) were explored to map oil palm plantations in Cameroon, using PALSAR 50 m Orthorectified Mosaic images and differently sized training samples. SVM had the ideal performance with overall accuracy ranging from 86% to 92% and a Kappa coefficient from 0.76 to 0.85, depending upon the training sample size (ranging from 20 to 500 pixels per class). The advantage of SVM was more obvious when the training sample size was smaller. K-Means required the user’s intervention, and thus, the accuracy depended on the level of his/her expertise and experience. For large-scale mapping of oil palm plantations, the Decision Tree algorithm outperformed both SVM and K-Means in terms of speed and performance. In addition, the decision threshold values of Decision Tree for a large training sample size agrees with the results from previous studies, which implies the possible universality of the decision threshold. If it can be verified, the Decision Tree algorithm will be an easy and robust methodology for mapping oil palm plantations.

A novel approach is proposed for classifying the polarimetric SAR (PolSAR) data by integrating polarimetric decomposition, sub-aperture decomposition and decision tree algorithm. It is composed of three key steps: sub-aperture decomposition, feature extraction and combination, and decision tree classification. Feature extraction and combination is the main contribution to the innovation of the proposed method. Firstly, the full-resolution PolSAR image and its two sub-aperture images are decomposed to obtain the scattering entropy, average scattering angle and anisotropy, respectively. Then, the difference information between the two sub-aperture images are extracted, and combined with the target decomposition features from full-resolution images to form the classification feature set. Finally, C5.0 decision tree algorithm is used to classify the PolSAR image. A comparison between the proposed method and commonly-used Wishart supervised classification was made to verify the improvement of the proposed method on the classification. The overall accuracy using the proposed method was 88.39%, much higher than that using the Wishart supervised classification, which exhibited an overall accuracy of 69.82%. The Kappa Coefficient was 0.83, whereas that using the Wishart supervised classification was 0.56. The results indicate that the proposed method performed better than Wishart supervised classification for landscape classification in urban area using PolSAR data. Further investigation was carried out on the contribution of difference information to PolSAR classification. It was found that the sub-aperture decomposition improved the classification accuracy of forest, buildings and grassland effectively in high-density urban area. Compared with support vector machine (SVM) and QUEST classifier, C5.0 decision tree classifier performs more efficient in time consumption, feature selection and construction of decision rule.

The purpose of this study was to examine how different polarimetric parameters and an object-based approach influence the classification results of various land use/land cover types using fully polarimetric ALOS PALSAR data over coastal wetlands in Yancheng, China. To verify the efficiency of the proposed method, five other classifications (the Wishart supervised classification, the proposed method without polarimetric parameters, the proposed method without an object-based analysis, the proposed method without textural and geometric information and the proposed method using the nearest-neighbor classifier) were applied for comparison. The results indicated that some polarimetric parameters, such as Shannon entropy, Krogager_Kd, Alpha, HAAlpha_T11, VanZyl3_Vol, Derd, Barnes2_T33, polarization fraction, Barnes1_T33, Neuman_delta_mod and entropy, greatly improved the classification results. The shape index was a useful feature in distinguishing fish ponds and rivers. The distance to the sea can be regarded as an important factor in reducing the confusion between herbaceous wetland vegetation and grasslands. Furthermore, the decision tree algorithm increased the overall accuracy by 6.8% compared with the nearest neighbor classifier. This research demonstrated that different polarimetric parameters and the object-based approach significantly improved the performance of land cover classification in coastal wetlands using ALOS PALSAR data.

The origin of large areas dominated by pristine open vegetation that is in sharp contrast with surrounding dense forest within the Amazonian lowland has generally been related to past arid climates, but this is still an issue open for debate. In this paper, we characterize a large open vegetation patch over a residual megafan located in the northern Amazonia. The main goal was to investigate the relationship between this paleolandform and vegetation classes mapped based on the integration of optical and SAR data using the decision tree. Our remote sensing dataset includes PALSAR and TM/Landsat images. Five classes were identified: rainforest; flooded forest; wooded open vegetation; grassy-shrubby open vegetation; and water body. The output map resulting from the integration of PALSAR and TM/Landsat images showed an overall accuracy of 94%. Narrow, elongated and sinuous belts of forest within the open vegetation areas progressively bifurcate into others revealing paleochannels arranged into distributary pattern. Such characteristics, integrated with pre-existing geological information, led us to propose that the distribution of vegetation classes highlight a morphology attributed to a Quaternary megafan developed previous to the modern fluvial tributary system. The characterization of such megafan is important for reconstructing landscape changes associated with the evolution of the Amazon drainage basin.

Accurate estimation and monitoring of rice phenology is necessary for the management and yield prediction of rice. The radar backscattering coefficient, one of the most direct and accessible parameters has been proved to be capable of retrieving rice growth parameters. This paper aims to investigate the possibility of monitoring the rice phenology (i.e., transplanting, vegetative, reproductive, and maturity) using the backscattering coefficients or their simple combinations of multi-temporal RADARSAT-2 datasets only. Four RADARSAT-2 datasets were analyzed at 30 sample plots in Meishan City, Sichuan Province, China. By exploiting the relationships of the backscattering coefficients and their combinations versus the phenology of rice, HH/VV, VV/VH, and HH/VH ratios were found to have the greatest potential for phenology monitoring. A decision tree classifier was applied to distinguish the four phenological phases, and the classifier was effective. The validation of the classifier indicated an overall accuracy level of 86.2%. Most of the errors occurred in the vegetative and reproductive phases. The corresponding errors were 21.4% and 16.7%, respectively. [ABSTRACT FROM AUTHOR]

In the dwindling natural mangrove today, mangrove reforestation projects are conducted worldwide to prevent further losses. Due to monoculture and the low survival rate of artificial mangroves, it is necessary to pay attention to mapping and monitoring them dynamically. Remote sensing techniques have been widely used to map mangrove forests due to their capacity for large-scale, accurate, efficient, and repetitive monitoring. This study evaluated the capability of a 0.5-m Pléiades-1 in classifying artificial mangrove species using both pixel-based and object-based classification schemes. For comparison, three machine learning algorithms--decision tree (DT), support vector machine (SVM), and random forest (RF)--were used as the classifiers in the pixel-based and object-based classification procedure. The results showed that both the pixel-based and object-based approaches could recognize the major discriminations between the four major artificial mangrove species. However, the object-based method had a better overall accuracy than the pixel-based method on average. For pixel-based image analysis, SVM produced the highest overall accuracy (79.63%); for object-based image analysis, RF could achieve the highest overall accuracy (82.40%), and it was also the best machine learning algorithm for classifying artificial mangroves. The patches produced by object-based image analysis approaches presented a more generalized appearance and could contiguously depict mangrove species communities. When the same machine learning algorithms were compared by McNemar's test, a statistically significant difference in overall classification accuracy between the pixel-based and object-based classifications only existed in the RF algorithm. Regarding species, monoculture and dominant mangrove species Sonneratia apetala group 1 (SA1) as well as partly mixed and regular shape mangrove species Hibiscus tiliaceus (HT) could well be identified. However, for complex and easily-confused mangrove species Sonneratia apetala group 2 (SA2) and other occasionally presented mangroves species (OT), only major distributions could be extracted, with an accuracy of about two-thirds. This study demonstrated that more than 80% of artificial mangroves species distribution could be mapped. [ABSTRACT FROM AUTHOR]

This paper intends to find a more cost-effective way for training oil spill classification systems by introducing active learning (AL) and exploring its potential, so that satisfying classifiers could be learned with reduced number of labeled samples. The dataset used has 143 oil spills and 124 look-alikes from 198 RADARSAT images covering the east and west coasts of Canada from 2004 to 2013. Six uncertainty-based active sample selecting (ACS) methods are designed to choose the most informative samples. A method for reducing information redundancy amongst the selected samples and a method with varying sample preference are considered. Four classifiers (k-nearest neighbor (KNN), support vector machine (SVM), linear discriminant analysis (LDA) and decision tree (DT)) are coupled with ACS methods to explore the interaction and possible preference between classifiers and ACS methods. Three kinds of measures are adopted to highlight different aspect of classification performance of these AL-boosted classifiers. Overall, AL proves its strong potential with 4% to 78% reduction on training samples in different settings. The SVM classifier shows to be the best one for using in the AL frame, with perfect performance evolving curves in different kinds of measures. The exploration and exploitation criterion can further improve the performance of the AL-boosted SVM classifier but not of the other classifiers. [ABSTRACT FROM AUTHOR]

Disturbances are key processes in the carbon cycle of forests and other ecosystems. In recent decades, mountain pine beetle (MPB; Dendroctonus ponderosae) outbreaks have become more frequent and extensive in western North America. Remote sensing has the ability to fill the data gaps of long-term infestation monitoring, but the elimination of observational noise and attributing changes quantitatively are two main challenges in its effective application. Here, we present a forest growth trend analysis method that integrates Landsat temporal trajectories and decision tree techniques to derive annual forest disturbance maps over an 11-year period. The temporal trajectory component successfully captures the disturbance events as represented by spectral segments, whereas decision tree modeling efficiently recognizes and attributes events based upon the characteristics of the segments. Validated against a point set sampled across a gradient of MPB mortality, 86.74% to 94.00% overall accuracy was achieved with small variability in accuracy among years. In contrast, the overall accuracies of single-date classifications ranged from 37.20% to 75.20% and only become comparable with our approach when the training sample size was increased at least four-fold. This demonstrates that the advantages of this time series work flow exist in its small training sample size requirement. The easily understandable, interpretable and modifiable characteristics of our approach suggest that it could be applicable to other ecoregions.