Search

Due to budget and sensor technology constraints, a single sensor cannot simultaneously provide observational images with both a high spatial and temporal resolution. To solve the above problem, the spatiotemporal fusion (STF) method was proposed and proved to be an indispensable tool for monitoring land surface dynamics. There are relatively few systematic reviews of the STF method. Bibliometrics is a valuable method for analyzing the scientific literature, but it has not yet been applied to the comprehensive analysis of the STF method. Therefore, in this paper, we use bibliometrics and scientific mapping to analyze the 2967 citation data from the Web of Science from 1991 to 2023 in a metrological manner, covering the themes of STF, data fusion, multi-temporal analysis, and spatial analysis. The results of the literature analysis reveal that the number of articles displays a slow to rapid increase during the study period, but decreases significantly in 2023. Research institutions in China (1059 papers) and the United States (432 papers) are the top two contributors in the field. The keywords "Sentinel", "deep learning" (DL), and "LSTM" (Long Short-Term Memory) appeared most frequently in the past three years. In the future, remote sensing spatiotemporal fusion research can address more of the limitations of heterogeneous landscapes and climatic conditions to improve fused images' accuracy. [ABSTRACT FROM AUTHOR]

The analysis of marine environmental parameters plays a significant role in various aspects, including sea surface target detection, the monitoring of the marine ecological environment, marine meteorology and disaster forecasting, and the monitoring of internal waves in the ocean. In particular, for sea surface target detection, the accurate and high-resolution input of marine environmental parameters is crucial for multi-scale sea surface modeling and the prediction of sea clutter characteristics. In this paper, based on the low-resolution wind speed, significant wave height, and wave period data provided by ECMWF for the surrounding seas of China (specified latitude and longitude range), a deep learning model based on a residual structure is proposed. By introducing an attention module, the model effectively addresses the poor modeling performance of traditional methods like nearest neighbor interpolation and linear interpolation at the edge positions in the image. Experimental results demonstrate that with the proposed approach, when the spatial resolution of wind speed increases from 0.5° to 0.25°, the results achieve a mean square error (MSE) of 0.713, a peak signal-to-noise ratio (PSNR) of 49.598, and a structural similarity index measure (SSIM) of 0.981. When the spatial resolution of the significant wave height increases from 1° to 0.5°, the results achieve a MSE of 1.319, a PSNR of 46.928, and an SSIM of 0.957. When the spatial resolution of the wave period increases from 1° to 0.5°, the results achieve a MSE of 2.299, a PSNR of 44.515, and an SSIM of 0.940. The proposed method can generate high-resolution marine environmental parameter data for the surrounding seas of China at any given moment, providing data support for subsequent sea surface modeling and for the prediction of sea clutter characteristics. [ABSTRACT FROM AUTHOR]

In the context of global sustainable development, solar energy is very widely used. The installed capacity of photovoltaic panels in countries around the world, especially in China, is increasing steadily and rapidly. In order to obtain accurate information about photovoltaic panels and provide data support for the macro-control of the photovoltaic industry, this paper proposed a hierarchical information extraction method, including positioning information and shape information, and carried out photovoltaic panel distribution mapping. This method is suitable for large-scale centralized photovoltaic power plants based on multi-source satellite remote sensing images. This experiment takes the three northwest provinces of China as the research area. First, a deep learning scene classification model, the EfficientNet-B5 model, is used to locate the photovoltaic power plants on 16-m spatial resolution images. This step obtains the area that contains or may contain photovoltaic panels, greatly reducing the study area with an accuracy of 99.97%. Second, a deep learning semantic segmentation model, the U2-Net model, is used to precisely locate photovoltaic panels on 2-m spatial resolution images. This step achieves the exact extraction results of the photovoltaic panels from the area obtained in the previous step, with an accuracy of 97.686%. This paper verifies the superiority of a hierarchical information extraction method in terms of accuracy and efficiency through comparative experiments with DeepLabV3+, U-Net, SegNet, and FCN8s. This meaningful work identified 180 centralized photovoltaic power plants in the study area. Additionally, this method makes full use of the characteristics of different remote sensing data sources. This method can be applied to the rapid extraction of global photovoltaic panels. [ABSTRACT FROM AUTHOR]

The accurate estimation of forest aboveground biomass is of great significance for forest management and carbon balance monitoring. Remote sensing instruments have been widely applied in forest parameters inversion with wide coverage and high spatiotemporal resolution. In this paper, the capability of different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 and Landsat-8) and various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), in aboveground forest biomass estimation. In particular, based on the forest inventory data of Hangzhou in China, the Random Forest (RF), Convolutional Neural Network (CNN) and Convolutional Neural Networks Long Short-Term Memory Networks (CNN-LSTM) algorithms were deployed to construct the forest biomass estimation models, respectively. The estimate accuracies were evaluated under the different configurations of images and methods. The results show that for the SAR data, ALOS-2 has a higher biomass estimation accuracy than the GaoFen-3 and Sentinel-1. Moreover, the GaoFen-6 data is slightly worse than Sentinel-2 and Landsat-8 optical data in biomass estimation. In contrast with the single source, integrating multisource data can effectively enhance accuracy, with improvements ranging from 5% to 10%. The CNN-LSTM generally performs better than CNN and RF, regardless of the data used. The combination of CNN-LSTM and multisource data provided the best results in this case and can achieve the maximum R2 value of up to 0.74. It was found that the majority of the biomass values in the study area in 2018 ranged from 60 to 90 Mg/ha, with an average value of 64.20 Mg/ha. [ABSTRACT FROM AUTHOR]

The rapid and accurate extraction of wide-area coseismic landslide locations is critical in earthquake emergencies. At present, the extraction of coseismic landslides is mainly based on post-earthquake site investigation or the interpretation of human–computer interactions based on remote sensing images. However, the identification efficiency is low, which seriously delays the earthquake emergency response. On the basis of the available multisource and multiscale remote sensing data, numerous studies have been carried out on the methods of coseismic landslide extraction, such as pixel analysis, object-oriented analysis, change detection, and machine learning. However, the effectiveness of coseismic landslide extraction was low in wide areas with complex topographic and geomorphic backgrounds. Therefore, this paper offers a comprehensive study of the factors influencing coseismic landslides and researches rapid and accurate wide-area coseismic landslide extraction methods with multisource remote sensing and geoscience technology. These techniques include digital elevation modeling (DEM) and its derived slopes and aspects. An embedded multichannel spectral–topographic feature fusion model for coseismic landslide extraction based on DeepLab V3+ is proposed, and a knowledge-enhanced deep learning information extraction method integrating geological knowledge is formed. Using the Jiuzhaigou Ms7.0 earthquake (seismic intensity VIII) in Sichuan Province, China, a comparison of landslide extraction models and strategies is carried out. The results show that the model proposed in this paper achieves the best balance in the accuracy and efficiency of wide-area extractions. Using multiple feature data of coseismic landslides, the problem of mixed pixels is solved. The rate of the misidentification of landslides as clouds, snow, buildings, and roads is significantly lower than in other methods. The identified landslide boundaries are smoother and more accurate, and the connectivity is better. Compared with other methods, ours can more accurately eliminate landslides not triggered by the Jiuzhaigou earthquake. While using the image block strategy to ensure extraction efficiency, it also improves the extraction accuracy of wide-area coseismic landslides in complex backgrounds. [ABSTRACT FROM AUTHOR]

Land desertification is one of the serious ecological and environmental problems facing mankind today, which threatens the survival and development of human society. China is one of the countries with the most serious land desertification problems in the world. Therefore, it is of great theoretical value and practical significance to carry out accurate identification and monitoring of land desertification and its influencing factors in ecologically fragile areas of China. This is conducive to curbing land desertification and ensuring regional ecological security. Minqin County, Gansu Province, located in northwestern China, is one of the most serious areas of land desertification, which is also one of the four sandstorm sources in China. Based on ENVINet5, this paper constructs a high-precision land desertification identification method with an accuracy of 93.71%, which analyzes the trend and reasons of land desertification in this area, provides suggestions for disaster prevention in Minqin County. and provides a reference for other similar areas to make corresponding desertification control policies. [ABSTRACT FROM AUTHOR]

Going beyond previous work, this paper presents a systematic literature review that explores the deployment of satellites, drones, and ground-based sensors for yield prediction in agriculture. It covers multiple aspects of the topic, including crop types, key sensor platforms, data analysis techniques, and performance in estimating yield. To this end, datasets from Scopus and Web of Science were analyzed, resulting in the full review of 269 out of 1429 retrieved publications. Our study revealed that China (93 articles, >1800 citations) and the USA (58 articles, >1600 citations) are prominent contributors in this field; while satellites were the primary remote sensing platform (62%), followed by airborne (30%) and proximal sensors (27%). Additionally, statistical methods were used in 157 articles, and model-based approaches were utilized in 60 articles, while machine learning and deep learning were employed in 142 articles and 62 articles, respectively. When comparing methods, machine learning and deep learning methods exhibited high accuracy in crop yield prediction, while other techniques also demonstrated success, contingent on the specific crop platform and method employed. The findings of this study serve as a comprehensive roadmap for researchers and farmers, enabling them to make data-driven decisions and optimize agricultural practices, paving the way towards a fully digitized yield prediction. [ABSTRACT FROM AUTHOR]

Rice is an important food crop in China, and diseases and pests are the main factors threatening its safety, ecology, and efficient production. The development of remote sensing technology provides an important means for non-destructive and rapid monitoring of diseases and pests that threaten rice crops. This paper aims to provide insights into current and future trends in remote sensing for rice crop monitoring. First, we expound the mechanism of remote sensing monitoring of rice diseases and pests and introduce the applications of different commonly data sources (hyperspectral data, multispectral data, thermal infrared data, fluorescence, and multi-source data fusion) in remote sensing monitoring of rice diseases and pests. Secondly, we summarize current methods for monitoring rice diseases and pests, including statistical discriminant type, machine learning, and deep learning algorithm. Finally, we provide a general framework to facilitate the monitoring of rice diseases or pests, which provides ideas and technical guidance for remote sensing monitoring of unknown diseases and pests, and we point out the challenges and future development directions of rice disease and pest remote sensing monitoring. This work provides new ideas and references for the subsequent monitoring of rice diseases and pests using remote sensing. [ABSTRACT FROM AUTHOR]

Timely and accurate crop yield information can ensure regional food security. In the field of predicting crop yields, deep learning techniques such as long short-term memory (LSTM) and convolutional neural networks (CNN) are frequently employed. Many studies have shown that the predictions of models combining the two are better than those of single models. Crop growth can be reflected by the vegetation index calculated using data from remote sensing. However, the use of pure remote sensing data alone ignores the spatial heterogeneity of different regions. In this paper, we tested a total of three models, CNN-LSTM, CNN and convolutional LSTM (ConvLSTM), for predicting the annual rice yield at the county level in Hubei Province, China. The model was trained by ERA5 temperature (AT) data, MODIS remote sensing data including the Enhanced Vegetation Index (EVI), Gross Primary Productivity (GPP) and Soil-Adapted Vegetation Index (SAVI), and a dummy variable representing spatial heterogeneity; rice yield data from 2000–2019 were employed as labels. Data download and processing were based on Google Earth Engine (GEE). The downloaded remote sensing images were processed into normalized histograms for the training and prediction of deep learning models. According to the experimental findings, the model that included a dummy variable to represent spatial heterogeneity had a stronger predictive ability than the model trained using just remote sensing data. The prediction performance of the CNN-LSTM model outperformed the CNN or ConvLSTM model. [ABSTRACT FROM AUTHOR]

The geometric registration of mountainous remote sensing images is always a challenging project, as terrain fluctuations increase the complexity. Deep learning, with its superior computing power and data-driven nature, promises to solve this problem. However, the lack of an appropriate dataset limits the development of deep learning technology for mountainous remote sensing image registration, which it still an unsolved problem in photogrammetry and remote sensing. To remedy this problem, this paper presents a manually constructed imagery dataset of mountainous regions, called the MID (mountainous imagery dataset). To create the MID, we use 38 images from the Gaofen-2 satellite developed by China and generated 4093 pairs of reference and sensed image patches, making this the first real mountainous dataset to our knowledge. Simultaneously, we propose a fully unsupervised, convolutional-network-based iterative registration scheme for the MID. First, the large and global deformation of the reference and sensed images is reduced using an affine registration module, generating the coarse alignment. Then, the local and varied distortions are learned and eliminated progressively using a hybrid dilated convolution (HDC)-based encoder–decoder module with multistep iterations, achieving fine registration results. The HDC aims to increase the receptive field without blocking the artifacts, allowing for the continuous characteristics of the mountainous images of a local region to be represented. We provide a performance analysis of some typical registration algorithms and the developed approach for the MID. The proposed scheme gives the highest registration precision, achieving the subpixel alignment of mountainous remote sensing images. Additionally, the experimental results demonstrate the usability of the MID, which can lay a foundation for the development of deep learning technology in large mountainous remote sensing image registration tasks. [ABSTRACT FROM AUTHOR]

Seismic landslides are the most common and highly destructive earthquake-triggered geological hazards. They are large in scale and occur simultaneously in many places. Therefore, obtaining landslide information quickly after an earthquake is the key to disaster mitigation and relief. The survey results show that most of the landslide-information extraction methods involve too much manual participation, resulting in a low degree of automation and the inability to provide effective information for earthquake rescue in time. In order to solve the abovementioned problems and improve the efficiency of landslide identification, this paper proposes an automatic landslide identification method named improved U-Net model. The intelligent extraction of post-earthquake landslide information is realized through the automatic extraction of hierarchical features. The main innovations of this paper include the following: (1) On the basis of the three RGB bands, three new bands, DSM, slope, and aspect, with spatial information are added, and the number of feature parameters of the training samples is increased. (2) The U-Net model structure is rebuilt by adding residual learning units during the up-sampling and down-sampling processes, to solve the problem that the traditional U-Net model cannot fully extract the characteristics of the six-channel landslide for its shallow structure. At the end of the paper, the new method is used in Jiuzhaigou County, Sichuan Province, China. The results show that the accuracy of the new method is 91.3%, which is 13.8% higher than the traditional U-Net model. It is proved that the new method is effective and feasible for the automatic extraction of post-earthquake landslides. [ABSTRACT FROM AUTHOR]

The frequent occurrence of landslides poses a serious threat to people's lives and property. In order to evaluate disaster hazards based on remote sensing images via machine learning means, it is essential to establish an image database with manually labeled boundaries of landslides. However, the existing datasets do not cover diverse types of mountainous landslides. To address this issue, we propose a high-resolution (1 m) diverse mountainous landslide remote sensing dataset (DMLD), including 990 landslide instances across different terrain in southwestern China. To evaluate the performance of the DMLD, seven state-of-the-art deep learning models with different loss functions were implemented on it. The experiment results demonstrate not only that all of these deep learning methods with different characteristics can adapt well to the DMLD, but also that the DMLD has potential adaptability to other geographical regions. [ABSTRACT FROM AUTHOR]

Forest fires, as severe natural disasters, pose significant threats to ecosystems and human societies, and their spread is characterized by constant evolution over time and space. This complexity presents an immense challenge in predicting the course of forest fire spread. Traditional methods of forest fire spread prediction are constrained by their ability to process multidimensional fire-related data, particularly in the integration of spatiotemporal information. To address these limitations and enhance the accuracy of forest fire spread prediction, we proposed the AutoST-Net model. This innovative encoder–decoder architecture combines a three-dimensional Convolutional Neural Network (3DCNN) with a transformer to effectively capture the dynamic local and global spatiotemporal features of forest fire spread. The model also features a specially designed attention mechanism that works to increase predictive precision. Additionally, to effectively guide the firefighting work in the southwestern forest regions of China, we constructed a forest fire spread dataset, including forest fire status, weather conditions, terrain features, and vegetation status based on Google Earth Engine (GEE) and Himawari-8 satellite. On this dataset, compared to the CNN-LSTM combined model, AutoST-Net exhibits performance improvements of 5.06% in MIou and 6.29% in F1-score. These results demonstrate the superior performance of AutoST-Net in the task of forest fire spread prediction from remote sensing images. [ABSTRACT FROM AUTHOR]

High-spatial-resolution urban buildings play a crucial role in urban planning, emergency response, and disaster management. However, challenges such as missing building contours due to occlusion problems (occlusion between buildings of different heights and buildings obscured by trees), uneven contour extraction due to mixing of building edges with other feature elements (roads, vehicles, and trees), and slow training speed in high-resolution image data hinder efficient and accurate building extraction. To address these issues, we propose a semantic segmentation model composed of a lightweight backbone, coordinate attention module, and pooling fusion module, which achieves lightweight building extraction and adaptive recovery of spatial contours. Comparative experiments were conducted on datasets featuring typical urban building instances in China and the Mapchallenge dataset, comparing our method with several classical and mainstream semantic segmentation algorithms. The results demonstrate the effectiveness of our approach, achieving excellent mean intersection over union (mIoU) and frames per second (FPS) scores on both datasets (China dataset: 85.11% and 110.67 FPS; Mapchallenge dataset: 90.27% and 117.68 FPS). Quantitative evaluations indicate that our model not only significantly improves computational speed but also ensures high accuracy in the extraction of urban buildings from high-resolution imagery. Specifically, on a typical urban building dataset from China, our model shows an accuracy improvement of 0.64% and a speed increase of 70.03 FPS compared to the baseline model. On the Mapchallenge dataset, our model achieves an accuracy improvement of 0.54% and a speed increase of 42.39 FPS compared to the baseline model. Our research indicates that lightweight networks show significant potential in urban building extraction tasks. In the future, the segmentation accuracy and prediction speed can be further balanced on the basis of adjusting the deep learning model or introducing remote sensing indices, which can be applied to research scenarios such as greenfield extraction or multi-class target extraction. [ABSTRACT FROM AUTHOR]

The development of global urbanization has brought about a significant amount of solid waste. These untreated wastes may be dumped in any corner, causing serious pollution to the environment. Thus, it is necessary to accurately obtain their distribution locations and detailed edge information. In this study, a practical deep learning network for recognizing solid waste piles over extensive areas using unmanned aerial vehicle (UAV) imagery has been proposed and verified. Firstly, a high-resolution dataset serving to solid waste detection was created based on UAV aerial data. Then, a dual-branch solid waste semantic segmentation model was constructed to address the characteristics of the integration of solid waste distribution with the environment and the irregular edge morphology. The Context feature branch is responsible for extracting high-level semantic features, while the Spatial feature branch is designed to capture fine-grained spatial details. After information fusion, the model obtained more comprehensive feature representation and segmentation ability. The effectiveness of the improvement was verified through ablation experiments and compared with 13 commonly used semantic segmentation models, demonstrating the advantages of the method in solid waste segmentation tasks, with an overall accuracy of over 94%, and a recall rate of 88.6%—much better than the best performing baselines. Finally, a spatial distribution map of solid waste over Jiaxing district, China was generated by the model inference, which assisted the environmental protection department in completing environmental management. The proposed method provides a feasible approach for the accurately monitoring of solid waste, so as to provide policy support for environmental protection. [ABSTRACT FROM AUTHOR]

Stereo photogrammetric survey used to be used to extract the height of buildings, then to convert the height to number of stories through certain rules to estimate the number of stories of buildings by means of satellite remote sensing. In contrast, we propose a new method using deep learning to estimate the number of stories of buildings from monocular optical satellite image end to end in this paper. To the best of our knowledge, this is the first attempt to directly estimate the number of stories of buildings from monocular satellite images. Specifically, in the proposed method, we extend a classic object detection network, i.e., Mask R-CNN, by adding a new head to predict the number of stories of detected buildings from satellite images. GF-2 images from nine cities in China are used to validate the effectiveness of the proposed methods. The result of experiment show that the mean absolute error of prediction on buildings whose stories between 1–7, 8–20, and above 20 are 1.329, 3.546, and 8.317, respectively, which indicate that our method has possible application potentials in low-rise buildings, but the accuracy in middle-rise and high-rise buildings needs to be further improved. [ABSTRACT FROM AUTHOR]

Remote sensing image segmentation with samples imbalance is always one of the most important issues. Typically, a high-resolution remote sensing image has the characteristics of high spatial resolution and low spectral resolution, complex large-scale land covers, small class differences for some land covers, vague foreground, and imbalanced distribution of samples. However, traditional machine learning algorithms have limitations in deep image feature extraction and dealing with sample imbalance issue. In the paper, we proposed an improved full-convolution neural network, called DeepLab V3+, with loss function based solution of samples imbalance. In addition, we select Sentinel-2 remote sensing images covering the Yuli County, Bayingolin Mongol Autonomous Prefecture, Xinjiang Uygur Autonomous Region, China as data sources, then a typical region image dataset is built by data augmentation. The experimental results show that the improved DeepLab V3+ model can not only utilize the spectral information of high-resolution remote sensing images, but also consider its rich spatial information. The classification accuracy of the proposed method on the test dataset reaches 97.97%. The mean Intersection-over-Union reaches 87.74%, and the Kappa coefficient 0.9587. The work provides methodological guidance to sample imbalance correction, and the established data resource can be a reference to further study in the future. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is significant for landslide risk assessment. However, there remains no consensus on which method is optimal for LSM. This study implements a dynamic approach to landslide hazard mapping by integrating spatio-temporal probability analysis with time-varying ground deformation velocity derived from the MT-InSAR (Multi-Temporal InSAR) method. Reliable landslide susceptibility maps (LSMs) can inform landslide risk managers and government officials. First, sixteen factors were selected to construct a causal factor system for LSM. Next, Pearson correlation analysis, multicollinearity analysis, information gain ratio, and GeoDetector methods were applied to remove the least important factors of STI, plan curvature, TRI, and slope length. Subsequently, information quantity (IQ), logistic regression (LR), frequency ratio (FR), artificial neural network (ANN), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) methods were performed to construct the LSM. The results showed that the distance to a river, slope angle, distance from structure, and engineering geological rock group were the main factors controlling landslide development. A comprehensive set of statistical indicators was employed to evaluate these methods' effectiveness; sensitivity, F1-measure, and AUC (area under the curve) were calculated and subsequently compared to assess the performance of the methods. Machine learning methods' training and prediction accuracy were higher than those of statistical methods. The AUC values of the IQ, FR, LR, BP-ANN, RBF-ANN, RF, SVM, and CNN methods were 0.810, 0.854, 0.828, 0.895, 0.916, 0.932, 0.948, and 0.957, respectively. Although the performance order varied for other statistical indicators, overall, the CNN method was the best, while the BP-ANN and RBF-ANN method was the worst among the five examined machine methods. Hence, adopting the CNN approach in this study can enhance LSM accuracy, catering to the needs of planners and government agencies responsible for managing landslide-prone areas and preventing landslide-induced disasters. [ABSTRACT FROM AUTHOR]

Pine Wilt Disease (PWD) is a devastating global forest disease that spreads rapidly and causes severe ecological and economic losses. Drone remote sensing imaging technology is an effective way to detect PWD and control its spread. However, the existing algorithms for detecting PWD using drone images have low recognition accuracy, difficult image calibration, and slow detection speed. We propose a fast detection algorithm for PWD based on an improved YOLOv8 model. The model first adds a small object detection layer to the Neck module in the YOLOv8 base framework to improve the detection performance of small diseased pine trees and then inserts three attention mechanism modules on the backbone network to extend the sensory field of the network to enhance the extraction of image features of deep diseased pine trees. To evaluate the proposed algorithm framework, we collected and created a dataset in Weihai City, China, containing PWD middle-stage and late-stage infected tree samples. The experimental results show that the improved YOLOv8s-GAM model achieves 81%, 67.2%, and 76.4% optimal detection performance on mAP50, mAP50-95, and Mean evaluation metrics, which is 4.5%, 4.5%, and 2.7% higher than the original YOLOv8s model. Our proposed improved YOLOv8 model basically meets the needs of large-scale PWD epidemic detection and can provide strong technical support for forest protection personnel. [ABSTRACT FROM AUTHOR]

Accurate prediction of future chlorophyll-a (Chl-a) concentrations is of great importance for effective management and early warning of marine ecological systems. However, previous studies primarily focused on chlorophyll-a inversion and reconstruction, while methods for predicting Chl-a concentrations remain limited. To address this issue, we adopted four deep learning approaches, including Convolutional LSTM Network (ConvLSTM), Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Eidetic 3D LSTM (E3D-LSTM), and Self-Attention ConvLSTM (SA-ConvLSTM) models, to predict Chl-a over the Yellow Sea and Bohai Sea (YBS) in China. Furthermore, 14 environmental variables obtained from the remote sensing data of Moderate-resolution Imaging Spectroradiometer (MODIS) and ECMWF Reanalysis v5 (ERA5) were utilized to predict the Chl-a concentrations in the study area. The results showed that all four models performed satisfactorily in predicting Chl-a concentrations in the YBS, with SA-ConvLSTM exhibiting a closer approximation to true values. Furthermore, we analyzed the impact of the Self-Attention Memory Module (SAM) on the prediction results. Compared to the ConvLSTM model, the SA-ConvLSTM model integrated with the SAM module better captured subtle large-scale variations within the study area. The SA-ConvLSTM model exhibited the highest prediction accuracy, and the one-month Pearson correlation coefficient reached 0.887. Our study provides an available approach for anticipating Chl-a concentrations over a large area of sea. [ABSTRACT FROM AUTHOR]

A high-quality remote sensing interpretation dataset has become crucial for driving an intelligent model, i.e., deep learning (DL), to produce land-use/land-cover (LULC) products. The existing remote sensing datasets face the following issues: the current studies (1) lack object-oriented fine-grained information; (2) they cannot meet national standards; (3) they lack field surveys for labeling samples; and (4) they cannot serve for geographic engineering application directly. To address these gaps, the national-standards- and DL-oriented raster and vector benchmark dataset (RVBD) is the first to be established to map LULC for conducting soil water erosion assessment (SWEA). RVBD has the following significant innovation and contributions: (1) it is the first second-level object- and DL-oriented dataset with raster and vector data for LULC mapping; (2) its classification system conforms to the national industry standards of the Ministry of Water Resources of the People's Republic of China; (3) it has high-quality LULC interpretation accuracy assisted by field surveys rather than indoor visual interpretation; and (4) it could be applied to serve for SWEA. Our dataset is constructed as follows: (1) spatio-temporal-spectrum information is utilized to perform automatic vectorization and label LULC attributes conforming to the national standards; and (2) several remarkable DL networks (DenseNet161, HorNet, EfficientNetB7, Vision Transformer, and Swin Transformer) are chosen as the baselines to train our dataset, and five evaluation metrics are chosen to perform quantitative evaluation. Experimental results verify the reliability and effectiveness of RVBD. Each chosen network achieves a minimum overall accuracy of 0.81 and a minimum Kappa of 0.80, and Vision Transformer achieves the best classification performance with overall accuracy of 0.87 and Kappa of 0.86. It indicates that RVBD is a significant benchmark, which could lay a foundation for intelligent interpretation of relevant geographic research about SWEA in the Yangtze River Basin and promote artificial intelligence technology to enrich geographical theories and methods. [ABSTRACT FROM AUTHOR]

The North China agro–pastoral zone is a large, ecologically fragile zone in the arid and semi-arid regions. Quantitative remote sensing inversion of soil organic carbon (SOC) in this region can facilitate understanding of the current status of degraded land restoration and provide data support for carbon cycling research in the region. Deep learning (DNN) for SOC inversion has been W.a hot topic over the past decade, but there have been few studies at the regional scale in the arid and semi-arid zones. In this study, a DNN model with five hidden layers and five skip connections was established using 644 spatially distributed SOC samples and Landsat 8 OLI imagery. The model was compared with the random forest algorithm in terms of generalization ability. The main conclusions were as follows: 1. The DNN algorithm can establish a high-precision SOC inversion model (R2 = 0.52, RMSE = 0.7), with 90% of errors concentrated in the range of −2.5 to 2.5 kg·C/m2; 2. the Boruta variable-screening algorithm can effectively improve the model accuracy of the random forest algorithm, but due to the DNN's better ability to mine hidden information in the data, the improvement effect on the DNN model accuracy is limited; 3. the SOC samples in arid and semi-arid areas are highly positively skewed, with a significant impact on the modeling accuracy of DNN, and conversion is required to obtain a model with better generalization ability; and 4. in arid and semi-arid regions, SOC has a weak correlation with vegetation indices but a stronger correlation with temperature, elevation, and aridity. This study established a reliable deep learning model for SOC density in a large arid and semi-arid region, providing a reference and framework for the establishment of SOC inversion models in other regions. [ABSTRACT FROM AUTHOR]

Landslide detection and distribution mapping are essential components of geohazard prevention. For the extremely difficult problem of automatic forested landslide detection, airborne remote sensing technologies, such as LiDAR and optical cameras, can obtain more accurate landslide monitoring data. In practice, however, airborne LiDAR data and optical images are treated independently. The complementary information of the remote sensing data from multiple sources has not been thoroughly investigated. To address this deficiency, we investigate how to use LiDAR data and optical images together to develop an automatic detection model for forested landslide detection. First, a new dataset for detecting forested landslides in the Jiuzhaigou earthquake region is compiled. LiDAR-derived DEM and hillshade maps are used to mitigate the influence of forest cover on the detection of forested landslides. Second, a new deep learning model called DemDet is proposed for the automatic detection of forested landslides. In the feature extraction component of DemDet, a self-supervised learning module is proposed for extracting geometric features from LiDAR-derived DEM. Additionally, a transformer-based deep neural network is proposed for identifying landslides from hillshade maps and optical images. In the data fusion component of DemDet, an attention-based neural network is proposed to combine DEM, hillshade, and optical images. DemDet is able to extract key features from hillshade images, optical images, and DEM, as demonstrated by experimental results on the proposed dataset. In comparison to ResUNet, LandsNet, HRNet, MLP, and SegFormer, DemDet obtains the highest mean accuracy, mIoU, and F1 values, namely 0.95, 0.67, and 0.777. DemDet is therefore capable of autonomously identifying the forest-covered landslides in the Jiuzhaigou earthquake zone. The results of landslide detection mapping reveal that slopes along roads and seismogenic faults are the most crucial areas requiring geohazard prevention. [ABSTRACT FROM AUTHOR]

Building height serves as an essential feature of urban morphology that provides valuable insights into human socio-cultural behaviors and their impact on the environment in an urban milieu. However, openly accessible building height information at the individual building level is still lacking and remains sorely limited. Previous studies have shown that the ICESat-2′s ATL03/08 products are of good accuracy for urban building heights retrieval, however, these studies are limited to areas with available data coverage. To this end, we propose a method for extracting urban building height by using ICESat-2 ATL03 photons and high-resolution remote sensing images. We first extracted the information of building roof to footprint offsets and building shadows from high resolution imagery using multitasking CNN frameworks. Using the building height samples calculated from ICESat-2 ATL03 photons, we developed a building height estimation method that combines building offset and shadow length information. We assessed the efficacy of the proposed method in the Wujiaochang area of Shanghai city, China. The results indicated that the proposed method is able to extract building height with a MAE of 4.7 m, and outperforms the traditional shadow-based and offset-based method. We believe that the proposed method is a good candidate for accurately retrieving building heights on a city-wide scale. [ABSTRACT FROM AUTHOR]

Limitations in the current capability of monitoring PM2.5 adversely impact air quality management and health risk assessment of PM2.5 exposure. Commonly, ground-based monitoring networks are established to measure the PM2.5 concentrations in highly populated regions and protected areas such as national parks, yet large gaps exist in spatial coverage. Satellite-derived aerosol optical properties serve to complement the missing spatial information of ground-based monitoring networks. However, satellite remote sensing AODs are hampered under cloudy/hazy conditions or during nighttime. Here we strive to overcome the long-standing restriction that surface PM2.5 cannot be obtained with satellite remote sensing under cloudy/hazy conditions or during nighttime. In this work, we introduce a deep spatiotemporal neural network (ST-NN) and demonstrate that it can artfully fill these observational gaps. We quantified the quantitative impact of input variables on the results using sensitivity and visual analysis of the model. This technique provides ground-level PM2.5 concentrations with a high spatial resolution (0.01°) and 24-h temporal coverage, hour-by-hour, complete coverage. In central and eastern China, the 10-fold cross-validation results show that R2 is between 0.8 and 0.9, and RMSE is between 6 and 26 (µg m−3). The relative error varies in different concentration ranges and is generally less than 20%. Better constrained spatiotemporal distributions of PM2.5 concentrations will contribute to improving health effects studies, atmospheric emission estimates, and air quality predictions. [ABSTRACT FROM AUTHOR]

Landslide detection is crucial for natural disaster risk management. Deep-learning-based object-detection algorithms have been shown to be effective in landslide studies. However, advanced algorithms currently used for landslide detection require high computational complexity and memory requirements, limiting their practical applicability. In this study, we developed a high-resolution dataset for landslide-prone regions in China by extracting historical landslide remote sensing images from the Google Earth platform. We propose a lightweight LP-YOLO algorithm based on YOLOv5, with a more-lightweight backbone that incorporates our designed PartitionNet and neck equipped with CSPCrossStage. We constructed and added the vertical and horizontal (VH) block to the backbone, which explores and aggregates long-range information with two directions, while consuming a small amount of computational cost. A new feature fusion structure is proposed to boost information flow and enhance the location accuracy. To speed up the model learning process and improve the accuracy, the SCYLLA-IoU (SIoU) bounding box regression loss function was used to replace the complete IoU (CIoU) loss function. The experimental results demonstrated that our proposed model achieved the highest detection performance (53.7% of Precision, 49% of AP50 and 25.5% of AP50:95) with a speed of 74 fps. Compared to the YOLOv5 model, the proposed model achieved 4% improvement for Precision, 2.6% improvement for AP50, and 2.5% for AP50:95, while reducing the model parameters and FLOPs by 38.4% and 53.1%, respectively. The results indicated that the proposed lightweight method provides a technical guidance for achieving reliable and real-time automatic landslide detection and can be used for disaster prevention and mitigation. [ABSTRACT FROM AUTHOR]

Efficient and accurate landslide recognition is crucial for disaster prevention and post-disaster rescue efforts. However, compared to machine learning, deep learning approaches currently face challenges such as long model runtimes and inefficiency. To tackle these challenges, we proposed a novel knowledge distillation network based on Swin-Transformer (Distilled Swin-Transformer, DST) for landslide recognition. We created a new landslide sample database and combined nine landslide influencing factors (LIFs) with remote sensing images (RSIs) to evaluate the performance of DST. Our approach was tested in Zigui County, Hubei Province, China, and our quantitative evaluation showed that the combined RSIs with LIFs improved the performance of the landslide recognition model. Specifically, our model achieved an Overall Accuracy (OA), Precision, Recall, F1-Score (F1), and Kappa that were 0.8381%, 0.6988%, 0.9334%, 0.8301%, and 0.0125 higher, respectively, than when using only RSIs. Compared with the results of other neural networks, namely ResNet50, Swin-Transformer, and DeiT, our proposed deep learning model achieves the best OA (98.1717%), Precision (98.1672%), Recall (98.1667%), F1 (98.1615%), and Kappa (0.9766). DST has the lowest number of FLOPs, which is crucial for improving computational efficiency, especially in landslide recognition applications after geological disasters. Our model requires only 2.83 GFLOPs, which is the lowest among the four models and is 1.8242 GFLOPs, 1.741 GFLOPs, and 2.0284 GFLOPs less than ResNet, Swin, and DeiT, respectively. The proposed method has good applicability in rapid recognition scenarios after geological disasters. [ABSTRACT FROM AUTHOR]

The pine wood nematode (PWN; Bursaphelenchus xylophilus) is a major invasive species in China, causing huge economic and ecological damage to the country due to the absence of natural enemies and the extremely rapid rate of infection and spread. Accurate monitoring of pine wilt disease (PWD) is a prerequisite for timely and effective disaster prevention and control. UAVs can carry hyperspectral sensors for near-ground remote sensing observations, which can obtain rich spatial and spectral information and have the potential for infected tree identification. Deep learning techniques can use rich multidimensional data to mine deep features in order to achieve tasks such as classification and target identification. Therefore, we propose an improved Mask R-CNN instance segmentation method and an integrated approach combining a prototypical network classification model with an individual tree segmentation algorithm to verify the possibility of deep learning models and UAV hyperspectral imagery for identifying infected individual trees at different stages of PWD. The results showed that both methods achieved good performance for PWD identification: the overall accuracy of the improved Mask R-CNN with the screened bands as input data was 71%, and the integrated method combining prototypical network classification model with individual tree segmentation obtained an overall accuracy of 83.51% based on the screened bands data, in which the early infected pine trees were identified with an accuracy of 74.89%. This study indicates that the improved Mask R-CNN and integrated prototypical network method are effective and practical for PWD-infected individual trees identification using UAV hyperspectral data, and the proposed integrated prototypical network enables early identification of PWD, providing a new technical guidance for early monitoring and control of PWD. [ABSTRACT FROM AUTHOR]

Understanding the evolution of river morphology is crucial for comprehending changes in water resources and implementing development projects along rivers. This study proposes an integrated approach utilizing remote sensing image data combined with deep learning and visual interpretation algorithms to analyze continuous-type changes in river morphology. This research focuses on the lower reaches of the Minjiang River in China and comprehensively analyzes the river's morphological evolution from 1986 to 2021. The results show that the proposed method of river water identification in this study demonstrates high accuracy and effectiveness, with an F1 score and Kappa coefficient greater than 0.96 and 0.91, respectively. The morphology of the river channel remains stable in the upstream and estuarine sections of the study region while undergoing substantial alterations in the middle section. Additionally, this study also identifies several factors that significantly impact the evolution of river morphology, including reservoir construction, river sediment mining, river training measures, geological conditions, and large flood events. The findings of this study can provide some insights into the management and conservation of water resources. [ABSTRACT FROM AUTHOR]

In recent years, remote sensing techniques such as satellite and drone-based imaging have been used to monitor Pine Wilt Disease (PWD), a widespread forest disease that causes the death of pine species. Researchers have explored the use of remote sensing imagery and deep learning algorithms to improve the accuracy of PWD detection at the single-tree level. This study introduces a novel framework for PWD detection that combines high-resolution RGB drone imagery with free-access Sentinel-2 satellite multi-spectral imagery. The proposed approach includes an PWD-infected tree detection model named YOLOv5-PWD and an effective data augmentation method. To evaluate the proposed framework, we collected data and created a dataset in Xianning City, China, consisting of object detection samples of infected trees at middle and late stages of PWD. Experimental results indicate that the YOLOv5-PWD detection model achieved 1.2% higher mAP compared to the original YOLOv5 model and a further improvement of 1.9% mAP was observed after applying our dataset augmentation method, which demonstrates the effectiveness and potential of the proposed framework for PWD detection. [ABSTRACT FROM AUTHOR]

Recognizing and classifying natural or artificial geo-objects under complex geo-scenes using remotely sensed data remains a significant challenge due to the heterogeneity in their spatial distribution and sampling bias. In this study, we propose a deep learning method of surface complexity analysis based on multiscale entropy. This method can be used to reduce sampling bias and preserve entropy-based invariance in learning for the semantic segmentation of land use and land cover (LULC) images. Our quantitative models effectively identified and extracted local surface complexity scores, demonstrating their broad applicability. We tested our method using the Gaofen-2 image dataset in mainland China and accurately estimated multiscale complexity. A downstream evaluation revealed that our approach achieved similar or better performance compared to several representative state-of-the-art deep learning methods. This highlights the innovative and significant contribution of our entropy-based complexity analysis and its applicability in improving LULC semantic segmentations through optimal stratified sampling and constrained optimization, which can also potentially be used to enhance semantic segmentation under complex geo-scenes using other machine learning methods. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polarization data. To address these issues, a new land cover mapping framework which is suitable for complex terrain is proposed based on Gaofen-3 data of ascending and descending orbits. Firstly, the geometric distortion area is determined according to the local incident angle, based on analysis of the SAR imaging mechanism, and the correct polarization information of the opposite track is used to compensate for the geometric distortion area, including layovers and shadows. Then, the dual orbital polarization characteristics (DOPC) and dual polarization radar vegetation index (DpRVI) of dual-pol SAR data are extracted, and the optimal feature combination is found by means of Jeffries–Matusita (J-M) distance analysis. Finally, the deep learning method 2D convolutional neural network (2D-CNN) is applied to classify the compensated images. The proposed method was applied to a mountainous region of the Danjiangkou ecological protection area in China. The accuracy and reliability of the method were experimentally compared using the uncompensated images and the images without DpRVI. Quantitative evaluation revealed that the proposed method achieved better performance in complex terrain areas, with an overall accuracy (OA) score of 0.93, and a Kappa coefficient score of 0.92. Compared with the uncompensated image, OA increased by 5% and Kappa increased by 6%. Compared with the images without DpRVI, OA increased by 4% and Kappa increased by 5%. In summary, the results demonstrate the importance of ascending and descending orbit data to compensate geometric distortion and reveal the effectiveness of optimal feature combination including DpRVI. Its simple and effective polarization information compensation capability can broaden the promising application prospects of SAR images. [ABSTRACT FROM AUTHOR]

With the development of deep learning and remote sensing technologies in recent years, many semantic segmentation methods based on convolutional neural networks (CNNs) have been applied to road extraction. However, previous deep learning-based road extraction methods primarily used RGB imagery as an input and did not take advantage of the spectral information contained in hyperspectral imagery. These methods can produce discontinuous outputs caused by objects with similar spectral signatures to roads. In addition, the images obtained from different Earth remote sensing sensors may have different spatial resolutions, enhancing the difficulty of the joint analysis. This work proposes the Multiscale Fusion Attention Network (MSFANet) to overcome these problems. Compared to traditional road extraction frameworks, the proposed MSFANet fuses information from different spectra at multiple scales. In MSFANet, multispectral remote sensing data is used as an additional input to the network, in addition to RGB remote sensing data, to obtain richer spectral information. The Cross-source Feature Fusion Module (CFFM) is used to calibrate and fuse spectral features at different scales, reducing the impact of noise and redundant features from different inputs. The Multiscale Semantic Aggregation Decoder (MSAD) fuses multiscale features and global context information from the upsampling process layer by layer, reducing information loss during the multiscale feature fusion. The proposed MSFANet network was applied to the SpaceNet dataset and self-annotated images from Chongzhou, a representative city in China. Our MSFANet performs better over the baseline HRNet by a large margin of +6.38 IoU and +5.11 F1-score on the SpaceNet dataset, +3.61 IoU and +2.32 F1-score on the self-annotated dataset (Chongzhou dataset). Moreover, the effectiveness of MSFANet was also proven by comparative experiments with other studies. [ABSTRACT FROM AUTHOR]

High-resolution remote-sensing imagery has proven useful for building extraction. Unfortunately, due to the high acquisition costs and infrequent availability of high-resolution imagery, low-resolution images are more practical for large-scale mapping or change tracking of buildings. However, extracting buildings from low-resolution images is a challenging task. Compared with high-resolution images, low-resolution images pose two critical challenges in terms of building segmentation: the effects of fuzzy boundary details on buildings and the lack of local textures. In this study, we propose a sparse geometric feature attention network (SGFANet) based on multi-level feature fusion to address the aforementioned issues. From the perspective of the fuzzy effect, SGFANet enhances the representative boundary features by calculating the point-wise affinity of the selected feature points in a top-down manner. From the perspective of lacking local textures, we convert the top-down propagation from local to non-local by introducing the grounding transformer harvesting the global attention of the input image. SGFANet outperforms competing baselines on remote-sensing images collected worldwide and multiple sensors at 4 and 10 m resolution, thereby, improving the IoU by at least 0.66%. Notably, our method is robust and generalizable, which makes it useful for extending the accessibility and scalability of building dynamic tracking across developing areas (e.g., the Xiong'an New Area in China) by using low-resolution images. [ABSTRACT FROM AUTHOR]

Estimation of the number and geo-location of oil wells is important for policy holders considering their impact on energy resource planning. With the recent development in optical remote sensing, it is possible to identify oil wells from satellite images. Moreover, the recent advancement in deep learning frameworks for object detection in remote sensing makes it possible to automatically detect oil wells from remote sensing images. In this paper, we collected a dataset named Northeast Petroleum University–Oil Well Object Detection Version 1.0 (NEPU–OWOD V1.0) based on high-resolution remote sensing images from Google Earth Imagery. Our database includes 1192 oil wells in 432 images from Daqing City, which has the largest oilfield in China. In this study, we compared nine different state-of-the-art deep learning models based on algorithms for object detection from optical remote sensing images. Experimental results show that the state-of-the-art deep learning models achieve high precision on our collected dataset, which demonstrate the great potential for oil well detection in remote sensing. [ABSTRACT FROM AUTHOR]

Lakes have been identified as an important indicator of climate change and a finer lake area can better reflect the changes. In this paper, we propose an effective unsupervised deep gradient network (UDGN) to generate a higher resolution lake area from remote sensing images. By exploiting the power of deep learning, UDGN models the internal recurrence of information inside the single image and its corresponding gradient map to generate images with higher spatial resolution. The gradient map is derived from the input image to provide important geographical information. Since the training samples are only extracted from the input image, UDGN can adapt to different settings per image. Based on the superior adaptability of the UDGN model, two strategies are proposed for super-resolution (SR) mapping of lakes from multispectral remote sensing images. Finally, Landsat 8 and MODIS (moderate-resolution imaging spectroradiometer) images from two study areas on the Tibetan Plateau in China were used to evaluate the performance of UDGN. Compared with four unsupervised SR methods, UDGN obtained the best SR results as well as lake extraction results in terms of both quantitative and visual aspects. The experiments prove that our approach provides a promising way to break through the limitations of median-low resolution remote sensing images in lake change monitoring, and ultimately support finer lake applications. [ABSTRACT FROM AUTHOR]

There are a large number of lakes with beaded distribution in the semi-arid areas of the Inner Mongolian Plateau, and some of them have degraded or even disappeared during the past three decades. We studied the reasons of the disappearance of these lakes by determining the way of replenishment of these lakes and the impact of the natural-social environment of the basin, with the aim of saving these gradually disappearing lakes. Based on remote sensing image and hydrological analysis, this paper studied the recharge of Daihai Lake and Huangqihai Lake. The deep learning method was used to establish the time-series of lake evolution. The same method was combined with the innovative woodland and farmland extraction method to set up the time-series of ground classification composition in the basins. Using relevant survey data, combined with soil water infiltration test, water chemical, and isotopic signature analysis of various water bodies, we found that the Daihai Lake area is the largest in dry season and the smallest in rainy season and the other lake is not satisfied with this phenomenon. In addition, we calculated the specific recharge and consumption of the study basin. These experiments indicated that the exogenous groundwater is recharged directly through the faults at the bottom of Daihai Lake, while the exogenous groundwater is recharged in Huangqihai Lake through rivers indirectly. Large-scale exploitation of groundwater for agricultural irrigation and industrial production is the main cause of lake degradation. Reducing the extraction of groundwater for agricultural irrigation is an important measure to restore lake ecology. [ABSTRACT FROM AUTHOR]

The development of effective and comprehensive methods for mapping and monitoring reservoirs is essential for the utilization of water resources and flood control. Remote sensing has the great advantages of broad spatial coverage and regular revisit to meet the demand of large-scale and long-term tasks of earth observation. Although there already exist some methods for coarse-grained identification of reservoirs at region-level in remote sensing images, it remains a challenge to recognize and localize reservoirs accurately with insufficiency of object details and samples annotated. This study focuses on the fine-grained identification and location of reservoirs with a two-stage CNN framework method, which is comprised of a coarse classification between aquatic and land areas of image patches and a fine detection of reservoirs in aquatic patches with precise geographical coordinates. Moreover, a NIR RCNN detection network is proposed to make use of the multi-spectral characteristics of Sentinel-2 images. To verify the effectiveness of our proposed method, we construct a reservoir and dam dataset of 36 Sentinel-2 images which are sampled in various provinces across China and annotated at the instance level by manual work. The experimental results in the test set show that the two-stage CNN method achieves an average recall of 80.83% nationwide, and the comparison between reservoirs recognized by the proposed model and those provided by the China Institute of Water Resources and Hydropower Research verifies that the model reaches a recall of about 90%. Both the indicator evaluation and visualization of identification results have shown the applicability of the proposed method to reservoir recognition in remote sensing images. Being the first attempt to make a fine-grained identification of reservoirs at the instance level, the two-stage CNN framework, which can automatically identify and localize reservoirs in remote sensing images precisely, shows the prospect to be a useful tool for large-scale and long-term reservoir monitoring. [ABSTRACT FROM AUTHOR]

Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China's major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average R2 of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions. [ABSTRACT FROM AUTHOR]

Deep learning-based semantic segmentation technology is widely applied in remote sensing and has achieved excellent performance in remote sensing image target extraction. Greenhouses play an important role in the development of agriculture in China. However, the rapid expansion of greenhouses has had a series of impacts on the environment. Therefore, the extraction of large-scale greenhouses is crucial for the sustainable development of agriculture and environmental governance. It is difficult for existing methods to acquire precise boundaries. Therefore, we propose a spatial convolutional long short-term memory structure, which can fully consider the spatial continuity of ground objects. We use multitask learning to improve the network's ability to extract image boundaries and promote convergence through auxiliary loss. We propose a superpixel optimization module to optimize the main-branch results of network semantic segmentation using more precise boundaries obtained by advanced superpixel segmentation techniques. Compared with other mainstream methods, our proposed structure can better consider spatial information and obtain more accurate results. We chose Shandong Province, China, as the study area and used Gaofen-1 satellite remote sensing images to create a new greenhouse dataset. Our method achieved an F1 score of 77%, a significant improvement over mainstream semantic segmentation networks, and it could extract greenhouse results with more precise boundaries. We also completed large-scale greenhouse mapping for Shandong Province, and the results show that our proposed modules have great potential in greenhouse extraction. [ABSTRACT FROM AUTHOR]

Attempts have been made to incorporate remote sensing techniques and in situ observations for enhanced water quality assessments. Estimations of nonoptical indicators sensitive to water environment changes, however, have not been fully studied, mainly due to complex nonlinear relationships between the observed values and surface reflectance. In this study, we applied a novel deep learning approach driven by a range of spectral properties to retrieve 6-year changes in water quality variables, i.e., Chl-a, BOD, TN, CODMn, NH3-N, and TP, on a monthly basis between 2013 and 2018 at Dongping Lake, an impounded lake located in the Yellow River in China. Band arithmetic was used to compute 26 predictors from Landsat 8 OLI imagery for model inputs. The results showed generally strong agreement between in situ and ConvLSTM-derived lake variables, generating R2 of 0.92, 0.88, 0.84, 0.80, 0.83, and 0.77 for TN, NH3-N, CODMn, Chl-a, TP, and BOD, which suggest good performance of the developed model. We then used statistical analysis to identify the spatial and temporal heterogeneity. The framework established in this study has applications in effective water quality monitoring and serves as an alarming tool for water-environment management in the complex inland lake waters. [ABSTRACT FROM AUTHOR]

In recent years, the development of China's marine aquaculture has brought serious challenges to the marine ecological environment. Therefore, it is significant to classify and extract the aquaculture zone and spatial distribution in order to provide a reference for aquaculture management. However, considering the complex marine aquaculture environment, it is difficult for traditional remote sensing technology and deep learning to achieve a breakthrough in the extraction of large-scale aquaculture zones so far. This study proposes a method based on the combination of piecewise linear stretching and R3Det to classify and extract raft aquaculture and cage aquaculture zones. The grayscale value is changed by piecewise linear stretching to reduce the influence of complex aquaculture backgrounds on the extraction accuracy, to effectively highlight the appearance characteristics of the aquaculture zone, and to improve the image contrast. On this basis, the aquaculture zone is classified and extracted by R3Det. Taking the aquaculture zone of Sansha Bay as the research object, the experimental results showed that the accuracy of R3Det in extracting the number of raft aquaculture and cage aquaculture zones was 98.91% and 97.21%, respectively, and the extraction precision of the area of the aquaculture zone reached 92.08%. The proposed method can classify and extract large-scale marine aquaculture zones more simply and efficiently than common remote sensing techniques. [ABSTRACT FROM AUTHOR]

The spatial pattern and temporal variation in paddy rice areas captured by remote sensing imagery provide an effective way of performing crop management and developing suitable agricultural policies. However, fragmented and scattered rice paddies due to undulating and varied topography, and the availability and quality of remote sensing images (e.g., frequent cloud coverage) pose significant challenges to accurate long-term rice mapping, especially for traditional pixel and phenological methods in subtropical monsoon regions. This study proposed a superpixel and deep-learning-based time series method to analyze Landsat time series data for paddy rice classification in complex landscape regions. First, a superpixel segmentation map was generated using a dynamic-time-warping-based simple non-iterative clustering algorithm with preprocessed spectral indices (SIs) time series data. Second, the SI images were overlaid onto the superpixel map to construct mean SIs time series for each superpixel. Third, a multivariate long short-term memory full convolution neural network (MLSTM-FCN) classifier was employed to learn time series features of rice paddies to produce accurate paddy rice maps. The method was evaluated using Landsat imagery from 2000 to 2020 in Cengong County, Guizhou Province, China. Results indicate that the superpixel MLSTM-FCN achieved a high performance with an overall accuracy varying from 0.9547 to 0.9721, which presents an 0.17–1.23% improvement compared to the random forest method. This study showed that combining spectral, spatial, and temporal features with deep learning methods can generate accurate paddy rice maps in complex landscape regions. [ABSTRACT FROM AUTHOR]

The continuous and extensive pinewood nematode disease has seriously threatened the sustainable development of forestry in China. At present, many studies have used high-resolution remote sensing images combined with a deep semantic segmentation algorithm to identify standing dead trees in the red attack period. However, due to the complex background, closely distributed detection scenes, and unbalanced training samples, it is difficult to detect standing dead trees (SDTs) in a variety of complex scenes by using conventional segmentation models. In order to further solve the above problems and improve the recognition accuracy, we proposed a new detection method called multi-scale spatial supervision convolutional network (MSSCN) to identify SDTs in a wide range of complex scenes based on airborne remote sensing imagery. In the method, a Gaussian kernel approach was used to generate a confidence map from SDTs marked as points for training samples, and a multi-scale spatial attention block was added into fully convolutional neural networks to reduce the loss of spatial information. Further, an augmentation strategy called copy–pasting was used to overcome the lack of efficient samples in this research area. Validation at four different forest areas belonging to two forest types and two diseased outbreak intensities showed that (1) the copy–pasting method helps to augment training samples and can improve the detecting accuracy with a suitable oversampling rate, and the best oversampling rate should be carefully determined by the input training samples and image data. (2) Based on the two-dimensional spatial Gaussian kernel distribution function and the multi-scale spatial attention structure, the MSSCN model can effectively find the dead tree extent in a confidence map, and by following this with maximum location searching we can easily locate the individual dead trees. The averaged precision, recall, and F1-score across different forest types and disease-outbreak-intensity areas can achieve 0.94, 0.84, and 0.89, respectively, which is the best performance among FCN8s and U-Net. (3) In terms of forest type and outbreak intensity, the MSSCN performs best in pure pine forest type and low-outbreak-intensity areas. Compared with FCN8s and U-Net, the MSSCN can achieve the best recall accuracy in all forest types and outbreak-intensity areas. Meanwhile, the precision metric is also maintained at a high level, which means that the proposed method provides a trade-off between the precision and recall in detection accuracy. [ABSTRACT FROM AUTHOR]

Forests are crucial in carbon sequestration and oxygen release. An accurate assessment of forest carbon storage is meaningful for Chinese cities to achieve carbon peak and carbon neutrality. For an accurate estimation of regional-scale forest aboveground carbon density, this study applied a Sentinel-2 multispectral instrument (MSI), Advanced Land Observing Satellite 2 (ALOS-2) L-band, and Sentinel-1 C-band synthetic aperture radar (SAR) to estimate and map the forest carbon density. Considering the forest field-inventory data of eastern China from 2018 as an experimental sample, we explored the potential of the deep-learning algorithms convolutional neural network (CNN) and Keras. The results showed that vegetation indices from Sentinel-2, backscatter and texture characters from ALOS-2, and coherence from Sentinel-1 were principal contributors to the forest carbon-density estimation. Furthermore, the CNN model was found to perform better than traditional models. Results of forest carbon-density estimation validated the improvements effectively by combining the optical and radar data. Compared with traditional regression methods, deep learning has a higher potential for accurately estimating forest carbon density using multisource remote-sensing data. [ABSTRACT FROM AUTHOR]

Large-scale infrastructure, such as China–Europe Railway Express (CER-Express), which connects countries and regions across Asia and Europe, has a potentially profound effect on land use, as evidenced by changes in land cover along the railway. To ensure sustainable development of such infrastructure and appropriate land administration, effective ways to monitor and assess its impact need to be developed. Remote sensing based on publicly available satellite imagery represents an obvious choice. In the study presented here, we employ a state-of-the-art deep-learning-based approach to automatically detect different types of land cover based on multispectral Sentinel-2 imagery. We then use these data to conduct and present a study of the changes in land use in two geopolitically diverse regions of interest (in Serbia and China and with and without CER-Express infrastructure) for the period of the last three years. Our results show that the standard image-patch-based land cover classification approaches suffer a significant drop in performance in our target scenario in which each pixel needs to be assigned a cove class, but still, validate the applicability of the proposed approach as a remote sensing tool to support the sustainable development of large infrastructure. We discuss the technical limitations of the proposed approach in detail and potential ways in which it can be improved. [ABSTRACT FROM AUTHOR]

Automatic building extraction based on high-resolution aerial imagery is an important challenge with a wide range of practical applications. One of the mainstream methods for extracting buildings from high-resolution images is deep learning because of its excellent deep feature extraction capability. However, existing models suffer from the problems of hollow interiors of some buildings and blurred boundaries. Furthermore, the increase in remote sensing image resolution has also led to rough segmentation results. To address these issues, we propose a generative adversarial segmentation network (ASGASN) for pixel-level extraction of buildings. The segmentation network of this framework adopts an asymmetric encoder–decoder structure. It captures and aggregates multiscale contextual information using the ASPP module and improves the classification and localization accuracy of the network using the global convolutional block. The discriminator network is an adversarial network that correctly discriminates the output of the generator and ground truth maps and computes multiscale L 1 loss by fusing multiscale feature mappings. The segmentation network and the discriminator network are trained alternately on the WHU building dataset and the China typical cities building dataset. Experimental results show that the proposed ASGASN can accurately identify different types of buildings and achieve pixel-level high accuracy extraction of buildings. Additionally, compared to available deep learning models, ASGASN also achieved the highest accuracy performance (89.4% and 83.6% IoU on these two datasets, respectively). [ABSTRACT FROM AUTHOR]

China's urbanization has dramatically accelerated in recent decades. Land for urban build-up has changed not only in large cities but also in small counties. Land cover mapping is one of the fundamental tasks in the field of remote sensing and has received great attention. However, most current mapping requires a significant manual effort for labeling or classification. It is of great practical value to use the existing low-resolution label data for the classification of higher resolution images. In this regard, this work proposes a method based on noise-label learning for fine-grained mapping of urban build-up land in a county in central China. Specifically, this work produces a build-up land map with a resolution of 10 m based on a land cover map with a resolution of 30 m. Experimental results show that the accuracy of the results is improved by 5.5% compared with that of the baseline method. This notion indicates that the time required to produce a fine land cover map can be significantly reduced using existing coarse-grained data. [ABSTRACT FROM AUTHOR]

Digital soil mapping has emerged as a new method to describe the spatial distribution of soils economically and efficiently. In this study, a lightweight soil organic matter (SOM) mapping method based on a deep residual network, which we call LSM-ResNet, is proposed to make accurate predictions with background covariates. ResNet not only integrates spatial background information around the observed environmental covariates, but also reduces problems such as information loss, which undermines the integrity of information and reduces prediction uncertainty. To train the model, rectified linear units, mean squared error, and adaptive momentum estimation were used as the activation function, loss/cost function, and optimizer, respectively. The method was tested with Landsat5, the meteorological data from WorldClim, and the 1602 sampling points set from Xinxiang, China. The performance of the proposed LSM-ResNet was compared to a traditional machine learning algorithm, the random forest (RF) algorithm, and a training set (80%) and a test set (20%) were created to test both models. The results showed that the LSM-ResNet (RMSE = 6.40, R2 = 0.51) model outperformed the RF model in both the roots mean square error (RMSE) and coefficient of determination (R2), and the training accuracy was significantly improved compared to RF (RMSE = 6.81, R2 = 0.46). The trained LSM-ResNet model was used for SOM prediction in Xinxiang, a district of plain terrain in China. The prediction maps can be deemed an accurate reflection of the spatial variability of the SOM distribution. [ABSTRACT FROM AUTHOR]

Water is an imperative part of the Earth and an essential resource in human life and production. Under the effects of climate change and human activities, the spatial and temporal distribution of water bodies has been changing, and the shortage of water resources is becoming increasingly serious worldwide. Therefore, the monitoring of water bodies is indispensable. Remote sensing has the advantages of real time, wide coverage, and rich information and has become a brand-new technical means to quickly obtain water information. This study summarizes the current common methods of water extraction based on optical and radar images, including the threshold method, support vector machine, decision tree, object-oriented extraction, and deep learning, as well as the advantages and disadvantages of each method. These methods were applied to the Huai River Basin in China and Nam Co on the Qinghai-Tibet Plateau. The extraction results show that all the aforementioned approaches can obtain reliable results. Among them, the threshold segmentation method based on normalized difference water index is more robust than others. In the water extraction process, there are still many problems that restrict the accuracy of the results. In the future, researchers will continue to search for more automatic, extensive, and high-precision water extraction methods. [ABSTRACT FROM AUTHOR]