Jiawei Zou, Hao Li, Chao Ding, Suhong Liu, Qingdong Shi
Populus euphratica is a unique constructive tree species within riparian desert areas that is essential for maintaining oasis ecosystem stability. The Tarim River Basin contains the most densely distributed population of P. euphratica forests in the world, and obtaining accurate distribution data in the mainstream of the Tarim River would provide important support for its protection and restoration. We propose a new method for automatically extracting P. euphratica using Sentinel-1 and 2 and Landsat-8 images based on the Google Earth Engine cloud platform and the random forest algorithm. A mask of the potential distribution area of P. euphratica was created based on prior knowledge to save computational resources. The NDVI (Normalized Difference Vegetation Index) time series was then reconstructed using the preferred filtering method to obtain phenological parameter features, and the random forest model was input by combining the phenological parameter, spectral index, textural, and backscattering features. An active learning method was employed to optimize the model and obtain the best model for extracting P. euphratica. Finally, the map of natural P. euphratica forests with a resolution of 10 m in the mainstream of the Tarim River was obtained. The overall accuracy, producer’s accuracy, user’s accuracy, kappa coefficient, and F1-score of the map were 0.96, 0.98, 0.95, 0.93, and 0.96, respectively. The comparison experiments showed that simultaneously adding backscattering and textural features improved the P. euphratica extraction accuracy, while textural features alone resulted in a poor extraction effect. The method developed in this study fully considered the prior and posteriori information and determined the feature set suitable for the P. euphratica identification task, which can be used to quickly obtain accurate large-area distribution data of P. euphratica. The method can also provide a reference for identifying other typical desert vegetation.
胡杨是沙漠河岸地区独特的建群树种，对维持绿洲生态系统的稳定至关重要。塔里木河流域拥有世界上分布最密集的胡杨林种群，获得塔里木河主流地区的准确分布数据将为胡杨林的保护和恢复提供重要支持。我们基于谷歌地球引擎云平台和随机森林算法，提出了一种利用 Sentinel-1 和 2 以及 Landsat-8 图像自动提取 P. euphratica 的新方法。为了节省计算资源，我们根据先验知识创建了一个 P. euphratica 潜在分布区的掩膜。然后使用优选滤波方法重建归一化植被指数（NDVI）时间序列，以获得物候参数特征，并结合物候参数、光谱指数、纹理和反向散射特征输入随机森林模型。采用主动学习方法对模型进行优化，获得提取极乐鸟的最佳模型。最后，得到了塔里木河主流地区分辨率为 10 米的天然欧鼠李森林分布图。该地图的总体准确度、生产者准确度、用户准确度、卡帕系数和 F1 分数分别为 0.96、0.98、0.95、0.93 和 0.96。对比实验表明，同时添加反向散射特征和纹理特征提高了极乐鸟的提取精度，而单独添加纹理特征则提取效果不佳。本研究建立的方法充分考虑了先验信息和后验信息，确定了适合于极乐鸟识别任务的特征集，可用于快速获取准确的极乐鸟大面积分布数据。该方法还可为识别其他典型沙漠植被提供参考。
{"title":"Mapping Natural Populus euphratica Forests in the Mainstream of the Tarim River Using Spaceborne Imagery and Google Earth Engine","authors":"Jiawei Zou, Hao Li, Chao Ding, Suhong Liu, Qingdong Shi","doi":"10.3390/rs16183429","DOIUrl":"https://doi.org/10.3390/rs16183429","url":null,"abstract":"Populus euphratica is a unique constructive tree species within riparian desert areas that is essential for maintaining oasis ecosystem stability. The Tarim River Basin contains the most densely distributed population of P. euphratica forests in the world, and obtaining accurate distribution data in the mainstream of the Tarim River would provide important support for its protection and restoration. We propose a new method for automatically extracting P. euphratica using Sentinel-1 and 2 and Landsat-8 images based on the Google Earth Engine cloud platform and the random forest algorithm. A mask of the potential distribution area of P. euphratica was created based on prior knowledge to save computational resources. The NDVI (Normalized Difference Vegetation Index) time series was then reconstructed using the preferred filtering method to obtain phenological parameter features, and the random forest model was input by combining the phenological parameter, spectral index, textural, and backscattering features. An active learning method was employed to optimize the model and obtain the best model for extracting P. euphratica. Finally, the map of natural P. euphratica forests with a resolution of 10 m in the mainstream of the Tarim River was obtained. The overall accuracy, producer’s accuracy, user’s accuracy, kappa coefficient, and F1-score of the map were 0.96, 0.98, 0.95, 0.93, and 0.96, respectively. The comparison experiments showed that simultaneously adding backscattering and textural features improved the P. euphratica extraction accuracy, while textural features alone resulted in a poor extraction effect. The method developed in this study fully considered the prior and posteriori information and determined the feature set suitable for the P. euphratica identification task, which can be used to quickly obtain accurate large-area distribution data of P. euphratica. The method can also provide a reference for identifying other typical desert vegetation.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"3 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Keyan Wang, Jia Jia, Peicheng Zhou, Haoyi Ma, Liyun Yang, Kai Liu, Yunsong Li
Due to the fact that invalid cloud-covered regions in remote sensing images consume a considerable quantity of coding bit rates under the limited satellite-to-ground transmission rate, existing image compression methods suffer from low compression efficiency and poor reconstruction quality, especially in cloud-free regions which are generally regarded as regions of interest (ROIs). Therefore, we propose an efficient on-board compression method for remote sensing images with arbitrary-shaped clouds by leveraging the characteristics of cloudy images. Firstly, we introduce two novel spatial preprocessing strategies, namely, the optimized adaptive filling (OAF) strategy and the controllable quantization (CQ) strategy. Specifically, the OAF strategy fills each cloudy region using the contextual information at its inner and outer edge to completely remove the information of cloudy regions and minimize their coding consumption, which is suitable for images with only thick clouds. The CQ strategy implicitly identifies thin and thick clouds and rationally quantifies the data in cloudy regions to alleviate information loss in thin cloud-covered regions, which can achieve the balance between coding efficiency and reconstructed image quality and is more suitable for images containing thin clouds. Secondly, we develop an efficient coding method for a binary cloud mask to effectively save the bit rate of the side information. Our method provides the flexibility for users to choose the desired preprocessing strategy as needed and can be embedded into existing compression framework such as JPEG2000. Experimental results on the GF-1 dataset show that our method effectively reduces the coding consumption of invalid cloud-covered regions and significantly improve the compression efficiency as well as the quality of decoded images.
{"title":"Efficient On-Board Compression for Arbitrary-Shaped Cloud-Covered Remote Sensing Images via Adaptive Filling and Controllable Quantization","authors":"Keyan Wang, Jia Jia, Peicheng Zhou, Haoyi Ma, Liyun Yang, Kai Liu, Yunsong Li","doi":"10.3390/rs16183431","DOIUrl":"https://doi.org/10.3390/rs16183431","url":null,"abstract":"Due to the fact that invalid cloud-covered regions in remote sensing images consume a considerable quantity of coding bit rates under the limited satellite-to-ground transmission rate, existing image compression methods suffer from low compression efficiency and poor reconstruction quality, especially in cloud-free regions which are generally regarded as regions of interest (ROIs). Therefore, we propose an efficient on-board compression method for remote sensing images with arbitrary-shaped clouds by leveraging the characteristics of cloudy images. Firstly, we introduce two novel spatial preprocessing strategies, namely, the optimized adaptive filling (OAF) strategy and the controllable quantization (CQ) strategy. Specifically, the OAF strategy fills each cloudy region using the contextual information at its inner and outer edge to completely remove the information of cloudy regions and minimize their coding consumption, which is suitable for images with only thick clouds. The CQ strategy implicitly identifies thin and thick clouds and rationally quantifies the data in cloudy regions to alleviate information loss in thin cloud-covered regions, which can achieve the balance between coding efficiency and reconstructed image quality and is more suitable for images containing thin clouds. Secondly, we develop an efficient coding method for a binary cloud mask to effectively save the bit rate of the side information. Our method provides the flexibility for users to choose the desired preprocessing strategy as needed and can be embedded into existing compression framework such as JPEG2000. Experimental results on the GF-1 dataset show that our method effectively reduces the coding consumption of invalid cloud-covered regions and significantly improve the compression efficiency as well as the quality of decoded images.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"33 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We use data from the Gravity Recovery and Climate Experiment and its Follow-On mission (GRACE/GRACE-FO) from April 2002 to December 2022 to analyze interannual glacial mass changes in High Mountain Asia (HMA) and its subregions and their driving factors. Glacial mass changes in the HMA subregions show clear regional characteristics. Interannual glacial mass changes in the HMA region are closely related to interannual oscillations of precipitation and temperature, and are also correlated with El Niño–Southern Oscillation (ENSO). Glacial mass changes in the regions (R1–R6) are dominated by precipitation, and ENSO affects interannual glacial mass changes mainly by affecting precipitation. In region (R7) and region (R8), the glacial mass changes are mainly controlled by temperature. ENSO also affects the interannual glacial mass changes by affecting interannual changes in temperature. The interannual glacial mass changes in regions (R9–R11) are jointly dominated by temperature and precipitation, and also related to ENSO. Another interesting finding of this study is that glacial mass changes in the western part of HMA (R1–R6) show a clear 6–7-year oscillation, strongly correlated with a similar oscillation in precipitation, while in the eastern part (R9–R11), a 2–3-year oscillation was found in both glacial mass change and precipitation, as well as temperature. These results verify the response of interannual HMA glacial mass changes to climate processes, crucial for understanding regional climate dynamics and sustainable water resource management.
{"title":"Interannual Glacial Mass Changes in High Mountain Asia and Connections to Climate Variability","authors":"Yifan Wang, Jingang Zhan, Hongling Shi, Jianli Chen","doi":"10.3390/rs16183426","DOIUrl":"https://doi.org/10.3390/rs16183426","url":null,"abstract":"We use data from the Gravity Recovery and Climate Experiment and its Follow-On mission (GRACE/GRACE-FO) from April 2002 to December 2022 to analyze interannual glacial mass changes in High Mountain Asia (HMA) and its subregions and their driving factors. Glacial mass changes in the HMA subregions show clear regional characteristics. Interannual glacial mass changes in the HMA region are closely related to interannual oscillations of precipitation and temperature, and are also correlated with El Niño–Southern Oscillation (ENSO). Glacial mass changes in the regions (R1–R6) are dominated by precipitation, and ENSO affects interannual glacial mass changes mainly by affecting precipitation. In region (R7) and region (R8), the glacial mass changes are mainly controlled by temperature. ENSO also affects the interannual glacial mass changes by affecting interannual changes in temperature. The interannual glacial mass changes in regions (R9–R11) are jointly dominated by temperature and precipitation, and also related to ENSO. Another interesting finding of this study is that glacial mass changes in the western part of HMA (R1–R6) show a clear 6–7-year oscillation, strongly correlated with a similar oscillation in precipitation, while in the eastern part (R9–R11), a 2–3-year oscillation was found in both glacial mass change and precipitation, as well as temperature. These results verify the response of interannual HMA glacial mass changes to climate processes, crucial for understanding regional climate dynamics and sustainable water resource management.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"30 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Snow cover distribution is of great significance for climate change and water resource management. Current deep learning-based methods for extracting snow cover from remote sensing images face challenges such as insufficient local detail awareness and inadequate utilization of global semantic information. In this study, a snow cover extraction algorithm integrating cross-scale edge perception and an attention mechanism on the U-net model architecture is proposed. The cross-scale edge perception module replaces the original jump connection of U-net, enhances the low-level image features by introducing edge detection on the shallow feature scale, and enhances the detail perception via branch separation and fusion features on the deep feature scale. Meanwhile, parallel channel and spatial attention mechanisms are introduced in the model encoding stage to adaptively enhance the model’s attention to key features and improve the efficiency of utilizing global semantic information. The method was evaluated on the publicly available CSWV_S6 optical remote sensing dataset, and the accuracy of 98.14% indicates that the method has significant advantages over existing methods. Snow extraction from Landsat 8 OLI images of the upper reaches of the Irtysh River was achieved with satisfactory accuracy rates of 95.57% (using two, three, and four bands) and 96.65% (using two, three, four, and six bands), indicating its strong potential for automated snow cover extraction over larger areas.
{"title":"Snow Cover Extraction from Landsat 8 OLI Based on Deep Learning with Cross-Scale Edge-Aware and Attention Mechanism","authors":"Zehao Yu, Hanying Gong, Shiqiang Zhang, Wei Wang","doi":"10.3390/rs16183430","DOIUrl":"https://doi.org/10.3390/rs16183430","url":null,"abstract":"Snow cover distribution is of great significance for climate change and water resource management. Current deep learning-based methods for extracting snow cover from remote sensing images face challenges such as insufficient local detail awareness and inadequate utilization of global semantic information. In this study, a snow cover extraction algorithm integrating cross-scale edge perception and an attention mechanism on the U-net model architecture is proposed. The cross-scale edge perception module replaces the original jump connection of U-net, enhances the low-level image features by introducing edge detection on the shallow feature scale, and enhances the detail perception via branch separation and fusion features on the deep feature scale. Meanwhile, parallel channel and spatial attention mechanisms are introduced in the model encoding stage to adaptively enhance the model’s attention to key features and improve the efficiency of utilizing global semantic information. The method was evaluated on the publicly available CSWV_S6 optical remote sensing dataset, and the accuracy of 98.14% indicates that the method has significant advantages over existing methods. Snow extraction from Landsat 8 OLI images of the upper reaches of the Irtysh River was achieved with satisfactory accuracy rates of 95.57% (using two, three, and four bands) and 96.65% (using two, three, four, and six bands), indicating its strong potential for automated snow cover extraction over larger areas.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"37 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yao Jiang, Rui Zhang, Bo Sun, Tianyu Wang, Bo Zhang, Jinsheng Tu, Shihai Nie, Hang Jiang, Kangyi Chen
The accuracy and reliability of soil moisture retrieval based on Global Positioning System (GPS) single-star Signal-to-Noise Ratio (SNR) data is low due to the influence of spatial and temporal differences of different satellites. Therefore, this paper proposes a Random Forest (RF)-based multi-satellite data fusion Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) soil moisture retrieval method, which utilizes the RF Model’s Mean Decrease Impurity (MDI) algorithm to adaptively assign arc weights to fuse all available satellite data to obtain accurate retrieval results. Subsequently, the effectiveness of the proposed method was validated using GPS data from the Plate Boundary Observatory (PBO) network sites P041 and P037, as well as data collected in Lamasquere, France. A Support Vector Machine model (SVM), Radial Basis Function (RBF) neural network model, and Convolutional Neural Network model (CNN) are introduced for the comparison of accuracy. The results indicated that the proposed method had the best retrieval performance, with Root Mean Square Error (RMSE) values of 0.032, 0.028, and 0.003 cm3/cm3, Mean Absolute Error (MAE) values of 0.025, 0.022, and 0.002 cm3/cm3, and correlation coefficients (R) of 0.94, 0.95, and 0.98, respectively, at the three sites. Therefore, the proposed soil moisture retrieval model demonstrates strong robustness and generalization capabilities, providing a reference for achieving high-precision, real-time monitoring of soil moisture.
{"title":"GNSS-IR Soil Moisture Retrieval Using Multi-Satellite Data Fusion Based on Random Forest","authors":"Yao Jiang, Rui Zhang, Bo Sun, Tianyu Wang, Bo Zhang, Jinsheng Tu, Shihai Nie, Hang Jiang, Kangyi Chen","doi":"10.3390/rs16183428","DOIUrl":"https://doi.org/10.3390/rs16183428","url":null,"abstract":"The accuracy and reliability of soil moisture retrieval based on Global Positioning System (GPS) single-star Signal-to-Noise Ratio (SNR) data is low due to the influence of spatial and temporal differences of different satellites. Therefore, this paper proposes a Random Forest (RF)-based multi-satellite data fusion Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) soil moisture retrieval method, which utilizes the RF Model’s Mean Decrease Impurity (MDI) algorithm to adaptively assign arc weights to fuse all available satellite data to obtain accurate retrieval results. Subsequently, the effectiveness of the proposed method was validated using GPS data from the Plate Boundary Observatory (PBO) network sites P041 and P037, as well as data collected in Lamasquere, France. A Support Vector Machine model (SVM), Radial Basis Function (RBF) neural network model, and Convolutional Neural Network model (CNN) are introduced for the comparison of accuracy. The results indicated that the proposed method had the best retrieval performance, with Root Mean Square Error (RMSE) values of 0.032, 0.028, and 0.003 cm3/cm3, Mean Absolute Error (MAE) values of 0.025, 0.022, and 0.002 cm3/cm3, and correlation coefficients (R) of 0.94, 0.95, and 0.98, respectively, at the three sites. Therefore, the proposed soil moisture retrieval model demonstrates strong robustness and generalization capabilities, providing a reference for achieving high-precision, real-time monitoring of soil moisture.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"18 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific evaluation of cultivated land quality (CLQ) is necessary for promoting rational utilization of cultivated land and achieving one of the Sustainable Development Goals (SDGs): Zero Hunger. However, the CLQ evaluation system proposed in previous studies was diversified, and the methods were inefficient. In this study, based on China’s first national standard “Cultivated Land Quality Grade” (GB/T 33469-2016), we constructed a unified county-level CLQ evaluation system by selecting 15 indicators from five aspects—site condition, environmental condition, physicochemical property, nutrient status and field management—and used the Delphi method to calculate the membership degree of the indicators. Taking Jimo district of Shandong Province, China, as a case study, we compared the performance of three machine learning models, including random forest, AdaBoost, and support vector regression, to evaluate CLQ using multi-temporal remote sensing data. The comprehensive index method was used to reveal the spatial distribution of CLQ. The results showed that the CLQ evaluation based on multi-temporal remote sensing data and machine learning model was efficient and reliable, and the evaluation results had a significant positive correlation with crop yield (r was 0.44, p < 0.001). The proportions of cultivated land of high-, medium- and poor-quality were 27.43%, 59.37% and 13.20%, respectively. The CLQ in the western part of the study area was better, while it was worse in the eastern and central parts. The main limiting factors include irrigation capacity and texture configuration. Accordingly, a series of targeted measures and policies were suggested, such as strengthening the construction of farmland water conservancy facilities, deep tillage of soil and continuing to construct well-facilitated farmland. This study proposed a fast and reliable method for evaluating CLQ, and the results are helpful to promote the protection of cultivated land and ensure food security.
{"title":"County-Level Cultivated Land Quality Evaluation Using Multi-Temporal Remote Sensing and Machine Learning Models: From the Perspective of National Standard","authors":"Dingding Duan, Xinru Li, Yanghua Liu, Qingyan Meng, Chengming Li, Guotian Lin, Linlin Guo, Peng Guo, Tingting Tang, Huan Su, Weifeng Ma, Shikang Ming, Yadong Yang","doi":"10.3390/rs16183427","DOIUrl":"https://doi.org/10.3390/rs16183427","url":null,"abstract":"Scientific evaluation of cultivated land quality (CLQ) is necessary for promoting rational utilization of cultivated land and achieving one of the Sustainable Development Goals (SDGs): Zero Hunger. However, the CLQ evaluation system proposed in previous studies was diversified, and the methods were inefficient. In this study, based on China’s first national standard “Cultivated Land Quality Grade” (GB/T 33469-2016), we constructed a unified county-level CLQ evaluation system by selecting 15 indicators from five aspects—site condition, environmental condition, physicochemical property, nutrient status and field management—and used the Delphi method to calculate the membership degree of the indicators. Taking Jimo district of Shandong Province, China, as a case study, we compared the performance of three machine learning models, including random forest, AdaBoost, and support vector regression, to evaluate CLQ using multi-temporal remote sensing data. The comprehensive index method was used to reveal the spatial distribution of CLQ. The results showed that the CLQ evaluation based on multi-temporal remote sensing data and machine learning model was efficient and reliable, and the evaluation results had a significant positive correlation with crop yield (r was 0.44, p < 0.001). The proportions of cultivated land of high-, medium- and poor-quality were 27.43%, 59.37% and 13.20%, respectively. The CLQ in the western part of the study area was better, while it was worse in the eastern and central parts. The main limiting factors include irrigation capacity and texture configuration. Accordingly, a series of targeted measures and policies were suggested, such as strengthening the construction of farmland water conservancy facilities, deep tillage of soil and continuing to construct well-facilitated farmland. This study proposed a fast and reliable method for evaluating CLQ, and the results are helpful to promote the protection of cultivated land and ensure food security.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"15 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jing Wang, Dongmei Jia, Jiaxing Xue, Zhongwu Wu, Wanying Song
Water extraction from synthetic aperture radar (SAR) images has an important application value in wetland monitoring, flood monitoring, etc. However, it still faces the problems of low generalization, weak extraction ability of detailed information, and weak suppression of background noises. Therefore, a new framework, Multi-scale Attention Detailed Feature fusion Network (MADF-Net), is proposed in this paper. It comprises an encoder and a decoder. In the encoder, ResNet101 is used as a solid backbone network to capture four feature levels at different depths, and then the proposed Deep Pyramid Pool (DAPP) module is used to perform multi-scale pooling operations, which ensure that key water features can be captured even in complex backgrounds. In the decoder, a Channel Spatial Attention Module (CSAM) is proposed, which focuses on feature areas that are critical for the identification of water edges by fusing attention weights in channel and spatial dimensions. Finally, the high-level semantic information is effectively fused with the low-level edge features to achieve the final water detection results. In the experiment, Sentinel-1 SAR images of three scenes with different characteristics and scales of water body are used. The PA and IoU of water extraction by MADF-Net can reach 92.77% and 89.03%, respectively, which obviously outperform several other networks. MADF-Net carries out water extraction with high precision from SAR images with different backgrounds, which could also be used for the segmentation and classification of other tasks from SAR images.
从合成孔径雷达（SAR）图像中提取水信息在湿地监测、洪水监测等方面具有重要的应用价值。然而，它仍然面临着泛化程度低、细节信息提取能力弱、背景噪声抑制能力弱等问题。因此，本文提出了一种新的框架--多尺度注意力细节特征融合网络（MADF-Net）。它由编码器和解码器组成。在编码器中，使用 ResNet101 作为坚实的骨干网络，捕捉不同深度的四个特征层，然后使用提出的深金字塔池（DAPP）模块执行多尺度池化操作，确保即使在复杂背景下也能捕捉到关键的水体特征。在解码器中，提出了通道空间关注模块（CSAM），通过融合通道和空间维度的关注权重，重点关注对识别水边至关重要的特征区域。最后，将高层语义信息与低层边缘特征有效融合，以实现最终的水域检测结果。实验中使用了三幅具有不同水体特征和尺度的 Sentinel-1 SAR 图像。MADF-Net 对水体提取的 PA 和 IoU 分别达到 92.77% 和 89.03%，明显优于其他几个网络。MADF-Net 可以从不同背景的合成孔径雷达图像中高精度地提取水体，也可用于合成孔径雷达图像中其他任务的分割和分类。
{"title":"Automatic Water Body Extraction from SAR Images Based on MADF-Net","authors":"Jing Wang, Dongmei Jia, Jiaxing Xue, Zhongwu Wu, Wanying Song","doi":"10.3390/rs16183419","DOIUrl":"https://doi.org/10.3390/rs16183419","url":null,"abstract":"Water extraction from synthetic aperture radar (SAR) images has an important application value in wetland monitoring, flood monitoring, etc. However, it still faces the problems of low generalization, weak extraction ability of detailed information, and weak suppression of background noises. Therefore, a new framework, Multi-scale Attention Detailed Feature fusion Network (MADF-Net), is proposed in this paper. It comprises an encoder and a decoder. In the encoder, ResNet101 is used as a solid backbone network to capture four feature levels at different depths, and then the proposed Deep Pyramid Pool (DAPP) module is used to perform multi-scale pooling operations, which ensure that key water features can be captured even in complex backgrounds. In the decoder, a Channel Spatial Attention Module (CSAM) is proposed, which focuses on feature areas that are critical for the identification of water edges by fusing attention weights in channel and spatial dimensions. Finally, the high-level semantic information is effectively fused with the low-level edge features to achieve the final water detection results. In the experiment, Sentinel-1 SAR images of three scenes with different characteristics and scales of water body are used. The PA and IoU of water extraction by MADF-Net can reach 92.77% and 89.03%, respectively, which obviously outperform several other networks. MADF-Net carries out water extraction with high precision from SAR images with different backgrounds, which could also be used for the segmentation and classification of other tasks from SAR images.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"163 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Claudia Zito, Massimo Mangifesta, Mirko Francioni, Luigi Guerriero, Diego Di Martire, Domenico Calcaterra, Nicola Sciarra
Cascading landslides are specific multi-hazard events in which a primary movement triggers successive landslide processes. Areas with dynamic and quickly changing environments are more prone to this type of phenomena. Both the kind and the evolution velocity of a landslide depends on the materials involved. Indeed, rockfalls are generated when rocks fall from a very steep slope, while debris flow and/or mudslides are generated by fine materials like silt and clay after strong water imbibition. These events can amplify the damage caused by the initial trigger and propagate instability along a slope, often resulting in significant environmental and societal impacts. The Morino-Rendinara cascading landslide, situated in the Ernici Mountains along the border of the Abruzzo and Lazio regions (Italy), serves as a notable example of the complexities and devastating consequences associated with such events. In March 2021, a substantial debris flow event obstructed the Liri River, marking the latest step in a series of landslide events. Conventional techniques such as geomorphological observations and geological surveys may not provide exhaustive information to explain the landslide phenomena in progress. For this reason, UAV image acquisition, InSAR interferometry, and pixel offset analysis can be used to improve the knowledge of the mechanism and kinematics of landslide events. In this work, the interferometric data ranged from 3 January 2020 to 24 March 2023, while the pixel offset data covered the period from 2016 to 2022. The choice of such an extensive data window provided comprehensive insight into the investigated events, including the possibility of identifying other unrecorded events and aiding in the development of more effective mitigation strategies. Furthermore, to supplement the analysis, a specific finite element method for slope stability analysis was used to reconstruct the deep geometry of the system, emphasizing the effect of groundwater-level flow on slope stability. All of the findings indicate that major landslide activities were concentrated during the heavy rainfall season, with movements ranging from several centimeters per year. These results were consistent with numerical analyses, which showed that the potential slip surface became significantly more unstable when the water table was elevated.
{"title":"Cascading Landslide: Kinematic and Finite Element Method Analysis through Remote Sensing Techniques","authors":"Claudia Zito, Massimo Mangifesta, Mirko Francioni, Luigi Guerriero, Diego Di Martire, Domenico Calcaterra, Nicola Sciarra","doi":"10.3390/rs16183423","DOIUrl":"https://doi.org/10.3390/rs16183423","url":null,"abstract":"Cascading landslides are specific multi-hazard events in which a primary movement triggers successive landslide processes. Areas with dynamic and quickly changing environments are more prone to this type of phenomena. Both the kind and the evolution velocity of a landslide depends on the materials involved. Indeed, rockfalls are generated when rocks fall from a very steep slope, while debris flow and/or mudslides are generated by fine materials like silt and clay after strong water imbibition. These events can amplify the damage caused by the initial trigger and propagate instability along a slope, often resulting in significant environmental and societal impacts. The Morino-Rendinara cascading landslide, situated in the Ernici Mountains along the border of the Abruzzo and Lazio regions (Italy), serves as a notable example of the complexities and devastating consequences associated with such events. In March 2021, a substantial debris flow event obstructed the Liri River, marking the latest step in a series of landslide events. Conventional techniques such as geomorphological observations and geological surveys may not provide exhaustive information to explain the landslide phenomena in progress. For this reason, UAV image acquisition, InSAR interferometry, and pixel offset analysis can be used to improve the knowledge of the mechanism and kinematics of landslide events. In this work, the interferometric data ranged from 3 January 2020 to 24 March 2023, while the pixel offset data covered the period from 2016 to 2022. The choice of such an extensive data window provided comprehensive insight into the investigated events, including the possibility of identifying other unrecorded events and aiding in the development of more effective mitigation strategies. Furthermore, to supplement the analysis, a specific finite element method for slope stability analysis was used to reconstruct the deep geometry of the system, emphasizing the effect of groundwater-level flow on slope stability. All of the findings indicate that major landslide activities were concentrated during the heavy rainfall season, with movements ranging from several centimeters per year. These results were consistent with numerical analyses, which showed that the potential slip surface became significantly more unstable when the water table was elevated.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"26 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Susanne I. Schmidt, Tanja Schröder, Rebecca D. Kutzner, Pia Laue, Hendrik Bernert, Kerstin Stelzer, Kurt Friese, Karsten Rinke
Remote sensing for water quality evaluation has advanced, with more satellites providing longer data series. Validations of remote sensing-derived data for water quality characteristics, such as chlorophyll-a, Secchi depth, and turbidity, have often remained restricted to small numbers of water bodies and have included local calibration. Here, we present an evaluation of > 100 water bodies in Germany covering different sizes, maximum depths, and trophic states. Data from Sentinel-2 MSI and Sentinel-3 OLCI were analyzed by two processing chains. Our work focuses on analysis of the accuracy of remote sensing products by comparing them to a large in situ data set from governmental monitoring from 13 federal states in Germany and, hence, achieves a national scale assessment. We quantified the fit between the remote sensing data and in situ data among processing chains, satellite instruments, and our three target water quality variables. In general, overall regressions between in situ data and remote sensing data followed the 1:1 regression. Remote sensing may, thus, be regarded as a valuable tool for complementing in situ monitoring by useful information on higher spatial and temporal scales in order to support water management, e.g., for the European Water Framework Directive (WFD) and the Bathing Water Directive (BWD).
{"title":"Evaluating Satellite-Based Water Quality Sensing of Inland Waters on Basis of 100+ German Water Bodies Using 2 Different Processing Chains","authors":"Susanne I. Schmidt, Tanja Schröder, Rebecca D. Kutzner, Pia Laue, Hendrik Bernert, Kerstin Stelzer, Kurt Friese, Karsten Rinke","doi":"10.3390/rs16183416","DOIUrl":"https://doi.org/10.3390/rs16183416","url":null,"abstract":"Remote sensing for water quality evaluation has advanced, with more satellites providing longer data series. Validations of remote sensing-derived data for water quality characteristics, such as chlorophyll-a, Secchi depth, and turbidity, have often remained restricted to small numbers of water bodies and have included local calibration. Here, we present an evaluation of > 100 water bodies in Germany covering different sizes, maximum depths, and trophic states. Data from Sentinel-2 MSI and Sentinel-3 OLCI were analyzed by two processing chains. Our work focuses on analysis of the accuracy of remote sensing products by comparing them to a large in situ data set from governmental monitoring from 13 federal states in Germany and, hence, achieves a national scale assessment. We quantified the fit between the remote sensing data and in situ data among processing chains, satellite instruments, and our three target water quality variables. In general, overall regressions between in situ data and remote sensing data followed the 1:1 regression. Remote sensing may, thus, be regarded as a valuable tool for complementing in situ monitoring by useful information on higher spatial and temporal scales in order to support water management, e.g., for the European Water Framework Directive (WFD) and the Bathing Water Directive (BWD).","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"6 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142251010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Monitoring soil salinity with remote sensing is difficult, but knowing the link between saline soil surface spectra, soil water, and salt transport processes might help in modeling for soil salinity monitoring. In this study, we used an indoor soil column experiment, an unmanned aerial vehicle multispectral sensor camera, and a soil moisture sensor to study the water and salt transport process in the soil column under different water addition conditions and investigate the relationship between the soil water and salt transport process and the spectral reflectance of the image on the soil surface. The observation results of the soil column show that the soil water and salt transportation process conforms to the basic transportation law of “salt moves together with water, and when water evaporates, salt is retained in the soil weight”. The salt accumulation phenomenon increases the image spectral reflectance of the surface layer of the soil column, while soil temperature has no effect on the reflectance. As the water percolates down, water and salt accumulate at the bottom of the soil column. The salinity index decreases instantly after the addition of brine and then tends to increase slowly. The experimental results indicate that this work can capture the relationship between the water and salt transport process and remote sensing spectra, which can provide theoretical basis and reference for soil water salinity monitoring.
{"title":"The Link between Surface Visible Light Spectral Features and Water–Salt Transfer in Saline Soils—Investigation Based on Soil Column Laboratory Experiments","authors":"Shaofeng Qin, Yong Zhang, Jianli Ding, Jinjie Wang, Lijing Han, Shuang Zhao, Chuanmei Zhu","doi":"10.3390/rs16183421","DOIUrl":"https://doi.org/10.3390/rs16183421","url":null,"abstract":"Monitoring soil salinity with remote sensing is difficult, but knowing the link between saline soil surface spectra, soil water, and salt transport processes might help in modeling for soil salinity monitoring. In this study, we used an indoor soil column experiment, an unmanned aerial vehicle multispectral sensor camera, and a soil moisture sensor to study the water and salt transport process in the soil column under different water addition conditions and investigate the relationship between the soil water and salt transport process and the spectral reflectance of the image on the soil surface. The observation results of the soil column show that the soil water and salt transportation process conforms to the basic transportation law of “salt moves together with water, and when water evaporates, salt is retained in the soil weight”. The salt accumulation phenomenon increases the image spectral reflectance of the surface layer of the soil column, while soil temperature has no effect on the reflectance. As the water percolates down, water and salt accumulate at the bottom of the soil column. The salinity index decreases instantly after the addition of brine and then tends to increase slowly. The experimental results indicate that this work can capture the relationship between the water and salt transport process and remote sensing spectra, which can provide theoretical basis and reference for soil water salinity monitoring.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":"13 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142251014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：