A Deep Learning Method for Mapping Glacial Lakes from the Combined Use of Synthetic-Aperture Radar and Optical Satellite Images
A Deep Learning Method for Mapping Glacial Lakes from the Combined Use of Synthetic-Aperture Radar and Optical Satellite Images
复制标题
结合使用合成孔径雷达和光学卫星图像来绘制冰川湖地图的深度学习方法
DOI：
10.3390/rs12244020
复制
发表时间：
2020-12
期刊：
影响因子：
5
通讯作者：
Xiang Wei
中科院分区：
文献类型：
--
作者：
Wu Renzhe;Liu Guoxiang;Zhang Rui;Wang Xiaowen;Li Yong;Zhang Bo;Cai Jialun;Xiang Wei
冰湖是连接水圈和冰冻圈的重要纽带，参与局部水文过程，其年际动态演变是区域气候变化的客观反映和指标。GLs所在山区地形和气候条件复杂，常规遥感观测手段难以获得稳定、准确、全面的观测数据。针对这种情况，本研究通过优化和改进一种深度学习（DL）语义分割网络模型，建立了一种高泛化能力的算法，用于从合成孔径雷达（SAR）幅值和多光谱图像数据中提取GL轮廓。目的是利用SAR的高穿透性和全天候优势，减少云层的影响，同时结合多光谱数据的多尺度和面向细节的优势，实现GL等高线的精确、定量提取。这些GLs主要分布在海拔4000 ~ 5500 m。这些GLs中只有17.4%的GLs的面积大于0.1 km2，而大量的小型GLs占大多数。通过分析和验证，发现该方法具有较强的河流和湖泊识别能力，能够有效减少对河流的错误识别和提取。基于光学和SAR图像的DL模型在验证集和预测集上的IoU得分分别提高了0.0212分（0.6207分）和0.038分（0.6397分）。这些验证数据充分证明了模型和算法的有效性。本研究采用的技术手段以及获得的结果和数据可以为相关领域的研究和应用拓展提供参考。
Glacial lakes (GLs), a vital link between the hydrosphere and the cryosphere, participate in the local hydrological process, and their interannual dynamic evolution is an objective reflection and an indicator of regional climate change. The complex terrain and climatic conditions in mountainous areas where GLs are located make it difficult to employ conventional remote sensing observation means to obtain stable, accurate, and comprehensive observation data. In view of this situation, this study presents an algorithm with a high generalization ability established by optimizing and improving a deep learning (DL) semantic segmentation network model for extracting GL contours from combined synthetic-aperture radar (SAR) amplitude and multispectral imagery data. The aim is to use the high penetrability and all-weather advantages of SAR to reduce the effects of cloud cover as well as to integrate the multiscale and detail-oriented advantages of multispectral data to facilitate accurate, quantitative extraction of GL contours. The accuracy and reliability of the model and algorithm were examined by employing them to extract the contours of GLs in a large region of south-eastern Tibet from Landsat 8 optical remote sensing images and Sentinel-1A amplitude images. In this study, the contours of a total 8262 GLs in south-eastern Tibet were extracted. These GLs were distributed predominantly at altitudes of 4000–5500 m. Only 17.4% of these GLs were greater than 0.1 km2 in size, while a large number of small GLs made up the majority. Through analysis and validation, the proposed method was found highly capable of distinguishing rivers and lakes and able to effectively reduce the misidentification and extraction of rivers. With the DL model based on combined optical and SAR images, the intersection-over-union (IoU) score increased by 0.0212 (to 0.6207) on the validation set and by 0.038 (to 0.6397) on the prediction set. These validation data sufficiently demonstrate the efficacy of the model and algorithm. The technical means employed in this study as well as the results and data obtained can provide a reference for research and application expansion in related fields.
登录
查看更多内容
影响因子：
--
作者：
Gao Li-jing
通讯作者：
Gao Li-jing
影响因子：
5.2
作者：
Hanshaw, M. N.;Bookhagen, B.
通讯作者：
Bookhagen, B.
影响因子：
3.4
作者：
Barbieux, Kevin;Charitsi, Antigoni;Merminod, Bertrand
通讯作者：
Merminod, Bertrand
使用反射均质化方法从异质背景中提取基于 Landsat 8 OLI 图像的陆地水
影响因子：
13.5
作者：
Yang Yuhao;Liu Yongxue;Zhou Minxi;Zhang Siyu;Zhan Wenfeng;Sun Chao;Duan Yuewei
通讯作者：
Duan Yuewei
DOI：
--
发表时间：
2005
期刊：
Journal of Glaciology and Geocryology
影响因子：
--
作者：
L. Shiyin
通讯作者：
L. Shiyin