A Deep Learning Method for Mapping Glacial Lakes from the Combined Use of Synthetic-Aperture Radar and Optical Satellite Images

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.

[1]  Jeffrey S. Kargel,et al.  ASTER measurement of supraglacial lakes in the Mount Everest region of the Himalaya , 2002, Annals of Glaciology.

[2]  W. Zhan,et al.  Landsat 8 OLI image based terrestrial water extraction from heterogeneous backgrounds using a reflectance homogenization approach , 2015 .

[3]  H. Xie,et al.  An inventory of glacial lakes in the Third Pole region and their changes in response to global warming , 2015 .

[4]  Changwei Xie,et al.  Glacier changes during the past century in the Gangrigabu mountains, southeast Qinghai–Xizang (Tibetan) Plateau, China , 2006, Annals of Glaciology.

[5]  Meiping Sun,et al.  Definition and classification system of glacial lake for inventory and hazards study , 2018, Journal of Geographical Sciences.

[6]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[7]  Fang Chen,et al.  Extraction of Glacial Lake Outlines in Tibet Plateau Using Landsat 8 Imagery and Google Earth Engine , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Hanqiu Xu.  Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery , 2006 .

[10]  Anthropogenic climate change and glacier lake outburst flood risk: local and global drivers and responsibilities for the case of lake Palcacocha, Peru , 2020 .

[11]  Pramod K. Varshney,et al.  Mutual information-based image registration for remote sensing data , 2003 .

[12]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[13]  M. Westoby,et al.  Modelling outburst floods from moraine-dammed glacial lakes , 2014 .

[14]  John M. Reynolds,et al.  An overview of glacial hazards in the Himalayas , 2000 .

[15]  L. Shiyin.  Glacier Variations since the Early 20th Century in the Gangrigabu Range, Southeast Tibetan Plateau , 2005 .

[16]  Yan Wei.  Study of the Fluctuations of Glaciers and Lakes around the Ranwu Lake of Southeast Tibetan Plateau using Remote Sensing , 2009 .

[17]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[18]  M. N. Hanshaw,et al.  Glacial areas, lake areas, and snow lines from 1975 to 2012: status of the Cordillera Vilcanota, including the Quelccaya Ice Cap, northern central Andes, Peru , 2013 .

[19]  B. Merminod,et al.  Icy lakes extraction and water-ice classification using Landsat 8 OLI multispectral data , 2018 .

[20]  Yu Zhang,et al.  Seasonal cycles of lakes on the Tibetan Plateau detected by Sentinel-1 SAR data. , 2019, The Science of the total environment.

[21]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[22]  Konrad Schindler,et al.  Lake Ice Detection from Sentinel-1 SAR with Deep Learning , 2020, ArXiv.

[23]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[24]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[25]  Gao Li-jing.  Automatic and high-precise extraction for water information from multispectral images with the step-by-step iterative transformation mechanism , 2009 .

[26]  Zhangbing Zhou,et al.  Lake level dynamics exploration using deep learning, artificial neural network, and multiple linear regression techniques , 2019, Environmental Earth Sciences.

[27]  Mritunjay Kumar Singh,et al.  Applicability of Landsat 8 data for characterizing glacier facies and supraglacial debris , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[28]  Kenneth Hewitt,et al.  Ice-Dammed Lakes and Outburst Floods, Karakoram Himalaya: Historical Perspectives on Emerging Threats , 2010 .

[29]  R. D. Gupta,et al.  A lake detection algorithm (LDA) using Landsat 8 data: A comparative approach in glacial environment , 2015, Int. J. Appl. Earth Obs. Geoinformation.