基于深度学习结合多源遥感的南极冰面湖变化监测及其成因研究

南极约98%的面积被冰盖覆盖，使其成为海平面上升的潜在最大贡献因素之一，而冰面湖的扩张又与南极冰盖质量亏损导致的海平面上升密切相关。由于南极少有人类活动，冰面湖的变化主要受气候变化的影响，对其快速变化的深入研究在分析气候变化和南极冰架稳定性方面具有重要意义。然而，受限于高质量遥感影像的数量，以往的研究主要侧重于冰面湖的年际变化，即使在冰面湖快速变化的研究中，其研究区域往往局限于少数冰架。因此，关于整个南极冰面湖高时间分辨率面积变化的认知仍显匮乏。

鉴于此，本文基于2016—2023年的Landsat-8、Landsat-9和Sentinel-2卫星影像数据，从上十万景影像中选取约1.5万景以构建影像数据集，并利用提出的AttDeepUNet深度学习模型，对整个南极冰面湖高时间分辨率面积变化进行监测。同时，结合气候模型和遥相关因子，对其时空分布特征和变化成因进行深入探究。本文主要研究内容如下：

（1）本文设计了一套自动提取南极冰面湖的数据处理流程。通过结合经典深度学习模型UNet和DeepUNet并引入注意力机制，提出改进的深度学习神经网络模型AttDeepUNet。该模型展现出较高的冰面湖提取精度，其准确率和平均交并比指标分别达到0.9996和0.9832。基于该模型，开发了一套从影像下载到后处理的遥感影像数据处理流程。

（2）本文将南极划分为1406个边长100 km格网，并基于其中存在冰面湖的95个格网，提取了2016—2023年的冰面湖面积变化时间序列，其时间和空间分辨率分别为10天和30米。通过分析冰面湖的面积变化时间序列和空间分布，揭示了其时空分布特征。总体来看，冰面湖总面积以- 121.07± 10.98 km2/yr的速度呈减少趋势，但其变化呈现出东南极收缩（最大速度为- 27.23± 2.32 km2/yr，加速度为0.12± 0.09 km2/yr2）与西南极扩张（最大速度为6.81± 4.15 km2/yr，加速度为- 0.23± 0.17 km2/yr2）两种明显不同的特征。

（3）本文通过深入分析气候模型中不同气候变量（如融雪、降雨、气温、再冻结、降雪以及地表物质平衡）对冰面湖面积变化特征的影响，进而阐明了冰面湖面积变化的成因。研究发现，融雪和降雨在冰面湖的形成和分布特征中占据主导地位（相应最大相关性系数分别为0.94和0.90），且各气候变量对冰面湖面积的影响存在不同的滞后度（滞后时间范围为0-2个月）。进一步的遥相关分析表明，冰面湖面积与Niño3.4等遥相关因子的变化趋势大体保持一致。

综上所述，本文设计了一套数据处理流程，旨在提取整个南极冰面湖高时间分辨率的面积变化，在此基础上探究南极冰面湖面积变化的时空分布特征及其成因。论文的分析结果不但为理解南极冰面湖面积变化的复杂机制提供新视角，也为深入理解南极对全球气候变化的影响以及其在海平面上升中的贡献提供了坚实的数据支撑。

[1] ARTHUR J F, STOKES C R, JAMIESON S S, et al. Large interannual variability in supraglacial lakes around East Antarctica [J]. Nat Commun, 2022, 13(1): 1711.
[2] CHEN J L, WILSON C, BLANKENSHIP D, et al. Accelerated Antarctic ice loss from satellite gravity measurements [J]. Nat Geosci, 2009, 2(12): 859-862.
[3] TEAM T I. Mass balance of the Antarctic Ice Sheet from 1992 to 2017 [J]. Nature, 2018, 558(7709): 219-222.
[4] 郑雷. 南极冰盖和海冰表面融化微波遥感监测及多尺度影响因子研究 [D], 2019.
[5] 丁明虎. 南极冰盖物质平衡最新研究进展 [J]. 地球物理学进展, 2013, 28(1): 24-35.
[6] ROTT H, ABDEL JABER W, WUITE J, et al. Changing pattern of ice flow and mass balance for glaciers discharging into the Larsen A and B embayments, Antarctic Peninsula, 2011 to 2016 [J]. The Cryosphere, 2018, 12(4): 1273-1291.
[7] VELICOGNA I, MOHAJERANI Y, LANDERER F, et al. Continuity of ice sheet mass loss in Greenland and Antarctica from the GRACE and GRACE Follow‐On missions [J]. Geophys Res Lett, 2020, 47(8): e2020GL087291.
[8] VELICOGNA I, WAHR J. Measurements of time-variable gravity show mass loss in Antarctica [J]. science, 2006, 311(5768): 1754-1756.
[9] DECONTO R M, POLLARD D. Contribution of Antarctica to past and future sea-level rise [J]. Nature, 2016, 531(7596): 591-597.
[10] TUCKETT P A, ELY J C, SOLE A J, et al. Rapid accelerations of Antarctic Peninsula outlet glaciers driven by surface melt [J]. Nat Commun, 2019, 10(1): 4311.
[11] LENAERTS J T M, LHERMITTE S, DREWS R, et al. Meltwater produced by wind–albedo interaction stored in an East Antarctic ice shelf [J]. Nat Clim Change, 2017, 7(1): 58-62.
[12] BELL R E, BANWELL A F, TRUSEL L D, et al. Antarctic surface hydrology and impacts on ice-sheet mass balance [J]. Nature Climate Change, 2018, 8(12): 1044-1052.
[13] LEESON A, FORSTER E, RICE A, et al. Evolution of supraglacial lakes on the Larsen B ice shelf in the decades before it collapsed [J]. Geophys Res Lett, 2020, 47(4): e2019GL085591.
[14] BANWELL A F, MACAYEAL D R, SERGIENKO O V. Breakup of the Larsen B Ice Shelf triggered by chain reaction drainage of supraglacial lakes [J]. Geophys Res Lett, 2013, 40(22): 5872-5876.
[15] BANWELL A F, WILLIS I C, MACDONALD G J, et al. Direct measurements of ice-shelf flexure caused by surface meltwater ponding and drainage [J]. Nat Commun, 2019, 10(1): 730.
[16] ALLEY K E, SCAMBOS T A, MILLER J Z, et al. Quantifying vulnerability of Antarctic ice shelves to hydrofracture using microwave scattering properties [J]. Remote Sens Environ, 2018, 210: 297-306.
[17] TEDESCO M, LüTHJE M, STEFFEN K, et al. Measurement and modeling of ablation of the bottom of supraglacial lakes in western Greenland [J]. Geophys Res Lett, 2012, 39(2).
[18] LEESON A A, SHEPHERD A, BRIGGS K, et al. Supraglacial lakes on the Greenland ice sheet advance inland under warming climate [J]. Nature Climate Change, 2015, 5(1): 51-55.
[19] DUNMIRE D, LENAERTS J, BANWELL A, et al. Observations of buried lake drainage on the Antarctic Ice Sheet [J]. Geophys Res Lett, 2020, 47(15).
[20] HUMPHREY N F, HARPER J T, PFEFFER W T. Thermal tracking of meltwater retention in Greenland's accumulation area [J]. J Geophys Res: Earth Surf, 2012, 117(F1).
[21] VAN WESSEM J M, VAN DE BERG W J, NOëL B P, et al. Modelling the climate and surface mass balance of polar ice sheets using RACMO2–Part 2: Antarctica (1979–2016) [J]. The Cryosphere, 2018, 12(4): 1479-1498.
[22] CHUDLEY T R, CHRISTOFFERSEN P, DOYLE S H, et al. Supraglacial lake drainage at a fast-flowing Greenlandic outlet glacier [J]. Proceedings of the National Academy of Sciences, 2019, 116(51): 25468-25477.
[23] LEESON A, SHEPHERD A, BRIGGS K, et al. Supraglacial lakes on the Greenland ice sheet advance inland under warming climate [J]. Nat Clim Change, 2015, 5(1): 51-55.
[24] QUAYLE W C, PECK L S, PEAT H, et al. Extreme responses to climate change in Antarctic lakes [J]. Science, 2002, 295(5555): 645-645.
[25] DIRSCHERL M C, DIETZ A J, KUENZER C. Seasonal evolution of Antarctic supraglacial lakes in 2015–2021 and links to environmental controls [J]. The Cryosphere, 2021, 15(11): 5205-5226.
[26] TUCKETT P A, ELY J C, SOLE A J, et al. Automated mapping of the seasonal evolution of surface meltwater and its links to climate on the Amery Ice Shelf, Antarctica [J]. The Cryosphere, 2021, 15(12): 5785-5804.
[27] SMITH L C, SHENG Y, MACDONALD G, et al. Disappearing arctic lakes [J]. Science, 2005, 308(5727): 1429-1429.
[28] WILLIAMSON A G, ARNOLD N S, BANWELL A F, et al. A Fully Automated Supraglacial lake area and volume Tracking (“FAST”) algorithm: Development and application using MODIS imagery of West Greenland [J]. Remote Sens Environ, 2017, 196: 113-133.
[29] TRUSEL L D, FREY K E, DAS S B, et al. Divergent trajectories of Antarctic surface melt under two twenty-first-century climate scenarios [J]. Nat Geosci, 2015, 8(12): 927-932.
[30] GILBERT E, KITTEL C. Surface Melt and Runoff on Antarctic Ice Shelves at 1.5°C, 2°C, and 4°C of Future Warming [J]. Geophys Res Lett, 2021, 48(8).
[31] SHUGAR D H, BURR A, HARITASHYA U K, et al. Rapid worldwide growth of glacial lakes since 1990 [J]. Nat Clim Change, 2020, 10(10): 939-945.
[32] YAO F F, LIVNEH B, RAJAGOPALAN B, et al. Satellites reveal widespread decline in global lake water storage [J]. Science, 2023, 380(6646): 743-749.
[33] PI X H, LUO Q Q, FENG L, et al. Mapping global lake dynamics reveals the emerging roles of small lakes [J]. Nat Commun, 2022, 13(1): 5777.
[34] ZHENG L, LI L J, CHEN Z Q, et al. Multi-sensor imaging of winter buried lakes in the Greenland Ice Sheet [J]. Remote Sens Environ, 2023, 295: 113688.
[35] BASSIS J N. Crevasse analysis reveals vulnerability of ice shelves to global warming [Z]. Nature Publishing Group UK London. 2020
[36] SHENG Y, SONG C, WANG J, et al. Representative lake water extent mapping at continental scales using multi-temporal Landsat-8 imagery [J]. Remote Sens Environ, 2016, 185: 129-141.
[37] YAO F, WANG J, WANG C, et al. Constructing long-term high-frequency time series of global lake and reservoir areas using Landsat imagery [J]. Remote Sens Environ, 2019, 232: 111210.
[38] PEKEL J-F, COTTAM A, GORELICK N, et al. High-resolution mapping of global surface water and its long-term changes [J]. Nature, 2016, 540(7633): 418-422.
[39] 梁相安, 张闻松, 李雅, 等. 南极半岛巴赫冰架冰面融水动态遥感监测 [J]. 极地研究, 2022, 34(02): 149-158.
[40] 李青, 周春霞, 刘芮希, 等. 东南极极记录冰川表面冰面湖变化监测 [J]. 极地研究, 2021, 33(01): 27-36.
[41] 王辉, 卢善龙, 丁俊, 等. 气候变化对南极冰面湖的影响研究—以埃默里和拉森 A 冰架为例 [J]. 极地研究, 2020, 32(3): 322.
[42] MOUSSAVI M, POPE A, HALBERSTADT A R W, et al. Antarctic supraglacial lake detection using Landsat 8 and Sentinel-2 imagery: Towards continental generation of lake volumes [J]. Remote Sens, 2020, 12(1): 134.
[43] WILLIAMSON A G, BANWELL A F, WILLIS I C, et al. Dual-satellite (Sentinel-2 and Landsat 8) remote sensing of supraglacial lakes in Greenland [J]. The Cryosphere, 2018, 12(9): 3045-3065.
[44] DIRSCHERL M, DIETZ A J, KNEISEL C, et al. A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning [J]. Remote Sens, 2021, 13(2): 197.
[45] SCHRöDER L, NECKEL N, ZINDLER R, et al. Perennial supraglacial lakes in northeast Greenland observed by polarimetric SAR [J]. Remote Sens, 2020, 12(17): 2798.
[46] MILES K E, WILLIS I C, BENEDEK C L, et al. Toward monitoring surface and subsurface lakes on the Greenland Ice Sheet using Sentinel-1 SAR and Landsat-8 OLI imagery [J]. Front Earth Sci, 2017, 5.
[47] RAN J J, LIU L, ZHANG G Q, et al. Contrasting lake changes in Tibet revealed by recent multi-modal satellite observations [J]. Sci Total Environ, 2023: 168342.
[48] LILLESAND T, KIEFER R W, CHIPMAN J. Remote sensing and image interpretation [M]. John Wiley & Sons, 2015.
[49] MCFEETERS S K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features [J]. Int J Remote Sens, 1996, 17(7): 1425-1432.
[50] BELGIU M, DRĂGUŢ L. Random forest in remote sensing: A review of applications and future directions [J]. ISPRS J Photogramm Remote Sens, 2016, 114: 24-31.
[51] YANG K, SMITH L C. Supraglacial streams on the Greenland Ice Sheet delineated from combined spectral–shape information in high-resolution satellite imagery [J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(4): 801-805.
[52] HU J J, HUANG H B, CHI Z H, et al. Distribution and evolution of supraglacial lakes in Greenland during the 2016–2018 melt seasons [J] 2022, 14(1)
[53] HEIDLER K, MOU L, BAUMHOER C, et al. HED-UNet: Combined segmentation and edge detection for monitoring the Antarctic coastline [J]. IEEE Trans Geosci Remote Sens, 2021, 60: 1-14.
[54] DONG S, TANG X, GUO J, et al. EisNet: Extracting bedrock and internal layers from radiostratigraphy of ice sheets with machine learning [J]. IEEE Trans Geosci Remote Sens, 2021, 60: 1-12.
[55] 陈星宇. 利用深度学习提取青藏高原湖泊季节性面积变化的理论和方法研究 [D]; 南方科技大学, 2022.
[56] QAYYUM N, GHUFFAR S, AHMAD H M, et al. Glacial lakes mapping using multi-satellite PlanetScope imagery and deep learning [J/OL] 2020, 9(10)
[57] 党宇, 张继贤, 邓喀中, 等. 基于深度学习AlexNet的遥感影像地表覆盖分类评价研究 [J]. 地球信息科学学报, 2017, 19(11): 1530-1537.
[58] 周岩, 董金玮. 陆表水体遥感监测研究进展 [J]. 地球信息科学学报, 2019, 21(11): 1768-1778.
[59] WENG L G, XU Y M, XIA M, et al. Water areas segmentation from remote sensing images using a separable residual SegNet network [J/OL] 2020, 9(4)
[60] 何海清, 杜敬, 陈婷, 等. 结合水体指数与卷积神经网络的遥感水体提取 [J]. 遥感信息, 2017, 32(05): 82-86.
[61] 陈前, 郑利娟, 李小娟, 等. 基于深度学习的高分遥感影像水体提取模型研究 [J]. 地理与地理信息科学, 2019, 35(04): 43-49.
[62] NIU L, TANG X, YANG S, et al. Detection of Antarctic surface meltwater using Sentinel-2 remote sensing images via U-Net with attention blocks: a case study over the Amery Ice Shelf [J]. IEEE Trans Geosci Remote Sens, 2023, 61: 1-13.
[63] KINGSLAKE J, ELY J C, DAS I, et al. Widespread movement of meltwater onto and across Antarctic ice shelves [J]. Nature, 2017, 544(7650): 349-352.
[64] 林祥, 卞林根. 南极长城站和中山站的近期气候变化及其对南极涛动的响应 [J]. 极地研究, 2017, 29(3): 357-367.
[65] 效存德. 南极地区气候系统变化: 过去, 现在和将来 [J]. 气候变化研究进展, 2008, 4(001): 1.
[66] GERRISH L, FRETWELL, P., & COOPER, P. . Medium resolution vector polygons of the Antarctic coastline (7.3) [Data set]. [DS]. 2020,
[67] ZWALLY H J, GIOVINETTO M B, BECKLEY M A, et al. Antarctic and Greenland drainage systems [J]. GSFC Cryospheric Sciences Laboratory, 2012, 265.
[68] GORELICK N, HANCHER M, DIXON M, et al. Google Earth Engine: Planetary-scale geospatial analysis for everyone [J]. Remote Sensing of Environment, 2017, 202: 18-27.
[69] GOWARD S N, WILLIAMS D L, ARVIDSON T, et al. Landsat's enduring legacy: Pioneering global land observations from space [J]. Photogrammetric Engineering & Remote Sensing, 2022, 88(6): 357-358.
[70] WULDER M A, LOVELAND T R, ROY D P, et al. Current status of Landsat program, science, and applications [J]. Remote Sens Environ, 2019, 225: 127-147.
[71] ROY D P, WULDER M A, LOVELAND T R, et al. Landsat-8: Science and product vision for terrestrial global change research [J]. Remote Sens Environ, 2014, 145: 154-172.
[72] MASEK J G, WULDER M A, MARKHAM B, et al. Landsat 9: Empowering open science and applications through continuity [J]. Remote Sens Environ, 2020, 248: 111968.
[73] DRUSCH M, DEL BELLO U, CARLIER S, et al. Sentinel-2: ESA's optical high-resolution mission for GMES operational services [J]. Remote Sens Environ, 2012, 120: 25-36.
[74] VAN WESSEM J, VAN DE BERG W, VAN DEN BROEKE M. Data set: Monthly averaged RACMO2. 3p2 variables (1979–2022); Antarctica, Zenodo [data set] [Z]. 2023
[75] MUñOZ-SABATER J, DUTRA E, AGUSTí-PANAREDA A, et al. ERA5-Land: A state-of-the-art global reanalysis dataset for land applications [J]. Earth Syst Sci Data, 2021, 13(9): 4349-4383.
[76] BARNSTON A G, CHELLIAH M, GOLDENBERG S B. Documentation of a highly ENSO-related SST region in the equatorial Pacific [J]. Atmosphere--Ocean (Canadian Meteorological & Oceanographic Society), 1997, 35(3).
[77] SAJI N, GOSWAMI B N, VINAYACHANDRAN P, et al. A dipole mode in the tropical Indian Ocean [J]. Nature, 1999, 401(6751): 360-363.
[78] CHANG P, JI L, LI H. A decadal climate variation in the tropical Atlantic Ocean from thermodynamic air-sea interactions [J]. Nature, 1997, 385(6616): 516-518.
[79] LIMPASUVAN V, HARTMANN D L. Eddies and the annular modes of climate variability [J]. Geophys Res Lett, 1999, 26(20): 3133-3136.
[80] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks [J]. Advances in neural information processing systems, 2012, 25.
[81] LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.
[82] HAN J, MORAGA C. The influence of the sigmoid function parameters on the speed of backpropagation learning [C]. Proceedings of the International Workshop on Artificial Neural Networks, 1995.
[83] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks [C]. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics,2011.
[84] MAAS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neural network acoustic models [C]. Proceedings of the Proc ICML, F, 2013.
[85] EVES H W. Foundations and fundamental concepts of mathematics [M]. Courier Corporation, 1997.
[86] SHARMA S, SHARMA S, ATHAIYA A. Activation functions in neural networks [J]. Towards Data Sci, 2017, 6(12): 310-316.
[87] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, F, 2015.
[88] JIANG D, LI X W, ZHANG K, et al. Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net [J]. Remote Sens, 2022, 14(19): 4998.
[89] RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation [C]. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, F, 2015.
[90] LI R R, LIU W J, YANG L, et al. DeepUNet: A deep fully convolutional network for pixel-level sea-land segmentation [J]. IEEE J Sel Top Appl Earth Obs Remote Sens, 2018, 11(11): 3954-3962.
[91] REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven Earth system science [J]. Nature, 2019, 566(7743): 195-204.
[92] YU H S, YANG Z G, TAN L, et al. Methods and datasets on semantic segmentation: A review [J]. Neurocomputing, 2018, 304: 82-103.
[93] YUAN Q Q, SHEN H F, LI T W, et al. Deep learning in environmental remote sensing: Achievements and challenges [J]. Remote Sens Environ, 2020, 241: 111716.
[94] ZHOU Z W, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. Unet++: A nested u-net architecture for medical image segmentation [C]. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, F, 2018.
[95] CHEN L-C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation [C]. European Conference on Computer Vision (ECCV), F, 2018.
[96] LIU W, CHEN X Y, RAN J J, et al. LaeNet: A novel lightweight multitask CNN for automatically extracting lake area and shoreline from remote sensing images [J]. Remote Sens, 2021, 13(1): 56.
[97] MOHAJERANI S, SAEEDI P. Cloud-net+: A cloud segmentation cnn for landsat 8 remote sensing imagery optimized with filtered jaccard loss function [J]. arXiv e-prints, 2020.
[98] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation [J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12): 2481-2495.
[99] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J], ArXiv Preprint ArXiv:1409.1556, 2014.
[100] WOO S, PARK J, LEE J-Y, et al. Cbam: Convolutional block attention module [C]. Proceedings of the European Conference on Computer Vision (ECCV), F, 2018.
[101] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [J]. Advances in Neural Information Processing Systems, 2017, 30.
[102] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, F, 2021.
[103] WARMERDAM F. The geospatial data abstraction library [M]. Open source approaches in spatial data handling. Springer. 2008: 87-104.
[104] TOMS S. ArcPy and ArcGIS–Geospatial Analysis with Python [M]. Packt Publishing Ltd, 2015.
[105] WESSEL B, HUBER M, WOHLFART C, et al. TanDEM-X PolarDEM 90 m of Antarctica: Generation and error characterization [J]. The Cryosphere, 2021, 15(11): 5241-5260.
[106] SCHNEIDER T. Analysis of incomplete climate data: Estimation of mean values and covariance matrices and imputation of missing values [J]. J Clim, 2001, 14(5): 853-871.
[107] CLAVERIE M, JU J, MASEK J G, et al. The Harmonized Landsat and Sentinel-2 surface reflectance data set [J]. Remote Sens Environ, 2018, 219: 145-161.
[108] CLAVERIE M, MASEK J G, JU J, et al. Harmonized landsat-8 sentinel-2 (HLS) product user’s guide [J]. National Aeronautics and Space Administration (NASA): Washington, DC, USA, 2017.
[109] YUNUS A P, DOU J, SONG X, et al. Improved bathymetric mapping of coastal and lake environments using Sentinel-2 and Landsat-8 images [J]. Sensors, 2019, 19(12): 2788.
[110] 张国庆, 王蒙蒙, 周陶, 等. 青藏高原湖泊面积, 水位与水量变化遥感监测研究进展 [J]. 遥感学报, 2022.
[111] MOUSSAVI M S, ABDALATI W, POPE A, et al. Derivation and validation of supraglacial lake volumes on the Greenland Ice Sheet from high-resolution satellite imagery [J]. Remote Sens Environ, 2016, 183: 294-303.
[112] POPE A, SCAMBOS T A, MOUSSAVI M, et al. Estimating supraglacial lake depth in West Greenland using Landsat 8 and comparison with other multispectral methods [J]. The Cryosphere, 2016, 10(1): 15-27.
[113] YANG K, SMITH L C. Supraglacial streams on the Greenland Ice Sheet delineated from combined spectral–shape information in high-resolution satellite imagery [J]. IEEE Geosci Remote Sens Lett, 2012, 10(4): 801-805.
[114] OTSU N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[115] GULLI A, PAL S. Deep learning with Keras [M]. Packt Publishing Ltd, 2017.
[116] KINGMA D P, BA J. Adam: A method for stochastic optimization [J], 2014.
[117] METZ C E. Basic principles of ROC analysis [C]. Proceedings of the Semin Nucl Med, F, 1978.
[118] TAHA A A, HANBURY A. Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool [J]. BMC Med Imaging, 2015, 15(1): 1-28.
[119] TANIMOTO T T. Elementary mathematical theory of classification and prediction [J]. 1958.
[120] BESTLEY S, ROPERT-COUDERT Y, BENGTSON NASH S, et al. Marine ecosystem assessment for the Southern Ocean: Birds and marine mammals in a changing climate [J]. Front Ecol Evol, 2020: 338.
[121] LI X C, CAI W J, MEEHL G A, et al. Tropical teleconnection impacts on Antarctic climate changes [J]. Nature Reviews Earth & Environment, 2021, 2(10): 680-698.
[122] CHEN X Y, LI S L, ZHANG C. Distinct impacts of two kinds of El Niño on precipitation over the Antarctic Peninsula and West Antarctica in austral spring [J]. Atmos Oceanic Sci Lett, 2023: 100387.