气候变化领域集成服务门户(CCPortal): An automated, generalized, deep-learning-based method for delineating the calving fronts of Greenland glaciers from multi-sensor remote sensing imagery

CCPortal

DOI	10.1016/j.rse.2020.112265
	An automated, generalized, deep-learning-based method for delineating the calving fronts of Greenland glaciers from multi-sensor remote sensing imagery
	Zhang E.; Liu L.; Huang L.; Ng K.S.
发表日期	2021
ISSN	00344257
卷号	254
英文摘要	In the past two decades, the data volume of remote sensing imagery in the polar regions has increased dramatically. The calving fronts of many Greenland glaciers have been undergoing substantial variations, and a comprehensive front dataset is necessary for better understanding such frontal dynamics. Therefore, there is a need for an automated approach to identifying glaciological features such as calving fronts. In 2019, three deep-learning-based methods were applied to calving front delineation, but were restricted to a specific area or dataset. Here, we develop a more generalized method that can be applied to a major outlet glacier or remote sensing datasets that are not included in the training. We integrate seven remote sensing datasets into a single deep learning network. The core datasets include optical (Landsat-8 and Sentinel-2) and synthetic aperture radar images (Envisat, ALOS-1 TerraSAR-X, Sentinel-1, and ALOS-2) taken over Jakobshavn Isbræ, Kangerlussuaq, and Helheim, spanning from 2002 to 2019. We evaluate four neural network architectures (e.g., U-Net, DeepLabv3+ with ResNet, DRN, and MobileNet as the backbones) and three histogram modification strategies (e.g., histogram normalization, linear stretching, and no histogram modification). We find that the combination of histogram normalization and DRN-DeepLabv3+ has the lowest test error, at 86 m. These promising results show that our method has a high generalization ability on various glaciers and data types. © 2020 Elsevier Inc.
语种	英语
scopus关键词	Graphic methods; Learning systems; Network architecture; Remote sensing; Synthetic aperture radar; Automated approach; Generalization ability; Generalized method; Histogram modification; Learning network; Learning-based methods; Remote sensing imagery; Substantial variations; Deep learning; automation; data set; glacier dynamics; histogram; ice sheet; image analysis; radar imagery; satellite altimetry; synthetic aperture radar; Arctic; Greenland; Kangerlussuaq Fjord
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/178986
作者单位	Earth System Science Programme, Faculty of Science, The Chinese University of Hong Kong, Hong Kong
推荐引用方式 GB/T 7714	Zhang E.,Liu L.,Huang L.,et al. An automated, generalized, deep-learning-based method for delineating the calving fronts of Greenland glaciers from multi-sensor remote sensing imagery[J],2021,254.
APA	Zhang E.,Liu L.,Huang L.,&Ng K.S..(2021).An automated, generalized, deep-learning-based method for delineating the calving fronts of Greenland glaciers from multi-sensor remote sensing imagery.Remote Sensing of Environment,254.
MLA	Zhang E.,et al."An automated, generalized, deep-learning-based method for delineating the calving fronts of Greenland glaciers from multi-sensor remote sensing imagery".Remote Sensing of Environment 254(2021).