GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping

Remote sensing is a powerful tool that provides flexibility and scalability for monitoring and investigating glacial lakes in High Mountain Asia (HMA). However, existing methods for mapping glacial lakes are designed based on a combination of several spectral features and ancillary data (such as the...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hang Zhao, Meimei Zhang, Fang Chen
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/5f3d2c8a47ec425d932c6643a15b1936
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5f3d2c8a47ec425d932c6643a15b1936
record_format dspace
spelling oai:doaj.org-article:5f3d2c8a47ec425d932c6643a15b19362021-11-25T18:55:48ZGAN-GL: Generative Adversarial Networks for Glacial Lake Mapping10.3390/rs132247282072-4292https://doaj.org/article/5f3d2c8a47ec425d932c6643a15b19362021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4728https://doaj.org/toc/2072-4292Remote sensing is a powerful tool that provides flexibility and scalability for monitoring and investigating glacial lakes in High Mountain Asia (HMA). However, existing methods for mapping glacial lakes are designed based on a combination of several spectral features and ancillary data (such as the digital elevation model, DEM) to highlight the lake extent and suppress background information. These methods, however, suffer from either the inevitable requirement of post-processing work or the high costs of additional data acquisition. Signifying a key advancement in the deep learning models, a generative adversarial network (GAN) can capture multi-level features and learn the mapping rules in source and target domains using a minimax game between a generator and discriminator. This provides a new and feasible way to conduct large-scale glacial lake mapping. In this work, a complete glacial lake dataset was first created, containing approximately 4600 patches of Landsat-8 OLI images edited in three ways—random cropping, density cropping, and uniform cropping. Then, a GAN model for glacial lake mapping (GAN-GL) was constructed. The GAN-GL consists of two parts—a generator that incorporates a water attention module and an image segmentation module to produce the glacial lake masks, and a discriminator which employs the ResNet-152 backbone to ascertain whether a given pixel belonged to a glacial lake. The model was evaluated using the created glacial lake dataset, delivering a good performance, with an F1 score of 92.17% and IoU of 86.34%. Moreover, compared to the mapping results derived from the global–local iterative segmentation algorithm and random forest for the entire Eastern Himalayas, our proposed model was superior regarding the segmentation of glacial lakes under complex and diverse environmental conditions, in terms of accuracy (precision = 93.19%) and segmentation efficiency. Our model was also very good at detecting small glacial lakes without assistance from ancillary data or human intervention.Hang ZhaoMeimei ZhangFang ChenMDPI AGarticlegenerative adversarial networksattention mechanismglacial lake mappingLandsat-8 OLIScienceQENRemote Sensing, Vol 13, Iss 4728, p 4728 (2021)
institution DOAJ
collection DOAJ
language EN
topic generative adversarial networks
attention mechanism
glacial lake mapping
Landsat-8 OLI
Science
Q
spellingShingle generative adversarial networks
attention mechanism
glacial lake mapping
Landsat-8 OLI
Science
Q
Hang Zhao
Meimei Zhang
Fang Chen
GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
description Remote sensing is a powerful tool that provides flexibility and scalability for monitoring and investigating glacial lakes in High Mountain Asia (HMA). However, existing methods for mapping glacial lakes are designed based on a combination of several spectral features and ancillary data (such as the digital elevation model, DEM) to highlight the lake extent and suppress background information. These methods, however, suffer from either the inevitable requirement of post-processing work or the high costs of additional data acquisition. Signifying a key advancement in the deep learning models, a generative adversarial network (GAN) can capture multi-level features and learn the mapping rules in source and target domains using a minimax game between a generator and discriminator. This provides a new and feasible way to conduct large-scale glacial lake mapping. In this work, a complete glacial lake dataset was first created, containing approximately 4600 patches of Landsat-8 OLI images edited in three ways—random cropping, density cropping, and uniform cropping. Then, a GAN model for glacial lake mapping (GAN-GL) was constructed. The GAN-GL consists of two parts—a generator that incorporates a water attention module and an image segmentation module to produce the glacial lake masks, and a discriminator which employs the ResNet-152 backbone to ascertain whether a given pixel belonged to a glacial lake. The model was evaluated using the created glacial lake dataset, delivering a good performance, with an F1 score of 92.17% and IoU of 86.34%. Moreover, compared to the mapping results derived from the global–local iterative segmentation algorithm and random forest for the entire Eastern Himalayas, our proposed model was superior regarding the segmentation of glacial lakes under complex and diverse environmental conditions, in terms of accuracy (precision = 93.19%) and segmentation efficiency. Our model was also very good at detecting small glacial lakes without assistance from ancillary data or human intervention.
format article
author Hang Zhao
Meimei Zhang
Fang Chen
author_facet Hang Zhao
Meimei Zhang
Fang Chen
author_sort Hang Zhao
title GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
title_short GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
title_full GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
title_fullStr GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
title_full_unstemmed GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping
title_sort gan-gl: generative adversarial networks for glacial lake mapping
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/5f3d2c8a47ec425d932c6643a15b1936
work_keys_str_mv AT hangzhao ganglgenerativeadversarialnetworksforglaciallakemapping
AT meimeizhang ganglgenerativeadversarialnetworksforglaciallakemapping
AT fangchen ganglgenerativeadversarialnetworksforglaciallakemapping
_version_ 1718410526066737152