Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks
Surface water monitoring with fine spatiotemporal resolution in the subarctic is important for understanding the impact of climate change upon hydrological cycles in the region. This study provides dynamic water mapping with daily frequency and a moderate (500 m) resolution over a heterogeneous ther...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13020175 https://doaj.org/article/b2a4029910564fb59f6b0c0cf62524bb |
id |
ftdoajarticles:oai:doaj.org/article:b2a4029910564fb59f6b0c0cf62524bb |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:b2a4029910564fb59f6b0c0cf62524bb 2024-01-07T09:44:42+01:00 Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks Hiroki Mizuochi Yoshihiro Iijima Hirohiko Nagano Ayumi Kotani Tetsuya Hiyama 2021-01-01T00:00:00Z https://doi.org/10.3390/rs13020175 https://doaj.org/article/b2a4029910564fb59f6b0c0cf62524bb EN eng MDPI AG https://www.mdpi.com/2072-4292/13/2/175 https://doaj.org/toc/2072-4292 doi:10.3390/rs13020175 2072-4292 https://doaj.org/article/b2a4029910564fb59f6b0c0cf62524bb Remote Sensing, Vol 13, Iss 2, p 175 (2021) data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN Science Q article 2021 ftdoajarticles https://doi.org/10.3390/rs13020175 2023-12-10T01:48:24Z Surface water monitoring with fine spatiotemporal resolution in the subarctic is important for understanding the impact of climate change upon hydrological cycles in the region. This study provides dynamic water mapping with daily frequency and a moderate (500 m) resolution over a heterogeneous thermokarst landscape in eastern Siberia. A combination of random forest and conditional generative adversarial networks (pix2pix) machine learning (ML) methods were applied to data fusion between the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Advanced Microwave Scanning Radiometer 2, with the addition of ancillary hydrometeorological information. The results show that our algorithm successfully filled in observational gaps in the MODIS data caused by cloud interference, thereby improving MODIS data availability from 30.3% to almost 100%. The water fraction estimated by our algorithm was consistent with that derived from the reference MODIS data (relative mean bias: −2.43%; relative root mean squared error: 14.7%), and effectively rendered the seasonality and heterogeneous distribution of the Lena River and the thermokarst lakes. Practical knowledge of the application of ML to surface water monitoring also resulted from the preliminary experiments involving the random forest method, including timing of the water-index thresholding and selection of the input features for ML training. Article in Journal/Newspaper lena river Subarctic Thermokarst Siberia Directory of Open Access Journals: DOAJ Articles Remote Sensing 13 2 175 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN Science Q |
spellingShingle |
data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN Science Q Hiroki Mizuochi Yoshihiro Iijima Hirohiko Nagano Ayumi Kotani Tetsuya Hiyama Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
topic_facet |
data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN Science Q |
description |
Surface water monitoring with fine spatiotemporal resolution in the subarctic is important for understanding the impact of climate change upon hydrological cycles in the region. This study provides dynamic water mapping with daily frequency and a moderate (500 m) resolution over a heterogeneous thermokarst landscape in eastern Siberia. A combination of random forest and conditional generative adversarial networks (pix2pix) machine learning (ML) methods were applied to data fusion between the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Advanced Microwave Scanning Radiometer 2, with the addition of ancillary hydrometeorological information. The results show that our algorithm successfully filled in observational gaps in the MODIS data caused by cloud interference, thereby improving MODIS data availability from 30.3% to almost 100%. The water fraction estimated by our algorithm was consistent with that derived from the reference MODIS data (relative mean bias: −2.43%; relative root mean squared error: 14.7%), and effectively rendered the seasonality and heterogeneous distribution of the Lena River and the thermokarst lakes. Practical knowledge of the application of ML to surface water monitoring also resulted from the preliminary experiments involving the random forest method, including timing of the water-index thresholding and selection of the input features for ML training. |
format |
Article in Journal/Newspaper |
author |
Hiroki Mizuochi Yoshihiro Iijima Hirohiko Nagano Ayumi Kotani Tetsuya Hiyama |
author_facet |
Hiroki Mizuochi Yoshihiro Iijima Hirohiko Nagano Ayumi Kotani Tetsuya Hiyama |
author_sort |
Hiroki Mizuochi |
title |
Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
title_short |
Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
title_full |
Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
title_fullStr |
Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
title_full_unstemmed |
Dynamic Mapping of Subarctic Surface Water by Fusion of Microwave and Optical Satellite Data Using Conditional Adversarial Networks |
title_sort |
dynamic mapping of subarctic surface water by fusion of microwave and optical satellite data using conditional adversarial networks |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13020175 https://doaj.org/article/b2a4029910564fb59f6b0c0cf62524bb |
genre |
lena river Subarctic Thermokarst Siberia |
genre_facet |
lena river Subarctic Thermokarst Siberia |
op_source |
Remote Sensing, Vol 13, Iss 2, p 175 (2021) |
op_relation |
https://www.mdpi.com/2072-4292/13/2/175 https://doaj.org/toc/2072-4292 doi:10.3390/rs13020175 2072-4292 https://doaj.org/article/b2a4029910564fb59f6b0c0cf62524bb |
op_doi |
https://doi.org/10.3390/rs13020175 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
2 |
container_start_page |
175 |
_version_ |
1787426124802818048 |