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: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13020175 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/2/175/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/2/175/ 2023-08-20T04:07:51+02:00 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 agris 2021-01-06 application/pdf https://doi.org/10.3390/rs13020175 EN eng Multidisciplinary Digital Publishing Institute Biogeosciences Remote Sensing https://dx.doi.org/10.3390/rs13020175 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 2; Pages: 175 data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN Text 2021 ftmdpi https://doi.org/10.3390/rs13020175 2023-08-01T00:48:57Z 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. Text lena river Subarctic Thermokarst Siberia MDPI Open Access Publishing Remote Sensing 13 2 175 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN |
spellingShingle |
data fusion subarctic thermokarst lakes AMSR2 MODIS random forest conditional GAN 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 |
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 |
Text |
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 |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13020175 |
op_coverage |
agris |
genre |
lena river Subarctic Thermokarst Siberia |
genre_facet |
lena river Subarctic Thermokarst Siberia |
op_source |
Remote Sensing; Volume 13; Issue 2; Pages: 175 |
op_relation |
Biogeosciences Remote Sensing https://dx.doi.org/10.3390/rs13020175 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13020175 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
2 |
container_start_page |
175 |
_version_ |
1774719778160640000 |