Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method

Terrestrial water storage represents both surface and subsurface water resources and plays a crucial role in the global hydrological cycle. The Gravity Recovery and Climate Experiment (GRACE) satellite mission provides large-scale and high-stability terrestrial water storage anomaly (TWSA) data for...

Full description

Saved in:
Bibliographic Details
Main Authors: Fengmin Hu, Beibei Yang, Zushuai Wei, Changlu Cui, Lingkui Meng
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2468418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224327392657408
author Fengmin Hu
Beibei Yang
Zushuai Wei
Changlu Cui
Lingkui Meng
author_facet Fengmin Hu
Beibei Yang
Zushuai Wei
Changlu Cui
Lingkui Meng
author_sort Fengmin Hu
collection DOAJ
description Terrestrial water storage represents both surface and subsurface water resources and plays a crucial role in the global hydrological cycle. The Gravity Recovery and Climate Experiment (GRACE) satellite mission provides large-scale and high-stability terrestrial water storage anomaly (TWSA) data for water resource analysis. However, an 11-month data gap exists between the two generations of gravity satellites, GRACE and GRACE Follow-On (July 2017 to May 2018), posing challenges for TWSA analysis and applications. This study proposed a long short-term memory (LSTM) and Bayesian convolutional neural network (BCNN) combined in an LSTM-BCNN reconstruction model. By extracting long-term temporal change features and recent environmental spatial features, the model reconstructs and corrects the trend and random terms of the TWSA decomposition to reconstruct the TWSA data during the gap period. The model was evaluated on a global scale across 40 basins and at a grid scale. At the grid scale, the LSTM-BCNN model achieves a correlation coefficient (CC) of 0.89 ± 0.06, Nash-Sutcliffe efficiency coefficient (NSE) of 0.78 ± 0.12, and normalized root mean square error (NRMSE) of 0.11 ± 0.02. Across the 40 basins, the LSTM-BCNN model effectively reconstructed the TWSA data during the gap period.
format Article
id doaj-art-dba6adf55590460da43ca8f6b2733a2c
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-dba6adf55590460da43ca8f6b2733a2c2025-08-25T11:31:34ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2468418Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction methodFengmin Hu0Beibei Yang1Zushuai Wei2Changlu Cui3Lingkui Meng4College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou, People’s Republic of ChinaChangjiang Spatial Information Technology Engineering Co., Ltd, Wuhan, People’s Republic of ChinaSchool of Artificial Intelligence, Jianghan University, Wuhan, People’s Republic of ChinaChangjiang River Scientific Research Institute, Changjiang River Water Resources Commission, Wuhan, People’s Republic of ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, People’s Republic of ChinaTerrestrial water storage represents both surface and subsurface water resources and plays a crucial role in the global hydrological cycle. The Gravity Recovery and Climate Experiment (GRACE) satellite mission provides large-scale and high-stability terrestrial water storage anomaly (TWSA) data for water resource analysis. However, an 11-month data gap exists between the two generations of gravity satellites, GRACE and GRACE Follow-On (July 2017 to May 2018), posing challenges for TWSA analysis and applications. This study proposed a long short-term memory (LSTM) and Bayesian convolutional neural network (BCNN) combined in an LSTM-BCNN reconstruction model. By extracting long-term temporal change features and recent environmental spatial features, the model reconstructs and corrects the trend and random terms of the TWSA decomposition to reconstruct the TWSA data during the gap period. The model was evaluated on a global scale across 40 basins and at a grid scale. At the grid scale, the LSTM-BCNN model achieves a correlation coefficient (CC) of 0.89 ± 0.06, Nash-Sutcliffe efficiency coefficient (NSE) of 0.78 ± 0.12, and normalized root mean square error (NRMSE) of 0.11 ± 0.02. Across the 40 basins, the LSTM-BCNN model effectively reconstructed the TWSA data during the gap period.https://www.tandfonline.com/doi/10.1080/17538947.2025.2468418GRACEGRACE-FOdata gapLong short-term memory Bayesian convolutional neural network (LSTM-BCNN)
spellingShingle Fengmin Hu
Beibei Yang
Zushuai Wei
Changlu Cui
Lingkui Meng
Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
International Journal of Digital Earth
GRACE
GRACE-FO
data gap
Long short-term memory Bayesian convolutional neural network (LSTM-BCNN)
title Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
title_full Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
title_fullStr Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
title_full_unstemmed Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
title_short Filling the data gap between GRACE and GRACE-FO based on a two-step reconstruction method
title_sort filling the data gap between grace and grace fo based on a two step reconstruction method
topic GRACE
GRACE-FO
data gap
Long short-term memory Bayesian convolutional neural network (LSTM-BCNN)
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2468418
work_keys_str_mv AT fengminhu fillingthedatagapbetweengraceandgracefobasedonatwostepreconstructionmethod
AT beibeiyang fillingthedatagapbetweengraceandgracefobasedonatwostepreconstructionmethod
AT zushuaiwei fillingthedatagapbetweengraceandgracefobasedonatwostepreconstructionmethod
AT changlucui fillingthedatagapbetweengraceandgracefobasedonatwostepreconstructionmethod
AT lingkuimeng fillingthedatagapbetweengraceandgracefobasedonatwostepreconstructionmethod