Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model

Abstract Relatively short records of Total Water Storage Anomalies (TWSA) from the Gravity Recovery and Climate Experiment (GRACE) and its Follow‐On (GRACE‐FO) missions have impeded our understanding of their full range and long‐term variability over the Lake Victoria Basin (LVB). This study introdu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jielong Wang, Yunzhong Shen, Joseph Awange, Yongze Song, Ling Yang, Qiujie Chen, Allan Kasedde
Format: Article
Language:English
Published: Wiley 2025-05-01
Series:Geophysical Research Letters
Online Access:https://doi.org/10.1029/2024GL114005
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184508907716608
author Jielong Wang
Yunzhong Shen
Joseph Awange
Yongze Song
Ling Yang
Qiujie Chen
Allan Kasedde
author_facet Jielong Wang
Yunzhong Shen
Joseph Awange
Yongze Song
Ling Yang
Qiujie Chen
Allan Kasedde
author_sort Jielong Wang
collection DOAJ
description Abstract Relatively short records of Total Water Storage Anomalies (TWSA) from the Gravity Recovery and Climate Experiment (GRACE) and its Follow‐On (GRACE‐FO) missions have impeded our understanding of their full range and long‐term variability over the Lake Victoria Basin (LVB). This study introduces an Enhanced RecNet (ERecNet) to reconstruct the LVB's TWSA from 1971 to 2022 using precipitation and Lake Victoria's level data. ERecNet integrates a multi‐layer perceptron and a combination of gridded and basin‐averaged loss functions for improving reconstruction performance. Our results reveal that ERecNet can successfully reconstruct the LVB's TWSA variations, outperforming hydrological models and reanalysis products in capturing the TWSA trends and amplitudes. The reconstruction aligns closely with the lake level and precipitation patterns while effectively closing the LVB's water balance budget. This study provides the first reconstruction of both human‐ and climate‐driven TWSA data over the LVB, offering valuable insights into its long‐term hydrological variability.
format Article
id doaj-art-b4aa1a7ce5df47fd9d66cdfd19684507
institution OA Journals
issn 0094-8276
1944-8007
language English
publishDate 2025-05-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-b4aa1a7ce5df47fd9d66cdfd196845072025-08-20T02:17:01ZengWileyGeophysical Research Letters0094-82761944-80072025-05-01529n/an/a10.1029/2024GL114005Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet ModelJielong Wang0Yunzhong Shen1Joseph Awange2Yongze Song3Ling Yang4Qiujie Chen5Allan Kasedde6College of Surveying and Geo‐informatics Tongji University Shanghai PR ChinaCollege of Surveying and Geo‐informatics Tongji University Shanghai PR ChinaDepartment of Land Surveying and Geo‐Informatics The Hong Kong Polytechnic University Hung Hom Hong KongSchool of Design and the Built Environment Curtin University Perth WA AustraliaCollege of Surveying and Geo‐informatics Tongji University Shanghai PR ChinaCollege of Surveying and Geo‐informatics Tongji University Shanghai PR ChinaStrategy, Research and Business Development Unit, Uganda Electricity Generation Company Limited Kampala UgandaAbstract Relatively short records of Total Water Storage Anomalies (TWSA) from the Gravity Recovery and Climate Experiment (GRACE) and its Follow‐On (GRACE‐FO) missions have impeded our understanding of their full range and long‐term variability over the Lake Victoria Basin (LVB). This study introduces an Enhanced RecNet (ERecNet) to reconstruct the LVB's TWSA from 1971 to 2022 using precipitation and Lake Victoria's level data. ERecNet integrates a multi‐layer perceptron and a combination of gridded and basin‐averaged loss functions for improving reconstruction performance. Our results reveal that ERecNet can successfully reconstruct the LVB's TWSA variations, outperforming hydrological models and reanalysis products in capturing the TWSA trends and amplitudes. The reconstruction aligns closely with the lake level and precipitation patterns while effectively closing the LVB's water balance budget. This study provides the first reconstruction of both human‐ and climate‐driven TWSA data over the LVB, offering valuable insights into its long‐term hydrological variability.https://doi.org/10.1029/2024GL114005
spellingShingle Jielong Wang
Yunzhong Shen
Joseph Awange
Yongze Song
Ling Yang
Qiujie Chen
Allan Kasedde
Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
Geophysical Research Letters
title Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
title_full Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
title_fullStr Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
title_full_unstemmed Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
title_short Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model
title_sort reconstructing total water storage anomalies over the lake victoria basin 1971 2022 using an enhanced recnet model
url https://doi.org/10.1029/2024GL114005
work_keys_str_mv AT jielongwang reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT yunzhongshen reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT josephawange reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT yongzesong reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT lingyang reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT qiujiechen reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel
AT allankasedde reconstructingtotalwaterstorageanomaliesoverthelakevictoriabasin19712022usinganenhancedrecnetmodel