Paper Info
Title
Developing A Long Short-Term Memory (Lstm)-Based Model For Reconstructing Terrestrial Water Storage Variations From 1982 To 2016 In The Tarim River Basin, Northwest China
Abstract
Estimating Terrestrial Water Storage (TWS) not only helps to provide a comprehensive insight into water resource variability and the hydrological cycle but also for better water resource management. In the current research, Gravity Recovery And Climate Experiment (GRACE) data are combined with the available hydrological data to reconstruct a longer record of Terrestrial Water Storage Anomalies (TWSA) prior to 2003 of the Tarim River Basin (TRB), based on a Long Short-Term Memory (LSTM) model. We found that the TWSA generated by LSTM using soil moisture, evapotranspiration, precipitation, and temperature best matches the GRACE-derived TWSA, with a high correlation coefficient (r) of 0.922 and a Normalized Root Mean Square Error (NRMSE) of 0.107 during the period 2003-2012. These results show that the LSTM model is an available and feasible method to generate TWSA. Further, the TWSA reveals a significant fluctuating downward trend (p < 0.001), with an average decline rate of 0.03 mm/month during the period 1982-2016 in the TRB. Moreover, the TWSA amount in the north of the TRB was less than that in the south of the basin. Overall, our findings unveiled that the LSTM model and GRACE data can be combined effectively to analyze the long-term TWSA in large-scale basins with limited hydrological data.
Year
DOI
Venue
2021
10.3390/rs13050889
REMOTE SENSING
Keywords
DocType
Volume
terrestrial water storage, Tarim River Basin, LSTM model, climate change
Journal
13
Issue
Citations 
PageRank 
5
0
0.34
References 
Authors
0
8
Name
Order
Citations
PageRank
Fei Wang100.34
Yaning Chen2511.01
Zhi Li303.38
Gonghuan Fang401.01
Yupeng Li502.70
Xuanxuan Wang600.68
Xueqi Zhang700.34
Patient Mindje Kayumba802.37