What question did this study set out to answer?

This research aims to improve the assessment of terrestrial water storage anomalies using machine learning on GRACE data.

May 24, 2026Open Access

Machine Learning Approaches for Terrestrial Water Storage Assessment in Coastal Lowland Aquifer System Using GRACE/GRACE-FO Satellite Data (2003–2023)

Key Points

This research aims to improve the assessment of terrestrial water storage anomalies using machine learning on GRACE data.
Utilized GRACE and GRACE-FO satellite data from 2003 to 2023 for analysis.
Applied machine learning models including Random Forest, ANN, and DNN for downscaling data to 800-m resolution.
Generated monthly terrestrial water storage anomaly maps and performed trend analysis using linear regression.
The western Coastal Lowland Aquifer System shows significant water storage depletion at rates of -0.30 cm/year in Zone 1.
The ANN model demonstrated strong predictive performance with R2 values between 0.869 to 0.989 and low root mean square error (RMSE).
The eastern CLAS displayed stable conditions with negligible increases in water storage, indicating variability rather than a sustained gain.

Abstract

The Gravity Recovery and Climate Experiment (GRACE) mascon data relies on minor gravitational field variations to map terrestrial water storage anomaly (TWSA). However, the coarse spatial resolution of three degrees by three degrees restricts their application for evaluating small-scale changes in water storage. To address this challenge, in this study, GRACE and GRACE Follow-On (GRACE-FO) data from 2003 to 2023 were downscaled to 800-m resolution across the Coastal Lowland Aquifer System (CLAS) in Texas, Louisiana, Mississippi, Alabama, and Florida. This downscaling used machine learning (ML) models, including Random Forest (RF), Artificial Neural Network (ANN), and Deep Neural Network (DNN). These models incorporated variables such as anomalies in total precipitation (APT), mean temperature (ATM), normalized difference vegetation index (ANDVI), evapotranspiration (AET) from 2003 to 2023, Shuttle Radar Topography Mission DEM, slope angle, soil type, and lithology to generate monthly 800-m TWSA maps. The ANN model showed strong predictive performance (R2 = 0.869–0.989 with low RMSE), although the DNN achieved slightly better statistical accuracy and spatial evaluation metrics; however, ANN was selected for its more realistic and spatially consistent outputs regionally. Building on this improved spatial resolution, analysis of the downscaled TWSA data from 2003 to 2023 identified an overall declining trend in water storage. Trend analysis using linear regression shows that the western CLAS—particularly the Gulf Coast aquifer in Texas and western Louisiana—experiences the strongest depletion, with rates of −0.30 and −0.17 cm/year in Zones 1 and 2, respectively, with Zone 1 being statistically significant. In contrast, the eastern CLAS shows relatively stable conditions, with weak, non-significant increases (+0.05 to +0.18 cm/year), likely reflecting natural variability rather than sustained long-term gain. Therefore, ML-based downscaling of GRACE data enables high-resolution TWS assessment and provides a framework for future extraction of groundwater storage anomalies (GWSA), supporting improved groundwater management.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Jahan et al. (Fri,) studied this question.

synapsesocial.com/papers/6a12960648a0ea1665672731 https://doi.org/https://doi.org/10.3390/rs18111680

Bookmark

View Full Paper