EventsThe 10th International Electronic Conference on Water Sciences
Published
This submission belongs to the session S7. Remote Sensing, Artificial Intelligence, and New Technologies in Water Sciences of the event The 10th International Electronic Conference on Water Sciences
Published date
19 Nov, 2026
Academic Editor
author-avatarNikiforos Samarinas
Citation
Anastasia I. Triantafyllou, Alexandros C. Karachles, Eleni A. Tzanou, George S. Vergos, Comparison of Hydroclimatic Predictor Sets for Machine-Learning Reconstruction of GRACE Terrestrial Water Storage in the Amazon, in Proceedings of The 10th International Electronic Conference on Water Sciences, 24 November–27 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

Comparison of Hydroclimatic Predictor Sets for Machine-Learning Reconstruction of GRACE Terrestrial Water Storage in the Amazon

Alexandros C. Karachles 1
image
1. Laboratory of Gravity Field Research and Applications - GravLab, Department of Geodesy and Surveying, Aristotle University of Thessaloniki, Thessaloniki, GR-54124, Greece
2. Department of Surveying and Geoinformatics Engineering, School of Engineering, International Hellenic University, Serres, Greece
Abstract

GRACE and GRACE-FO observations provide essential information on terrestrial water storage anomalies, but their coarse spatial resolution limits their direct use for subbasin-scale hydrological analysis. Machine-learning reconstruction offers a practical way to express the GRACE-derived storage signal in a spatial framework compatible with higher-resolution hydroclimatic datasets. However, reconstruction performance may depend strongly on the choice of predictor dataset. This study compares two GRACE reconstruction configurations in the Amazon using an identical XGBoost model structure but different hydroclimatic input sources.

The target variable is CSR GRACE Mascon liquid water equivalent thickness. Two predictor configurations are evaluated. The first combines CHIRPS precipitation with GLEAM variables representing soil moisture, evaporation, evapotranspiration components, and evaporative stress. The second uses CHIRPS precipitation and ERA5/Copernicus hydroclimatic variables, including soil moisture and evapotranspiration. Both configurations are harmonized to a common spatial and temporal grid, trained using the same model architecture, and evaluated over the same two Amazon subbasins. To reduce autocorrelation-driven performance, selected semesters are withheld from training, and model transferability is assessed through application beyond the training subbasin.

The comparison focuses on whether differences in predictor source lead to systematic differences in reconstructed terrestrial water storage patterns. Evaluation is performed using spatial maps and summary statistics, including absolute differences, RMSE, MAE, coefficient of determination, as well as Nash–Sutcliffe efficiency, and correlation with independent global total water storage anomaly data from the GRACE-SeDA (Self-supervised Data Assimilation) dataset. Feature-importance analysis is also used to examine whether the two configurations rely on similar hydrological controls or whether model behaviour changes depending on the predictor dataset.

Keywords
GRACE/GRACE-FO
XGBoost
downscaling
Storage-State Trajectory of the Amazon Basin from GRACE and Downscaled TWSA
Improving dimensionless centrifugal pump characteristic curve prediction through the incorporation of specific speed using Machine Learning