Thu Oct 08, F. Flechtner
• Sorted by Date • Sorted by Last Name of First Author •
Samalavičius, Vytautas, Solovey, Tatiana, Śliwińska–Bronowicz, Justyna, Stradczuk, Anna, and Zaslavsky, Ilya, 2026. Bias–Aware Machine Learning Spatial Downscaling of GRACE Signals: Application to the Bug River Basin. Remote Sensing, 18(17):2909, doi:10.3390/rs18172909.
• from the NASA Astrophysics Data System • by the DOI System •
@ARTICLE{2026RemS...18.2909S,
author = {{Samalavi{\v{c}}ius}, Vytautas and {Solovey}, Tatiana and {{\'S}liwi{\'n}ska-Bronowicz}, Justyna and {Stradczuk}, Anna and {Zaslavsky}, Ilya},
title = "{Bias-Aware Machine Learning Spatial Downscaling of GRACE Signals: Application to the Bug River Basin}",
journal = {Remote Sensing},
keywords = {machine learning, remote sensing, GRACE/GRACE-FO, Bug River Basin, spatial downscaling},
year = 2026,
month = aug,
volume = {18},
number = {17},
eid = {2909},
pages = {2909},
abstract = "{What are the main findings? GRACE TWS can be reliably gap-filled and
downscaled using a bias-aware Random Forest framework. The mass-
conserving correction reduces spatial bias while preserving the
original GRACE water-storage signal. GRACE TWS can be reliably
gap-filled and downscaled using a bias-aware Random Forest
framework. The mass-conserving correction reduces spatial bias
while preserving the original GRACE water-storage signal. What
is the implication of the main finding? The method supports
water-resource assessment in data-scarce and conflict-affected
transboundary basins. The method supports water-resource
assessment in data-scarce and conflict-affected transboundary
basins. GRACE and GRACE-FO satellite gravimetry provide unique
observations of terrestrial water storage (TWS), but their
coarse effective resolution and intermittent temporal gaps limit
water-resource applications at subregional and basin scales.
This study presents a framework to temporally reconstruct and
spatially downscale GRACE TWS anomalies for the transboundary
Bug River Basin (Poland--Ukraine--Belarus), a region where in
situ monitoring is limited and further disrupted by the 2022 war
in Ukraine. First, missing monthly GRACE TWS anomalies (2002--
2024) are imputed using a Random Forest model driven only by
lagged GRACE values (1--3 months) and seasonal timing, thereby
avoiding potential information leakage. Second, the continuous
GRACE signal is downscaled to 0.1{\textdegree} using an
independent set of hydroclimatic predictors with lagged and
rolling features, together with elevation, land type and
lithology. Model performance is evaluated under strict
spatiotemporal holdouts and cross-validation. The key
methodological advance is a bias-aware, block-wise mass-
conserving correction that reconciles downscaled fields with the
original GRACE water mass at coarse resolution. After
downscaling to 0.1{\textdegree}, systematic residual biases
between aggregated high-resolution estimates and GRACE
observations are quantified monthly and redistributed within
spatial blocks using river-runoff-based weights. This procedure
enforces exact mass closure while preserving physically
meaningful sub-grid variability.}",
doi = {10.3390/rs18172909},
adsurl = {https://ui.adsabs.harvard.edu/abs/2026RemS...18.2909S},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
Generated by
bib2html_grace.pl
(written by Patrick Riley
modified for this page by Volker Klemann) on
Thu Oct 08, 2026 16:44:00
GRACE-FO
Thu Oct 08, F. Flechtner