Mon Aug 24, F. Flechtner
• Sorted by Date • Sorted by Last Name of First Author •
Zheng, Xiaoling, Yu, Yilei, Jiang, Jiyi, Yang, Lihu, and Wang, Shiqin, 2026. Lagged Response of Groundwater Storage to Extreme Precipitation Using Machine–Learning–Downscaled GRACE Data at the Watershed Scale. Remote Sensing, 18(13):2217, doi:10.3390/rs18132217.
• from the NASA Astrophysics Data System • by the DOI System •
@ARTICLE{2026RemS...18.2217Z,
author = {{Zheng}, Xiaoling and {Yu}, Yilei and {Jiang}, Jiyi and {Yang}, Lihu and {Wang}, Shiqin},
title = "{Lagged Response of Groundwater Storage to Extreme Precipitation Using Machine-Learning-Downscaled GRACE Data at the Watershed Scale}",
journal = {Remote Sensing},
keywords = {GRACE, extreme precipitation events, lagged response, Baiyangdian Watershed},
year = 2026,
month = jul,
volume = {18},
number = {13},
eid = {2217},
pages = {2217},
abstract = "{What are the main findings? A LightGBM-based framework successfully
downscaled GRACE-derived groundwater storage anomalies to 1 km
resolution with high accuracy, enabling watershed-scale analysis
in the Baiyangdian Watershed. Groundwater storage showed a long-
term transition from rapid depletion to recovery after 2020,
while composite analysis of 11 EPEs showed that the groundwater
storage response was delayed: {\ensuremath{\Delta}}GWSA was weak
during the event month, became evident one month after the
event, and reached its maximum approximately two months after
the event. A LightGBM-based framework successfully downscaled
GRACE-derived groundwater storage anomalies to 1 km resolution
with high accuracy, enabling watershed-scale analysis in the
Baiyangdian Watershed. Groundwater storage showed a long-term
transition from rapid depletion to recovery after 2020, while
composite analysis of 11 EPEs showed that the groundwater
storage response was delayed: {\ensuremath{\Delta}}GWSA was weak
during the event month, became evident one month after the
event, and reached its maximum approximately two months after
the event. What are the implications of the main findings?
Machine-learning-downscaled GRACE data can provide an effective
tool for monitoring basin-scale groundwater dynamics where field
observations are sparse. Extreme precipitation alone is
insufficient to reverse groundwater depletion; sustained
recovery depends on cumulative climatic inputs, antecedent
groundwater conditions, and human water-management
interventions. Machine-learning-downscaled GRACE data can
provide an effective tool for monitoring basin-scale groundwater
dynamics where field observations are sparse. Extreme
precipitation alone is insufficient to reverse groundwater
depletion; sustained recovery depends on cumulative climatic
inputs, antecedent groundwater conditions, and human water-
management interventions. Understanding how groundwater storage
responds to extreme precipitation is essential for assessing
aquifer resilience under climate variability. In this study, we
developed a 1 km groundwater storage anomaly (GWSA) dataset for
the Baiyangdian Watershed from 2002 to 2024 by downscaling GRACE
observations with a Light Gradient Boosting Machine (LightGBM)
model. The downscaled GWSA showed good consistency with
independent hydrological datasets, including GLDAS and
groundwater-level anomalies. Based on the downscaled product, we
characterized long-term groundwater changes and quantified GWSA
responses to extreme precipitation events (EPEs). Groundwater
storage exhibited three distinct phases: rapid depletion before
2014 ({\ensuremath{-}}1.35 cm/yr), a slower decline during
2014--2019 ({\ensuremath{-}}1.04 cm/yr), and marked recovery
after 2020 (+3.45 cm/yr). Spatially, GWSA generally increased
from the southwest to the northeast of the watershed. Composite
analysis of 11 EPEs revealed a delayed groundwater response,
with the strongest signal occurring approximately two months
after precipitation. Monthly effective precipitation was more
closely associated with GWSA recovery than short-duration daily
precipitation extremes, and the response was stronger in plains
than in mountainous areas. These findings indicate that EPEs
provide episodic recharge pulses, while sustained groundwater
recovery depends on cumulative climatic inputs and human water-
management influences.}",
doi = {10.3390/rs18132217},
adsurl = {https://ui.adsabs.harvard.edu/abs/2026RemS...18.2217Z},
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
Mon Aug 24, 2026 17:14:24
GRACE-FO
Mon Aug 24, F. Flechtner