Publications related to the GRACE Missions (no abstracts)

• Sorted by Date • Sorted by Last Name of First Author •

Integrating Socioeconomic Withdrawals Into a Deep Learning Framework for High–Resolution Groundwater Storage Prediction in the Yellow River Basin

Guo, Shuitao, Yao, Yingying, Wu, Zhenjiang, Jia, Gaihong, Liang, Wei, Lancia, Michele, and Zheng, Chunmiao, 2026. Integrating Socioeconomic Withdrawals Into a Deep Learning Framework for High–Resolution Groundwater Storage Prediction in the Yellow River Basin. Water Resources Research, 62(7):e2025WR043071, doi:10.1029/2025WR043071.

Downloads

• from the NASA Astrophysics Data System  • by the DOI System  •

@ARTICLE{2026WRR....6243071G,
       author = {{Guo}, Shuitao and {Yao}, Yingying and {Wu}, Zhenjiang and {Jia}, Gaihong and {Liang}, Wei and {Lancia}, Michele and {Zheng}, Chunmiao},
        title = "{Integrating Socioeconomic Withdrawals Into a Deep Learning Framework for High-Resolution Groundwater Storage Prediction in the Yellow River Basin}",
      journal = {Water Resources Research},
     keywords = {Yellow River Basin, groundwater depletion, deep learning, GRACE downscaling, drought},
         year = 2026,
        month = jul,
       volume = {62},
       number = {7},
          eid = {e2025WR043071},
        pages = {e2025WR043071},
     abstract = "{Groundwater storage anomaly (GWSA) change provides a vital indicator for
        assessing groundwater depletion and drought, supporting informed
        decisions for sustainable water resources management. However,
        coarse spatial resolution of GRACE data limits detection of
        local changes, and downscaling often introduces bias by omitting
        groundwater withdrawals. This study develops a deep learning
        framework that incorporates socioeconomic groundwater extraction
        into the groundwater balance to constrain predictions of 1 km
        resolution GWSA in the Yellow River Basin (YRB), a global
        representative region under combined stress from climate
        variability and intensive groundwater use. Results show that the
        groundwater balance constrained Convolutional Neural Network
        (CNN) achieves higher accuracy, while the Residual Neural
        Network (ResNet) better captures spatial variability. Validation
        against 101 long-term wells (>10 years) confirms 81.2\% exhibit
        correlation coefficients greater than 0.7 with model outputs.
        Incorporating socioeconomic data into balance constraints
        significantly improved predictive performance, reducing errors
        by 28\% (CNN) and 68\% (ResNet). Groundwater depletion is
        present across 42.1\% of the basin, and within these areas,
        92.3\% experience high to severe compound stress under drought
        conditions. These depletion--drought hotspots are predominantly
        concentrated within 30 km of the main river corridor. While GWSA
        changes in 60.1\% of the basin area are strongly influenced by
        climate variability and 10.2\% by human activities, areas under
        stronger human influence experience faster depletion
        ({\ensuremath{-}}11.6 {\ensuremath{\pm}} 0.4 mm/yr) than areas
        where climate factors dominate ({\ensuremath{-}}3.0
        {\ensuremath{\pm}} 0.3 mm/yr). Our study enables high-resolution
        mapping of groundwater depletion and provides insights for
        sustainable groundwater management in large dryland basins.}",
          doi = {10.1029/2025WR043071},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2026WRR....6243071G},
      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

---

Mon Aug 24, F. Flechtner