Ghaneei et al. (2026) An Effective Monitoring of Evolving Groundwater Drought via Multivariate Data Assimilation and Machine Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Water Resources Research
• Year: 2026
• Date: 2026-02-01
• Authors: Parnian Ghaneei, Hamid Moradkhani
• DOI: 10.1029/2025wr041565

Research Groups

Not specified in the abstract.

Short Summary

This study introduces an observation-informed approach to produce daily groundwater drought maps at 1/8° resolution across the contiguous United States, revealing distinct and persistent dry clusters, particularly severe in the Western and Northeastern regions.

Objective

• To develop and apply an observation-informed approach for producing daily groundwater drought maps at 1/8° resolution across the contiguous United States (CONUS).

Study Configuration

• Spatial Scale: Contiguous United States (CONUS) at 1/8° resolution (approximately 14 km x 14 km).
• Temporal Scale: Daily.

Methodology and Data

• Models used: Noah-MP land surface model, Growing Neural Gas (machine learning-based pattern recognition algorithm).
• Data sources: Soil Moisture Active Passive (SMAP) soil moisture data, GRACE-FO terrestrial water storage data.

Main Results

• The approach successfully identified the onset of distinct and persistent dry groundwater drought clusters in recent years across the contiguous United States.
• Severe groundwater drought conditions were specifically identified in large regions of both the Western and Northeastern CONUS.
• Findings highlight the need to reassess groundwater resilience strategies due to intensifying and persistent droughts.

Contributions

• Introduction of an observation-informed approach for high spatial (1/8°) and temporal (daily) resolution groundwater drought monitoring.
• Joint assimilation of SMAP soil moisture and GRACE-FO terrestrial water storage data into Noah-MP, enhancing groundwater-surface water interaction representation.
• Application of the Growing Neural Gas algorithm for identifying emergent, evolving, and region-specific groundwater drought patterns.
• Provides a more accurate representation of groundwater drought dynamics, addressing limitations of existing monitoring methods.

Funding

Not specified in the abstract.

Citation

@article{Ghaneei2026Effective,
  author = {Ghaneei, Parnian and Moradkhani, Hamid},
  title = {An Effective Monitoring of Evolving Groundwater Drought via Multivariate Data Assimilation and Machine Learning},
  journal = {Water Resources Research},
  year = {2026},
  doi = {10.1029/2025wr041565},
  url = {https://doi.org/10.1029/2025wr041565}
}