Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs

Cao, Yijing; Zhang, Yongqiang; Chen, Yuyin; Zhang, Xuanze; Tian, Jing; Yang, Xuening; Huang, Qi; Su, Jianzhong

doi:10.3390/rs18101622

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs

by

Yijing Cao

¹,

Yongqiang Zhang

^1,2,*

,

Yuyin Chen

^1,3

,

Xuanze Zhang

¹,

Jing Tian

¹

,

Xuening Yang

^1,3,

Qi Huang

^1,3 and

Jianzhong Su

²

¹

Key Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China

²

Etuoke Banner Water Conservancy Development Center, Ordos City, 017000, China

³

University of Chinese Academy of Sciences, Beijing, 100101, China

^*

Author to whom correspondence should be addressed.

Remote Sens. 2026, 18(10), 1622; https://doi.org/10.3390/rs18101622

Submission received: 23 March 2026 / Revised: 6 May 2026 / Accepted: 15 May 2026 / Published: 18 May 2026

(This article belongs to the Special Issue Hydrological Modeling in the Age of AI and Remote Sensing)

Download Versions Notes

Abstract

Groundwater storage is vital for managing water resources, especially as global water scarcity intensifies. Estimating groundwater levels regionally is challenging due to natural heterogeneity. We employed a large groundwater observation sample, along with Global Land Data Assimilation System (GLDAS) and Gravity Recovery and Climate Experiments (GRACE) datasets, to develop a random forest model for predicting groundwater levels in China’s Yellow River Basin. The model showed robustness, achieving an R² of 0.95 in calibration and an R² of 0.91 ± 0.009 in 10-fold cross-validation with 100 repetitions. Temporal predictability was lower, with an R² of 0.72 for April–May 2023; however, the temporal prediction is preliminary and limited by the short validation period (April–May 2023), which should be interpreted with caution. Spatial maps revealed significant seasonal declines in fall and winter, particularly in the middle and lower reaches. This study highlights the potential of machine learning with extensive observations to estimate regional groundwater levels and supports groundwater analysis with robust data.

Keywords: random forest model; groundwater level; GLDAS; GRACE

Share and Cite

MDPI and ACS Style

Cao, Y.; Zhang, Y.; Chen, Y.; Zhang, X.; Tian, J.; Yang, X.; Huang, Q.; Su, J. Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs. Remote Sens. 2026, 18, 1622. https://doi.org/10.3390/rs18101622

AMA Style

Cao Y, Zhang Y, Chen Y, Zhang X, Tian J, Yang X, Huang Q, Su J. Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs. Remote Sensing. 2026; 18(10):1622. https://doi.org/10.3390/rs18101622

Chicago/Turabian Style

Cao, Yijing, Yongqiang Zhang, Yuyin Chen, Xuanze Zhang, Jing Tian, Xuening Yang, Qi Huang, and Jianzhong Su. 2026. "Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs" Remote Sensing 18, no. 10: 1622. https://doi.org/10.3390/rs18101622

APA Style

Cao, Y., Zhang, Y., Chen, Y., Zhang, X., Tian, J., Yang, X., Huang, Q., & Su, J. (2026). Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs. Remote Sensing, 18(10), 1622. https://doi.org/10.3390/rs18101622

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI