Chen et al. (2026) An integrated framework for mapping agricultural water impoundments using Sentinel −2 and GEE in Northwest China

Identification

• Journal: Journal of Hydrology
• Year: 2026
• Date: 2026-03-21
• Authors: Haochong Chen, Yuxiang Zhang, Haichao Yu, Sien Li
• DOI: 10.1016/j.jhydrol.2026.135362

Research Groups

• State Key Laboratory of Efficient Utilization of Agricultural Water Resources, Beijing, China
• National Field Scientific Observation and Research Station on Efficient Water Use of Oasis Agriculture in Wuwei of Gansu Province, Wuwei 733009, China
• Center for Agricultural Water Research in China, China Agricultural University, Beijing 100083, China
• College of Land Science and Technology, China Agricultural University, Beijing 100083, China
• School of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin, Heilongjiang 150030, China

Short Summary

This study developed an integrated framework using Sentinel-2 and Google Earth Engine to accurately map and monitor small-scale agricultural water impoundments (AWIs) in arid regions, providing the first high-resolution, multi-year inventory for the Hexi Corridor.

Objective

• To develop and implement an integrated framework for high-resolution, annual monitoring and mapping of agricultural water impoundments (AWIs) in arid regions, overcoming limitations of traditional remote sensing for small-scale features.

Study Configuration

• Spatial Scale: Hexi Corridor, Northwest China.
• Temporal Scale: Annual monitoring from 2018 to 2023.

Methodology and Data

• Models used: A novel mapping framework coupling inter-annual water persistence analysis with vector-derived morphometric features within an ensemble learning architecture.
• Data sources: Sentinel-2 satellite imagery processed on Google Earth Engine (GEE).

Main Results

• The developed framework accurately distinguishes agricultural water impoundments (AWIs) from natural water bodies with an overall accuracy of 0.89.
• A high-resolution (10 meters), multi-year inventory (2018–2023) of AWIs was created for the Hexi Corridor.
• In 2023, 2,037 impoundments were identified, with individual areas ranging from 1,000 to 10,000 square meters.
• In 2022, 26.5% of the identified AWIs were constructed, accounting for 63.5% of all newly-built AWIs that year, indicating a priority for large-scale AWI construction.
• Three distinct types of river-reservoir-AWI distribution patterns were identified in the Hexi Corridor through an upstream–downstream analysis.
• AWIs were found to be closer to rivers than wells, serving as immediate irrigation distribution points for riverine water sources.

Contributions

• Introduction of a novel mapping framework that integrates inter-annual water persistence analysis with vector-derived morphometric features within an ensemble learning architecture for AWIs.
• Overcoming the limitations of conventional remote sensing for monitoring small-scale agricultural water infrastructure.
• Creation of the first high-resolution (10 meters), multi-year (2018–2023) inventory of agricultural water impoundments across the Hexi Corridor.
• Identification, for the first time, of three distinct river-reservoir-AWI distribution patterns in the Hexi Corridor.
• Providing a new perspective for monitoring agricultural water infrastructure in arid regions, offering critical insights into sustainable water resource management.

Funding

• Not explicitly mentioned in the provided text.

Citation

@article{Chen2026integrated,
  author = {Chen, Haochong and Zhang, Yuxiang and Yu, Haichao and Li, Sien},
  title = {An integrated framework for mapping agricultural water impoundments using Sentinel −2 and GEE in Northwest China},
  journal = {Journal of Hydrology},
  year = {2026},
  doi = {10.1016/j.jhydrol.2026.135362},
  url = {https://doi.org/10.1016/j.jhydrol.2026.135362}
}