Deep Learning and Remote‐Sensed Observations Reveal Global Underestimation of River Obstructions
Abstract River obstructions are a subject of global concern due to their impact on river connectivity and aquatic ecosystems. However, detecting and quantifying these structures, especially small and undocumented ones, remains a major challenge due to limitations in existing data sets and detection methods. This study focuses on improving the global detection of river obstructions and revealing their spatial distribution patterns. We developed a deep‐learning‐based detection framework combined with manual validation, resulting in the Deep Learning‐Global River Obstructions Database, which comprises 50,061 river obstructions identified globally. This represents a 64% increase over previous estimates, which were based solely on manual identification. Spatial analyses reveal strong correlations between obstruction density and factors such as Gross Domestic Product, agricultural expansion, urbanization, and river morphology. By enhancing the precision and comprehensiveness of river obstruction data, our open‐source data set provides a solid foundation for accurate assessment of global river connectivity, basin‐to‐continental‐scale hydrological modeling, and impact assessments.
Authors
- Han Qiu (ORCID: https://orcid.org/0000-0001-9962-2472)
- W. J. Riley (ORCID: https://orcid.org/0000-0002-4615-2304)
- Liwei Sun (ORCID: https://orcid.org/0000-0002-7047-1866)
- Dongwei GUI (ORCID: https://orcid.org/0000-0002-2247-4325)
- Yi Zheng (ORCID: https://orcid.org/0000-0001-8442-182X)
- Chaopeng Shen (ORCID: https://orcid.org/0000-0002-0685-1901)
- John M. Mélack (ORCID: https://orcid.org/0000-0003-0619-841X)
- Bill X. Hu (ORCID: https://orcid.org/0000-0003-4490-5250)
- Dongdong Liu (ORCID: https://orcid.org/0000-0001-8834-9167)
- Mingyi He (ORCID: https://orcid.org/0000-0003-2051-6955)
- Mengyu Xie (ORCID: https://orcid.org/0009-0009-3653-6636)
- Qixin Wu
- Shaoqi Zhou (ORCID: https://orcid.org/0000-0001-9838-3983)
- Yong Fu
- Pan Wu
- Jie Niu
Institutions
- Pennsylvania State University (US)
- Lawrence Berkeley National Laboratory (US)
- University of California, Santa Barbara (US)
- Jinan University (CN)
- The University of Texas at Dallas (US)
- Southern University of Science and Technology (CN)
- China University of Geosciences (Beijing) (CN)
- University of Jinan (CN)
- Ministry of Education (RO)
- Institute of Ecology and Geography (MD)
- Xinjiang Institute of Ecology and Geography (CN)
- Guangdong Ocean University (CN)
Publication Details
- Journal
- Water Resources Research
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1029/2024wr039692
- Primary Topic
- Flood Risk Assessment and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China