Treffer: Deep Learning and Remote‐Sensed Observations Reveal Global Underestimation of River Obstructions.

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. Plain Language Summary: River obstructions, such as dams and locks, support agriculture, energy production, and water management, but they also disrupt natural river connectivity and aquatic ecosystems. Existing methods of identifying river obstructions, particularly small ones, have been limited in scope and accuracy. This study used advanced deep learning technology, combined with manual verification, to create a comprehensive global database of river obstructions and to uncover their spatial distribution patterns. Our Deep Learning‐Global River Obstructions Database (DL‐GROD) identified 50,061 obstructions worldwide, a 64% increase compared to previous manual estimates. This new data set reveals strong links between obstruction density and economic and river characteristics, highlighting the value of AI‐based methods in environmental monitoring. By offering precise and accessible data, DL‐GROD enables better assessments of river connectivity and supports hydrological modeling, fisheries management, and sustainable development planning at local, regional, and global scales. Key Points: A deep learning‐based detection model, combined with remote sensing, enables rapid and precise detection of river obstructions on a global scaleOver 50,000 river obstructions are identified on rivers wider than 30 m globally, a 64% increase over previous estimatesExplanatory machine learning on new obstruction data revealed a complex interplay of multiple factors in shaping obstruction density [ABSTRACT FROM AUTHOR]

Copyright of Water Resources Research is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)