2026-09-03 パシフィック・ノースウェスト国立研究所（PNNL）
This research explores how machine learning–enabled methods can make faster and more accurate riverbed sediment grain size estimates. The results showed that advanced technologies, like object detection algorithms, could improve the ability to understand and predict watershed function based on water flow and material transformation. (Image: Regier et al. [2025])
＜関連情報＞
- https://www.pnnl.gov/publications/machine-learning-approach-replace-both-manual-methods-and-top-down-estimates-riverbed
- https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2025.1529503/full
河床堆積物の粒径を推定するさまざまな方法は、流域規模で異なる結果を示す Different methods of estimating riverbed sediment grain size diverge at the basin scale
Peter Regier,Yunxiang Chen,Kyongho Son,Jie Bao,,Brieanne Forbes,Amy Goldman,Matt Kaufman,Kenton A. Rod,James Stegen
Frontiers in Earth Science Published:05 June 2025
DOI:https://doi.org/10.3389/feart.2025.1529503
Abstract
Introduction:
The distribution of sediment grain size in streams and rivers is often quantified by the median grain size (D50), a key metric for understanding and predicting hydrologic and biogeochemical function of streams and rivers. Manual D50 measurements are time-consuming and ignore larger grains, while approaches to model D50 based on catchment characteristics may over-generalize and miss site-scale heterogeneity. Machine learning-enabled object detection methods like You Only Look Once (YOLO) provides an alternative that enables estimation of D50 that is faster than manual measurements and more site-specific than predictions based on catchment characteristics.
Methods:
To understand the potential role of object detection methods for improving understanding of D50, we compared D50 estimates made manually, predicted from catchment characteristics, and using a YOLO-enabled approach across the Yakima River Basin.
Results:
We found distinct differences between methods for D50 averages and variability, and relationships between D50 estimates and basin characteristics.
Discussion:
We discuss the advantages and limitations of object detection methods versus current methods, and explore potential future directions to combine D50 methods to better estimate spatiotemporal variation of D50, and improve incorporation into basin-scale models.
