Search

Streambed grain sizes control river hydro‐biogeochemical (HBGC) processes and functions. However, measuring their quantities, distributions, and uncertainties is challenging due to the diversity and heterogeneity of natural streams. This work presents a photo‐driven, artificial intelligence (AI)‐enabled, and theory‐based workflow for extracting the quantities, distributions, and uncertainties of streambed grain sizes from photos. Specifically, we first trained You Only Look Once, an object detection AI, using 11,977 grain labels from 36 photos collected from nine different stream environments. We demonstrated its accuracy with a coefficient of determination of 0.98, a Nash–Sutcliffe efficiency of 0.98, and a mean absolute relative error of 6.65% in predicting the median grain size of 20 ground‐truth photos representing nine typical stream environments. The AI is then used to extract the grain size distributions and determine their characteristic grain sizes, including the 10th, 50th, 60th, and 84th percentiles, for 1,999 photos taken at 66 sites within a watershed in the Northwest US. The results indicate that the 10th, median, 60th, and 84th percentiles of the grain sizes follow log‐normal distributions, with most likely values of 2.49, 6.62, 7.68, and 10.78 cm, respectively. The average uncertainties associated with these values are 9.70%, 7.33%, 9.27%, and 11.11%, respectively. These data allow for the computation of the quantities, distributions, and uncertainties of streambed HBGC parameters, including Manning's coefficient, Darcy‐Weisbach friction factor, top layer interstitial velocity magnitude, and nitrate uptake velocity. Additionally, major sources of uncertainty in grain sizes and their impact on HBGC parameters are examined. Plain Language Summary: Streambed grain sizes control river hydro‐biogeochemical function by modulating the resistance, speed of water exchange, and nutrient transport at water‐sediment interface. Consequently, quantifying grain sizes and size‐dependent hydro‐biogeochemical parameters is critical for predicting river's function. In natural streams, measuring these sizes and parameters, however, is challenging because grain sizes vary from millimeters to a few meters, change from small creeks to big streams, and could be concealed by complex non‐grain materials such as water, ice, mud, and grasses. All these factors make the size measurements a time‐consuming and high‐uncertain task. We address these challenges by demonstrating a workflow that combines computer vision artificial intelligence (AI), smartphone photos, and new uncertainty quantification theories. The AI performs well across various sizes, locations, and stream environments as indicated by an accuracy metric of 0.98. We apply the AI to extract the grain sizes and their characteristic percentiles for 1,999 photos. These characteristic grain sizes are then input into existing and our new theories to derive the quantities, distributions, and uncertainties of hydrobiogeochemical parameters. The high accuracy of the AI and the success of extracting grain sizes and hydro‐biogeochemical parameters demonstrate the potential to advance river science with computer vision AI and mobile devices. Key Points: Stream sediments bigger than 44 microns can be detected from smartphone photos by You Only Look Once with a Nash–Sutcliffe efficiency of 0.98Quantities, distributions, and uncertainties of streambed grain sizes can be determined from photosImpact of grain size uncertainty on hydrobiogeochemical parameters is examined [ABSTRACT FROM AUTHOR]