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.

中文翻译：

---

使用机器学习模型 YOLO 量化河床颗粒大小、不确定性和水文生物地球化学参数


河床颗粒大小控制着河流水文生物地球化学 （HBGC） 过程和功能。然而，由于自然溪流的多样性和异质性，测量它们的数量、分布和不确定性具有挑战性。这项工作提出了一种照片驱动、人工智能 （AI） 支持和基于理论的工作流程，用于从照片中提取河床颗粒尺寸的数量、分布和不确定性。具体来说，我们首先使用从 9 个不同流环境中收集的 36 张照片中的 11,977 个颗粒标签训练了对象检测 AI You Only Look Once。我们以 0.98 的决定系数、0.98 的 Nash-Sutcliffe 效率和 6.65% 的平均绝对相对误差来预测代表 9 个典型河流环境的 20 张真实照片的中位粒度，证明了它的准确性。然后使用 AI 提取粒度分布并确定其特征粒度，包括第 10、50、60 和第 84 个百分位数，这些照片在美国西北部流域内的 66 个地点拍摄的 1,999 张照片。结果表明，晶粒尺寸的第 10 个、中位数、第 60 个和第 84 个百分位数服从对数正态分布，最有可能的值分别为 2.49、6.62、7.68 和 10.78 厘米。与这些值相关的平均不确定性分别为 9.70%、7.33%、9.27% 和 11.11%。这些数据允许计算河床 HBGC 参数的数量、分布和不确定性，包括 Manning 系数、Darcy-Weisbach 摩擦系数、顶层间隙速度大小和硝酸盐吸收速度。此外，还研究了晶粒尺寸不确定性的主要来源及其对 HBGC 参数的影响。