This study proposed a deep learning-based model to estimate stream water-use rate (WUR) using precipitation (P) and potential evapotranspiration (PET). Correlations were explored to identify relationships among accumulated meteorological variables for various time durations (three-, four-, five-, and six-month cumulative) and WUR, which revealed that three-month cumulative meteorological variables and WUR were highly correlated. A deep belief network (DBN) based on iterating parameter tuning was developed to estimate WUR using P, PET, and antecedent stream water-use rate (DWUR). The training and validation periods were 2011–2016, and 2017–2019, respectively. The results showed that the PET-DWUR based model provided better performances in Nash–Sutcliff efficiency (NSE), root mean square error (RMSE), and determination coefficient (R2) than the P-PET-DWUR and P-DWUR models. The framework in this study can provide a forecast model for deficiencies of stream water use coupled with a weather forecast model.

中文翻译：

---

使用深度置信网络基于水文气象变量估算用水率

本研究提出了一种基于深度学习的模型，利用降水 (P) 和潜在蒸散量 (PET) 估算河流用水率 (WUR)。探索相关性以确定不同持续时间（三个月、四月、五月和六个月累积）的累积气象变量与 WUR 之间的关系，这表明三个月累积气象变量与 WUR 高度相关。开发了基于迭代参数调整的深度置信网络 (DBN)，以使用 P、PET 和先行流用水率 (DWUR) 来估计 WUR。训练期和验证期分别为 2011-2016 年和 2017-2019 年。结果表明，基于 PET-DWUR 的模型在 Nash-Sutcliff 效率 (NSE)、均方根误差 (RMSE)、和决定系数 (R2) 比 P-PET-DWUR 和 P-DWUR 模型。本研究中的框架可以提供一个与天气预报模型相结合的河流用水不足的预测模型。