Department of Civil Engineering, Faculty of Engineering, Aksaray University, Aksaray 68100, Turkey E-mail:
Water Sci Technol. 2023 Jun;87(11):2742-2755. doi: 10.2166/wst.2023.171.
Predicting missing historical or forecasting streamflows for future periods is a challenging task. This paper presents open-source data-driven machine learning models for streamflow prediction. The Random Forests algorithm is employed and the results are compared with other machine learning algorithms. The developed models are applied to the Kızılırmak River, Turkey. First model is built with streamflow of a single station (SS), and the second model is built with streamflows of multiple stations (MS). The SS model uses input parameters derived from one streamflow station. The MS model uses streamflow observations of nearby stations. Both models are tested to estimate missing historical and predict future streamflows. Model prediction performances are measured by root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), coefficient of determination (R), and percent bias (PBIAS). The SS model has an RMSE of 8.54, NSE and R of 0.98, and PBIAS of 0.7% for the historical period. The MS model has an RMSE of 17.65, NSE of 0.91, R of 0.93, and PBIAS of -13.64% for the future period. The SS model is useful to estimate missing historical streamflows, while the MS model provides better predictions for future periods, with its ability to better catch flow trends.
预测缺失的历史或未来时期的流量是一项具有挑战性的任务。本文提出了用于流量预测的开源数据驱动机器学习模型。采用随机森林算法，并将结果与其他机器学习算法进行比较。所开发的模型应用于土耳其的基兹里达河。第一个模型是基于单个站点的流量（SS）构建的，第二个模型是基于多个站点的流量（MS）构建的。SS 模型使用源自单个流量站的输入参数。MS 模型使用附近站点的流量观测值。这两个模型都经过测试以估计缺失的历史流量并预测未来流量。通过均方根误差（RMSE）、纳什-苏特克里夫效率（NSE）、决定系数（R）和偏度百分比（PBIAS）来衡量模型预测性能。SS 模型在历史时期的 RMSE 为 8.54，NSE 和 R 为 0.98，PBIAS 为 0.7%。MS 模型在未来时期的 RMSE 为 17.65，NSE 为 0.91，R 为 0.93，PBIAS 为-13.64%。SS 模型可用于估计缺失的历史流量，而 MS 模型则可以更好地预测未来时期，因为它能够更好地捕捉流量趋势。
