Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost

被引:74
作者
Szczepanek, Robert [1 ]
机构
[1] Jagiellonian Univ, Inst Geol Sci, Fac Geog & Geol, PL-30387 Krakow, Poland
关键词
streamflow forecasting; machine learning; XGBoost; random forest; multiple linear regression; POLISH CARPATHIAN MOUNTAINS; PRECIPITATION; MODEL; PREDICTION; REGRESSION; RIVER;
D O I
10.3390/hydrology9120226
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
Streamflow forecasting in mountainous catchments is and will continue to be one of the important hydrological tasks. In recent years machine learning models are increasingly used for such forecasts. A direct comparison of the use of the three gradient boosting models (XGBoost, LightGBM and CatBoost) to forecast daily streamflow in mountainous catchment is our main contribution. As predictors we use daily precipitation, runoff at upstream gauge station and two-day preceding observations. All three algorithms are simple to implement in Python, fast and robust. Compared to deep machine learning models (like LSTM), they allow for easy interpretation of the significance of predictors. All tested models achieved Nash-Sutcliffe model efficiency (NSE) in the range of 0.85-0.89 and RMSE in the range of 6.8-7.8 m3s-1. A minimum of 12 years of training data series is required for such a result. The XGBoost did not turn out to be the best model for the daily streamflow forecast, although it is the most popular model. Using default model parameters, the best results were obtained with CatBoost. By optimizing the hyperparameters, the best forecast results were obtained by LightGBM. The differences between the model results are much smaller than the differences within the models themselves when suboptimal hyperparameters are used.
引用
收藏
页数:18
相关论文
共 56 条
[21]   Predicting Ice Phenomena in a River Using the Artificial Neural Network and Extreme Gradient Boosting [J].
Graf, Renata ;
Kolerski, Tomasz ;
Zhu, Senlin .
RESOURCES-BASEL, 2022, 11 (02)
[22]   CatBoost for big data: an interdisciplinary review [J].
Hancock, John T. ;
Khoshgoftaar, Taghi M. .
JOURNAL OF BIG DATA, 2020, 7 (01)
[23]   Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques [J].
Jose, Dinu Maria ;
Vincent, Amala Mary ;
Dwarakish, Gowdagere Siddaramaiah .
SCIENTIFIC REPORTS, 2022, 12 (01)
[24]   Applicability of ANN Model and CPSOCGSA Algorithm for Multi-Time Step Ahead River Streamflow Forecasting [J].
Kareem, Baydaa Abdul ;
Zubaidi, Salah L. ;
Ridha, Hussein Mohammed ;
Al-Ansari, Nadhir ;
Al-Bdairi, Nabeel Saleem Saad .
HYDROLOGY, 2022, 9 (10)
[25]  
Ke GL, 2017, ADV NEUR IN, V30
[26]   Altered precipitation characteristics in two Polish Carpathian basins, with implications for water resources [J].
Kedra, Mariola .
CLIMATE RESEARCH, 2017, 72 (03) :251-265
[27]  
Kholiavchuk D, 2019, THEOR APPL CLIMATOL, V138, P1615, DOI [10.1007/s00704-019-02943-4., 10.1007/s00704-019-02910-z]
[28]   Low-flow estimation beyond the mean - expectile loss and extreme gradient boosting for spatiotemporal low-flow prediction in Austria [J].
Laimighofer, Johannes ;
Melcher, Michael ;
Laaha, Gregor .
HYDROLOGY AND EARTH SYSTEM SCIENCES, 2022, 26 (17) :4553-4574
[29]   Investigating the effects of local weather, streamflow lag, and global climate information on 1-month-ahead streamflow forecasting by using XGBoost and SHAP: two case studies involving the contiguous USA [J].
Liu, Jin ;
Ren, Kun ;
Ming, Tingzhen ;
Qu, Jihong ;
Guo, Wenxian ;
Li, Haohao .
ACTA GEOPHYSICA, 2023, 71 (02) :905-925
[30]  
Lundberg SM, 2017, ADV NEUR IN, V30