Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes

• Published in: Stochastic environmental research and risk assessment Vol. 33; no. 2; pp. 481 - 514
• Main Authors: Papacharalampous, Georgia, Tyralis, Hristos, Koutsoyiannis, Demetris
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2019; Springer Nature B.V
• Subjects: Aquatic Pollution; Artificial intelligence; Chemistry and Earth Sciences; Computational Intelligence; Computer applications; Computer Science; Computer simulation; Earth and Environmental Science; Earth Sciences; Environment; Forecasting; Hydrology; Learning algorithms; Machine learning; Math. Appl. in Environmental Science; Original Paper; Physics; Probability Theory and Stochastic Processes; Production methods; River discharge; River flow; Rivers; Statistics for Engineering; Stochastic processes; Time series; Waste Water Technology; Water Management; Water Pollution Control; Support vector machines; No free lunch theorem; Stochastic hydrology; River discharge; Random forests; Time series
• ISSN: 1436-3240; 1436-3259
• DOI: 10.1007/s00477-018-1638-6

Research within the field of hydrology often focuses on the statistical problem of comparing stochastic to machine learning (ML) forecasting methods. The performed comparisons are based on case studies, while a study providing large-scale results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 extensive computational experiments based on simulations. Each of these experiments uses 2000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the forecasting performance of the methods using 18 metrics. The results indicate that stochastic and ML methods may produce equally useful forecasts.