Large-scale assessment of Prophet for multi-step ahead forecasting of monthly streamflow

Abstract

Abstract. We assess the performance of the recently introduced Prophet model in multi-step ahead forecasting of monthly streamflow by using a large dataset. Our aim is to compare the results derived through two different approaches. The first approach uses past information about the time series to be forecasted only (standard approach), while the second approach uses exogenous predictor variables alongside with the use of the endogenous ones. The additional information used in the fitting and forecasting processes includes monthly precipitation and/or temperature time series, and their forecasts respectively. Specifically, the exploited exogenous (observed or forecasted) information considered at each time step exclusively concerns the time of interest. The algorithms based on the Prophet model are in total four. Their forecasts are also compared with those obtained using two classical algorithms and two benchmarks. The comparison is performed in terms of four metrics. The findings suggest that the compared approaches are equally useful.

Prediction of Novel Coronavirus (nCOVID-19) Propagation Based on SEIR, ARIMA and Prophet Model

“…The novel idea is proposed by researchers [12] for analyzing the behavioral pattern of user smartphone by prophet algorithm to find out the continuous pattern and behavioral trend with the help of six daily behavioral patterns which are also used for training the model. The author [13] implemented prophet algorithm to analyze the result which was obtained by two different approaches. The variables were predicted in first approaches whereas the second approach used two variables like observed and forecasted values.…”

Short-Term Ambient Temperature Forecasting for Smart Heaters

“…Taylor and Letham [24] proposed Prophet, a flexible tool to decompose time-series into components like trend, seasonality and irregularity. Such tool has been used and compared with other techniques in several contexts, as air pollution forecasts [25], daily or monthly stream-flow forecasting [26], [27], and water precipitation [28].…”

Binary Grey Wolf Optimization-Regularized Extreme Learning Machine Wrapper Coupled with the Boruta Algorithm for Monthly Streamflow Forecasting

“…Streamflow forecasting models can be divided into two classes: physics-based models and datadriven models (Mohammadi et al 2020). In recent years, researchers have shown increased interest in developing data-driven models for streamflow forecasting due to their flexibility and simplicity (Adnan et al 2018;Hadi and Tombul 2018a, b;da Silva Melo Honorato et al 2018;Tyralis and Papacharalampous 2018;Woldemeskel et al 2018;Rezaie-Balf et al 2019;Jiang et al 2020).…”