Monthly Streamflow Modeling Based on Self-Organizing Maps and Satellite-Estimated Rainfall Data

Abstract

AbstractHydrological data provide valuable information for the decision-making process in water resources management, where long and complete time series are always desired. However, it is common to deal with missing data when working on streamflow time series. Rainfall-streamflow modeling is an alternative to overcome such a difficulty. In this paper, self-organizing maps (SOM) were developed to simulate monthly inflows to a reservoir based on satellite-estimated gridded precipitation time series. Three different calibration datasets from Três Marias Reservoir, composed of inflows (targets) and 91 TRMM-estimated rainfall data (inputs), from 1998 to 2019, were used. The results showed that the inflow data homogeneity pattern influenced the rainfall-streamflow modeling. The models generally showed superior performance during the calibration phase, whereas the outcomes varied depending on the data homogeneity pattern and the chosen SOM structure in the testing phase. Regardless of the input data homogeneity, the SOM networks showed excellent results for the rainfall-runoff modeling, presenting Nash–Sutcliffe coefficients greater than 0.90. Graphical Abstract