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

Abstract

Hydrological 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

Time Series Modeling on Daily Streamflow in a Lack-Data Catchment

“…This land cover data together with the soil texture data are used to determine the infiltration and percolation parameters in the loss method of SMA equation. High infiltration rates have the potential to occur in forest land cover with high density and coarse-grained soil types with high porosity [14]. Likewise, percolation always follows the previous process of infiltration [15][16].…”

Assessment of hybrid machine learning algorithms using TRMM rainfall data for daily inflow forecasting in Três Marias Reservoir, eastern Brazil

“…1 b illustrates the grid utilized to download TRMM data over the Upper São Francisco sub-basin, and the proportional areas of each measurement point within the river basin. TRMM represents a collaborative effort between the Japanese space agency NASDA (now JAXA) and NASA, focusing on investigating tropical and subtropical precipitation — which makes up two-thirds of terrestrial precipitation — and modeling global climate processes [ [30] , [31] , [32] , [33] ]. TRMM's primary objective is to establish a comprehensive database regarding rainfall distribution and latent heat exchanges in the region encompassing latitudes 35° N and 35° S. This area is predominantly occupied by oceans, leading to a dearth of surface and radiosonde atmospheric data.…”