Artificial neural networks aided annual rainfall erosivity factor values calculation in Poland

Abstract

Calculation and analysis of annual R-factor local values for 103 stations in Poland were the main aims of this study. Calculations were made by means of single hidden layer perceptron artificial neural network on the base of monthly precipitation totals from years: 1961-1980. For most of the analyzed stations calculated average annual R-factor values were low or moderate, at the range from 50 to 80 MJ⋅ha-1⋅cm⋅h-1. A strong relation between calculated average annual factor values and station elevation above see level was observed. Because of this, geostatistical algorithms incorporating elevation information should be used for further updating the isoerodents map of Poland.