Predicting Modified Fournier Index by Using Artificial Neural Network in Central Europe.
Journal:
International journal of environmental research and public health
PMID:
36078383
Abstract
The Modified Fournier Index () is one of the indices that can assess the erosivity of rainfall. However, the implementation of the artificial neural network (ANN) for the prediction of the is still rare. In this research, climate data (monthly and yearly precipitation (, ) (mm), daily maximum precipitation () (mm), monthly mean temperature () (°C), daily maximum mean temperature () (°C), and daily minimum mean temperature () (°C)) were collected from three stations in Hungary (Budapest, Debrecen, and Pécs) between 1901 and 2020. The was calculated, and then, the performance of two ANNs (multilayer perceptron (MLP) and radial basis function (RBF)) in predicting the was evaluated under four scenarios. The average values were between 66.30 ± 15.40 (low erosivity) in Debrecen and 75.39 ± 15.39 (low erosivity) in Pecs. The prediction of the by using MLP was good ( = 0.71, = 0.69). Additionally, the performance of RBF was accurate ( = 0.68, = 0.73). However, the correlation coefficient between the observed and the predicted one ranged between 0.83 (Budapest (SC2-MLP)) and 0.86 (Pécs (SC3-RBF)). Interestingly, the statistical analyses promoted SC2 ( + ) and SC4 + + + as the best scenarios for predicting by using the ANN-MLP and ANN-RBF, respectively. However, the sensitivity analysis highlighted that , , and had the highest relative importance in the prediction process. The output of this research promoted the ANN (MLP and RBF) as an effective tool for predicting rainfall erosivity in Central Europe.