Risk assessment of runoff generation using an artificial neural network and field plots in road and forest land areas

Abstract

Runoff generation potential (RGP) on hillslopes is an important issue in the forest roads network monitoring process. In this study, an artificial neural network (ANN) was used to predict RGP in forest road hillslopes. We trained, optimized, and tested the ANN by using field plot data from the Shirghalaye watershed located in the southern part of the Caspian Sea in Iran. Field plots were used to evaluate the effective factors in runoff generation, 45 plots were installed to measure actual runoff volume (RFP) in different environmental conditions including land cover, slope gradient, soil texture, and soil moisture. A multi-layer perceptron (MLP) network was implemented. The runoff volume was the output variable and the ground cover, slope gradient, initial moisture of soil, soil texture (clay, silt and sand percentage) were the network inputs. The results showed that ANN can predict runoff volume within the values of an appropriate level in the training (R2 = 0.95, mean squared error (MSE) = 0.009) and test stages (R2 = 0.80, MSE = 0.01). Moreover, the tested network was used to predict the runoff volume on the forest road hillslopes in the study area. Finally, an RGP map was generated based on the results of the prediction of the ANNs and the geographic information system (GIS) capabilities. The results showed the RGP in the forest road hillslopes was better predicted when using both an ANN and a GIS. This study provides new insights into the potential use of ANN in hydrological simulations.