Runoff analysis in humid forest catchment with artificial neural network

Hydrometeorological data, i.e. meteorological, water discharge and moisture content data have been collected over the past 10 years in the Tono area of central Japan. By analyzing soil moisture data and by making inferences from field studies, possible factors influencing stream discharge are explored. The soil moisture data obtained from 40-cm depth carry the integrated effect of the upstream catchment area and are important for estimating stream discharge. Vertical infiltration is important in the upper 20-cm, due to the high hydraulic conductivity of this part of forested soil. However, lateral flow through this layer becomes dominant during very high rainfall and/or following a long succession of rainfall events, resulting in rapid throughflow. A new type of artificial neural network (ANN) model based on a back propagation algorithm is formulated using the analyses. The formulated ANN model makes use of soil moisture data in estimating stream runoff and may be considered useful as an aid to catchment monitoring.