Concept of Soil Moisture Ratio for Determining the Spatial Distribution of Soil Moisture Using Physiographic Parameters of a Basin and Artificial Neural Networks (ANNs)

The results of investigations on shaping the soil moisture ratio in mountain basin Mątny stream located Gorce region, Poland, are presented. A was defined as a given point to one base watershed. Investigations were carried out, using TDR device, for 379 measuring points an irregular network, 0–25 cm layer. Values fluctuated between 0.75 and 1.85. Based measurements, artificial neural network (ANN) model MLP type constructed, with nine neurons input layer, four hidden layer neuron output Input parameters influencing chosen based physiographic parameters: altitude, flow direction, height a.s.l., clay content, land use, exposition, slope shape, hydrologic group place slope. ANN generated module data mining program Statistica 12. Physiographic database, digital elevation ArcGIS. value learning parameter obtained, 0.722, satisfactory. Comparison experimental values obtained showed good fit; determination coefficient 0.581. minimal tendency overestimate values. Global sensitivity analysis that highest influence wetness provided by slope, while lowest fraction hydrological group. explained relative satisfactory degree.