Estimations of nitrate nitrogen, total phosphorus flux and suspended sediment concentration (SSC) as indicators of surface-erosion processes using an ANN (Artificial Neural Network) based on geomorphological parameters in mountainous catchments

Abstract

In this paper, we describe methods to establish the relationships among geomorphology (physiographic) data, topography, and physical parameters in different-sized catchments using GIS techniques. GIS software allows performing interpolation point, vector or raster analysis based on topographic parameters, simultaneously with mapping land use. This technique depends on the quantity of spatial information. Our objective was to explain the most important geomorphological parameters with an emphasis on surface erosion in mountain areas. Assessment of fluvial sediment in streams is essential to evaluate surface run-off. In the present paper, Artificial Neural Networks (ANNs) were applied to show relationships among total phosphorus, nitrate nitrogen and suspended sediment concentration using architecture based on geomorphological features. Results may be applied at a catchment scale of 1 km2 to more than 50 km2. Our methods are important for investigating the land-use for final assembly depending on sediment-erosion appraisal. This understanding is critical for developing geomorphological models to predict the detachment of soil and transport from their mass, derived-debris material and surface run-off. Our approach will be useful for land management to evaluate risks of sediment transport and raindrop splash and rill erosion in mountainous catchment areas.