Development of a Spatial Hydrologic Soil Map Using Spectral Reflectance Band Recognition and a Multiple-Output Artificial Neural Network Model

Abstract

Soil type is important in any civil engineering project. Thorough and comprehensive information on soils 15 in both the spatial and temporal domains can assist in sustainable hydrological, environmental and agricultural 16 development. Conventional soil sampling and laboratory analysis are generally time-consuming, costly and limited in 17 their ability to retrieve the temporal and spatial variability, especially in large areas. Remote sensing is able to provide 18 meaningful data, including soil properties, on several spatial scales using spectral reflectance. In this study, a multiple 19 output artificial neural network model was integrated with geographic information system, remote sensing and survey 20 data to determine the distributions of hydrologic soil groups in the Horan Valley in the Western Desert of Iraq. The 21 model performance was evaluated using seven performance criteria along with the hydrologic soil groups developed 22 by the United States Geological Survey (USGS). On the basis of the performance criteria, the model performed best 23 for predicting the spatial distribution of clay soil, and the predicted soil types agreed well with the soil classifications 24 of the USGS. Most of the samples were categorized as sandy loam, whereas one sample was categorized as loamy 25 sand. The proposed method is reliable for predicting the hydrological soil groups in a study area.