Abstarct: The importance of proper utilization of limited resources of water and soil is clear to everybody. Soil as one of the most vital elements plays an important role in the life of organisms. In recent decades, following the massive growth of the world's population, human use of natural resources, especially agricultural lands, is not baxsed on their ability and talent. This study was conducted to investigate the spatial pattern of soil physical and chemical properties in green space of Abarkouh city in Yazd province, using geographic information system (GIS), and also the possibility of predicting the parameters of the Phillip and Horton parameters and final water infiltration rate using artificial neural network and support vector machine (SVM). To conduct this research, 100 points were selected in urban green space. In all studied areas, soil is collected from a depth of 0-30 cm of soil surface and some physical and chemical properties of soil including texture, electrical conductivity, acidity, organic matter and calcium carbonate using was measured standard laboratory method. The results showed that the kriging interpolation method was better than the inverse weight method. The multilxayer perceptron neural network (MLP) with 4 different scenarios including 3, 5, 7 and 9 inputs and SVM with 9 inputs were analyzed for infiltration parameters and final water infiltration rate prediction. The results showed that the network with 9 inputs had the greatest R2 and the lowest error in Phillip and Horton parameters prediction. The sensitivity analysis showed that the designed nets had the highest sensitivity to soil sodium adsorption ratio and the organic matter among studied inputs. The SVM model had better ability in soil water infiltration rate prediction compared to ANN model.