Precision farming aims at reducing environmental risks and increasing productivity. Soils are multi-functional media, in which air, water and biota occur together to form an essential part of the landscape, with a fundamental role in the environment. The requirement for herbicides and fertilizers can vary within a field in response to spatial differences in soil properties. Near infrared (NIR) spectroscopy is widely used today as a nondestructive analytical technique, which is capable of determining a number of physio-chemical parameters. The objective of this study was to develop optimal models for predicting chemical properties of paddy soils by visible and NIR reflectance spectra. Reflectance spectra, moisture contents, pH, total nitrogen, organic matter, available phosphate, exchangeable potassium, ex. calcium, ex. magnesium, ex. sodium, iron, manganese, zinc, and copper of soil samples were measured. The reflectance spectra were measured in the wavelength range of 400-2,500 nm with 2-nm intervals. The method of moving window partial least square (MWPLS) analysis, which is a wavelength interval selection method for multi-component spectra analysis, was used to determine the soil properties. MWPLS models showed the possibility to predict chemical properties of soil samples in the wavelength range of 1,000-2,500 nm, offering the possibility of considerable cost savings and increased efficiency over the conventional analysis method.