Irrigation Water Requirement Prediction through Various Data Mining Techniques Applied on a Carefully Pre-processed Dataset

Large amount of water in irrigated agriculture is wasted due to poor water management practices.To improve water management in irrigated areas, models for estimation of future water requirements are needed. In this study, we prepare a dataset containing information on suitable attributes. The data are obtained from three different sources namely water delivery statements,meteorological data, and remote sensing images. In order to make the prepared dataset useful for demand forecasting and pattern extraction we pre-process the dataset using a novel approach based on a combination of irrigation and data mining knowledge. We then evaluate the effectiveness of five different data mining methods and a traditional method based on Evapotranspiration (ETc), in water requirement prediction. Our experimental results indicate the usefulness of the proposed data pre-processing technique and the effectiveness of data mining methods (such as SysFor). Among the six methods we used, SysFor produces the best prediction with 97.5% accuracy.