Intelligent environmental knowledge system for sustainable water resource management solution

Water shortage is a severe issue in many areas of Australia, particularly in the agricultural sector which is responsible for 65% of the total water usage. Water usage for irrigation and associated electricity costs are extremely high in Australia. So, accurate and timely decision support regarding efficient water usage is essential. Thus, a short-term low cost solution is needed to provide reliable advices on irrigation planning for the farmers such that the water wastage is optimized. Development of an integrated environmental knowledge recommendation system based on large scale dynamic web data mining and contextual knowledge integration to provide an expert water resource management solution was the main purpose of this work. Five different environmental data sources namely SILO, AWAP, ASRIS, CosmOz, and MODIS were integrated to develop and test the proposed knowledge recommendation framework called i-EKbase (intelligent Environmental Knowledgebase). Data driven supervised machine learning techniques namely Sugano type Adaptive Neuro Fuzzy Inference System, Multilayer perceptron network, Probabilistic neural network and Radial basis function network were used to learn and predict agricultural water balance for a specific location and given time period. This newly proposed predictive water resource estimation method based on large multi scale knowledge integration could potentially make the irrigation decision support systems more robust and efficient.