Applications of Artificial Intelligence Based Tools to Distinct Problems Related to Different Aspects of the Water Sector

Abstract

This paper describes two applications of artificial intelligence based tools to distinct problems, related to different aspects of the water sector. The former describes the use of artificial neural networks (ANNs) to forecast the water quality of the Odivelas reservoir. The last is concerned with the development of clustering models applied to the public water supply. In this case an unsupervised learning was used to find groups of water with similar physical and chemical properties. Decision Trees were used in order to generate explanatory models of clusters formed. The number of clusters formed varied from 2 to 4. The model of the three clusters showed to be the most adequate since it allows differentiating the waters obtained from different sources.