AN INTELLIGENT DECISION SUPPORT SYSTEM FOR WASTEWATER TREATMENT PLANTS IN THE SULTANATE OF OMANSHERIMON PULIPRATHU CHERIAN, ALAA ISMAEEL, MANNA ANN MARIYAM, SIAN GIJO, WINNY ANNA VARKEY, SHERIN JOHN AND NISHA JOSEPH
All living things need access to clean water to survive. However, drinkable water is scarce, and as a result of human activity, these supplies are becoming severely contaminated. In order to replenish these depleting water supplies while also reducing contamination-causing activities, several steps must be made. Wastewater treatment plants (WWTPs) are essential for removing toxins from various sectors so that clean water may be released into the environment with the least amount of environmental harm. It involves a combination of complex processes used to treat and remove pollutants from water. All the decisions in WWTPs are conventionally taken by skilled and qualified plant operators with the necessary training and education in order to get the job done right. There can be a considerable amount of error that can occur when critical decisions are taken by these operators. In order to tackle this and to improve efficiency and accuracy, a Decision Support System (DSS) can be used as traditional methods of decision making by human operators are considerably less efficient. Water quality parameters such as pH, hardness, solids, chloramines, sulphate, conductivity, organic carbon, trihalomethanes, turbidity are used to determine the purity status of water being considered. The proposed study focuses on a Machine Learning based DSS built on Decision Tree (DT) algorithm that will predict the purity of water using historical data, which will aid the plant operators in making daily operational decisions at the WTTPs. The experimental result analysis shows that the model built using DT algorithm gives good performance.