KNOWLEDGE DISCOVERY MODEL FOR WATER QUALITY PREDICTION USING MACHINE LEARNING

KNOWLEDGE DISCOVERY MODEL FOR WATER QUALITY PREDICTION USING MACHINE LEARNING

Dhanya D Shetty1, Sahana M Naik2, Samiksha S Nagwekar3, Arul N4
1,2,3B E Students, Dept. of Computer Science and Engineering, A J Institute of Engineering and Technology, Mangaluru, India

4Assistant Professor, Dept. of Computer Science and Engineering, A J Institute of Engineering and Technology, Mangaluru, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - The survival of industry and agriculture depends on freshwater. An essential step in managing freshwater assets is the evaluation of the quality of the water. According to the World Health Organizations annual report, many people, particularly pregnant women, and children become ill or pass away as a result of a lack of access to safe drinking water. Before using water for anything, including drinking, chemical spraying (pesticides, etc.), or animal hydration, it is essential to assess its quality. Testing the quality of the water is one method of locating potable water. Therefore, proper water monitoring is essential for safe, sterile, and clean water. Water testing is essential for examining water sources; reliability and determining drinking water; safety. Using factors such as Ph value, conductivity, hardness, and so on, our model predicts whether or not the water is safe to drink. Access to safe drinking water is critical to health, a basic human right, and a component of any health-protection strategy. Various pollutants have been threatening water quality in recent years.

Key Words: water quality forecast; MLP neural network; Daubechies 5 wavelet; long short-term memory network; hybrid model; decomposition-and-ensemble.