Water Quality Prediction & Classification Based on Machine Learning Technique
Author(s):
CHAVANA SATEESH, T.N.R KUMAR
Keywords:
Machine Learning, Support vector Machine, Decision Tree
Abstract
One of the major problems the globe has faced in recent decades is estimating the quality of the water supply. This study offers a more precise classification and prediction model for water quality. Our everyday lives depend greatly on the quality of urban water. Urban water quality forecasting aids in reducing water pollution and safeguarding public health. However, estimating the quality of urban water is difficult since urban water quality fluctuates nonlinearly and depends on a variety of variables, including weather, water usage patterns, and land uses. Using the water quality data and water hydraulic data supplied by existing monitor stations and a range of data sources we saw in, we used a data-driven approach to predict the water quality over the following few hours in this work.
The city, including the weather, pipe networks, road network design, and points of interest (POIs). By conducting comprehensive experiments based on the literature, we first determine the key elements that have a significant impact on urban water quality. There are many machine learning algorithms for categorization, but selecting the right one is a crucial challenge. The proposed system experiment and study the machine learning algorithms to determine the optimal algorithm for the water quality monitoring system. In this experimental investigation, a real dataset is utilized to classify and predict the water quality in order to compare the effectiveness of the various classification methods.
Article Details
Unique Paper ID: 161011
Publication Volume & Issue: Volume 10, Issue 2
Page(s): 466 - 472
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024