New Frontiers in Communication and Intelligent Systems
Prediction of Water Portability using Machine Learning Methods
Authors: Mohak Verma, Sukriti Jaitly and Jaisakthi S M
Publishing Date: 06-05-2022
ISBN: 978-81-95502-00-4
Abstract
Water covers around 3/4th of our planet’s surface and is one of the most significant sources of energy for the continuation of life on the planet. In the wake of rapid urbanization and industrialization, water quality has declined at an alarming rate, leading to the spread of life-threatening illnesses and diseases. The consequences of polluted water are far-reaching, affecting every area of human existence. As a result, effective management of water is critical to ensuring that the water's quality is optimized. When data is evaluated and water quality predictions are made in advance, the consequences of water pollution may be dealt with more effectively. There have been many prior studies that have addressed this problem; nevertheless, there is still more work that needs to be done to improve the efficacy, dependability, accuracy, and usefulness of the existing water quality management methods. The goal of this research is to predict water portability by comparing the accuracy of six different machine learning models on a dataset containing water quality metrics for 3276 different water bodies and 10 features.
Keywords
Water quality prediction, Machine learning, XGBoost, SVM, Random Forest, Bagging Classifier.
Cite as
Mohak Verma, Sukriti Jaitly and Jaisakthi S M, "Prediction of Water Portability using Machine Learning Methods", In: Rahul Srivastava and Aditya Kr. Singh Pundir (eds), New Frontiers in Communication and Intelligent Systems, SCRS, India, 2022, pp. 415-424. https://doi.org/10.52458/978-81-95502-00-4-44