20200331_Efficient Water Quality Prediction Using Supervised Machine Learning
1. Title, Journal, and Authors
Title: Efficient Water Quality Prediction Using Supervised Machine Learning
Authors: Umair Ahmed1, Rafia Mumtaz1,*, Hirra Anwar1, Asa A. Shad1, Rabia Irfan1, and Jose Garcia-Nieto2
1 School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST)
2 Department of Languages and Computer Sciences, Ada Byron Research Building, University of Malaga
Early water quality prediction was carried with supervised machine learning algorithms, instead of already existing methodologies consuming a lot of time and expense. Data selection, dividing the data for learning with cross-validation, modeling, and results analysis were carried. Temperature, pH, turbidity, and TDS (Total Dissolved Solids, TDS) were selected as input variables with the results of the correlation. Regression and classification models are used to predict WQI (Water Quality Index, WQI) and WQC (Water Quality Class), respectively.
In the results, gradient boosting showed the highest accuracy for WQI and MLP (Multi Linear Perceptron) for WQC. In the future, it will be helpful to establish an early water quality prediction system with the combination of sensors, IoT systems, and these algorithms.
3. Originality & Creativity
- Supervised machine learning models are introduced to predict water quality.
4. Application to research
- In this research, WQI is used, but the Korean water class would be used to predict Korean water qualities.
Dae Seong Jeong / Integrated Ph.D. program
Environmental Systems Engineering Lab.
School of Environmental Science & Engineering
Gwangju Institute of Science and Technology
1 Oryong-dong Buk-gu Gwangju, 500-712, Korea
Phone : +82-10-2003-7860
E-mail : firstname.lastname@example.org