20200225_Predicting and Analyzing Water Quality using Machine Learning: A Comprehensive Model

 

1. Title, Journal, and Authors

Title: Predicting and Analyzing Water Quality using Machine Learning: A Comprehensive Model

Journal: IEEE

Authors: Yafra Khan, Chai Soo See

* Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Kota Samarahan, Malaysia

 

2. Summary

 This research is carried to devise a comprehensive water prediction model using an artificial intelligence model (ANN), multivariate statistical techniques such as PCA, and Non-linear Autoregressive (NAR) model. The water quality historical data with a 6-minutes time interval for 5 months for 4 parameters i.e. DO, Specific Conductance, Chlorophyll, and DO are used to input data.

 

 In the results of modeling, though all the parameters show high prediction accuracies, in the case of specific conductance, there is overfitting for the training data. Therefore, to improve this model, there needs to be a balance between bias and variance, afterward.

 

3. Application to research

- Time-series data analysis will be needed to predict the future.

 

4. Contact

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 : jeongds92@gist.ac.kr