Journal
WATER
Volume 14, Issue 19, Pages -Publisher
MDPI
DOI: 10.3390/w14192939
Keywords
classification; machine learning; water quality index (WQI); Langat River Basin
Categories
Funding
- Universiti Kebangsaan Malaysia [GGP-2020-032, GUP-2019-060]
Ask authors/readers for more resources
Traditionally, evaluating water quality has been expensive and ineffective for real-time monitoring. This study utilizes machine learning methods to construct a model capable of predicting water quality and finds that the Support Vector Machines (SVM) model performs the best in predicting river water quality. Additionally, the use of kernel functions, grid search methods, and multiclass classification techniques significantly impacts the effectiveness of the SVM model.
Traditionally, water quality is evaluated using expensive laboratory and statistical procedures, making real-time monitoring ineffective. Poor water quality requires a more practical and cost-effective solution. Water pollution has been a severe issue, hurting water quality in recent years. Therefore, it is crucial to create a model that forecasts water quality to control water pollution and inform consumers in the event of the detection of poor water quality. For effective water quality management, it is essential to accurately estimate the water quality class. Motivated by these considerations, we utilize the benefits of machine learning methods to construct a model capable of predicting the water quality index and water quality class. This study aims to investigate the performance of machine learning models for multiclass classification in the Langat River Basin water quality assessment. Three machine learning models were developed using Artificial Neural Networks (ANN), Decision Trees (DT), and Support Vector Machines (SVM) to classify river water quality. Comparative performance analysis between the three models indicates that the SVM is the best model for predicting river water quality in this study. In addition, there is a statistically significant difference in performance between the SVM, DT, and ANN models at the 0.05 level of confidence. The use of the kernel function, the grid search method, and the multiclass classification technique used in this study significantly impacts the effectiveness of the SVM model. The findings bolster the idea that machine learning models, particularly SVM, can be used to forecast WQI with a high degree of accuracy, hence enhancing water quality management. Consequently, the model based on machine learning lowered the cost and complexity of calculating sub-indices of six water quality parameters and classifying water quality compared to the standard IKA-JAS formula.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available