Surface Water Treatment Analysis: Performance Evaluation and Prediction Using Artificial Neural Network Modelling—A Case Study

DOI

10.2991/978-94-6463-884-4_50How to use a DOI?

Keywords

Water Quality Index (WQI); Artificial Neural Network (ANN); Long-Short Term Memory (LSTM); Root Mean Squared Error (RMSE); Mean Absolute Error (MAE); Coefficient of Determination (R2)

Abstract

This case study aims to assess how water quality is improved after water treatment processes and explores the LSTM model’s prediction capabilities for predicting the Water Quality Index (WQI) for the Kushighat Surface Water Treatment Plant in Sylhet, Bangladesh. A total of 420 datasets in the laboratory. The samples were collected monthly over a 7-months period (September 2023 to March 2024) on five water quality parameters. It was found that 71.19% of the samples met the ideal limits for pH, 90.48% for Electrical Conductivity, 98.10% for TDS, 88.10% for turbidity, and 100.00% for chloride according to WHO reference. The Water Quality Index (WQI) classifies water quality as excellent, good, poor, very poor, or requiring important treatment. After calculation of WQI, it was found that 72.61% of the water sample falls under the excellent category, 11.90% falls under the good category, 14.76% falls under the poor category, and 0% falls under the very poor category. The paper presents a Long Short-Term Memory (LSTM) model which is a type of artificial neural network, for predicting the Water Quality Index, demonstrating high predictive accuracy for both training and testing datasets. The root mean square error (RMSE) values are 0.885 and 1.3116, the mean absolute error (MAE) values are 0.566 and .75764 and, the coefficient of determination (R²) values are 0.99815 and 0.99592 respectively for train and test data. The study contributes to water quality evaluation and prediction methods by utilizing advanced machine learning techniques to regulate and prevent water pollution, despite some limitations.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md. Misbah Uddin
AU  - Md. Abu Sayeed
AU  - Md. Wayes Sajeeb
PY  - 2025
DA  - 2025/11/18
TI  - Surface Water Treatment Analysis: Performance Evaluation and Prediction Using Artificial Neural Network Modelling—A Case Study
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 417
EP  - 424
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_50
DO  - 10.2991/978-94-6463-884-4_50
ID  - Uddin2025
ER  -