Optimized Water Quality Prediction Using LSTM-MEOA Integration: Advancing Environmental Forecasting

DOI

10.2991/978-94-6463-738-0_32How to use a DOI?

Keywords

Water Quality Prediction; Long Short-Term Memory (LSTM); Modified Equilibrium Optimization Algorithm (MEOA); Time-Series Modeling; Machine Learning; Environmental Forecasting; LightGBM; Support Vector Machines (SVM); ARIMA

Abstract

Globally, biophysical environment, human health, and economic processes are threatened by the deteriorating quality of water. Since water quality data is often complex, non-linear and cross-dependent, most of the typical prediction models fail to deliver an accurate outcome. Improving the predictive power of the current models this research integrates the Long Short-Term Memory (LSTM) neural networks with the Equilibrium Optimisation Algorithm (MEOA). In this case, to formulate our solution, we combined the characteristics of LSTM in time series modelling, the optimisation of MEOA, fast training of LightGBM, classification of SVM and baseline comparison of ARIMA. Due to the nature of prediction tasks for water quality, this kind of approach tries to solve such problems. Our model could achieve localization to a highest fitness score of 61070.52 and an accuracy of 96.95% when validated with historical data and showed a significant improvement in the predictability. This state-of-the-art forecasting model might help to better preserve water resources and public health because it can offer environmental agencies and legislators considerable means for anticipating water quality problems in the future.

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  - D. Dhivagar
AU  - N. Pazhaniraja
AU  - M. Ganesan
AU  - K. Premkumar
PY  - 2025
DA  - 2025/06/22
TI  - Optimized Water Quality Prediction Using LSTM-MEOA Integration: Advancing Environmental Forecasting
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 387
EP  - 408
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_32
DO  - 10.2991/978-94-6463-738-0_32
ID  - Dhivagar2025
ER  -