Page 71 - AJWEP-22-5

Asian Journal of Water, Environment and Pollution. Vol. 22, No. 5 (2025), pp. 65-79.
doi: 10.36922/AJWEP025210165

ORIGINAL RESEARCH ARTICLE

Hybrid Nesterov-accelerated adaptive moment
estimation–differential evolution optimization for long

short-term memory-based dissolved oxygen prediction in

water quality assessment

Tu Jun* , Azman Yasin , and Nur Suhaili Mansor
School of Computing, College of Arts and Sciences, University Utara Malaysia, Sintok, Kedah, Malaysia
*Corresponding author: Tu Jun (tujun792324486@gmail.com)

Received: May 21, 2025; 1st revised: May 30, 2025; 2nd revised: June 13, 2025; Accepted: June 19, 2025;
Published online: July 10, 2025

Abstract: Accurate and dynamic prediction of water quality indicators is increasingly critical due to rising
pollution and water resource insecurity, particularly when dealing with high-dimensional, nonlinear time series
data. Dissolved oxygen (DO), a key indicator of aquatic ecosystem health and pollution, requires high prediction
accuracy for effective environmental management. This study aims to enhance the accuracy and adaptability of
DO prediction by addressing the limitations of traditional deep learning methods, such as slow convergence and
local optima. We propose a novel hybrid optimization framework that combines Nesterov-accelerated Adaptive
Moment Estimation (Nadam) with the differential evolution algorithm. A dual-population cooperation strategy and
an information exchange mechanism were incorporated during the training of a long short-term memory (LSTM)
network to achieve a dynamic balance between global exploration and local exploitation. This improves the
model’s optimization efficiency and generalization. The research utilized a multivariate water quality time series
dataset from Kaggle based on official data monitoring. Correlation analysis was conducted to ensure the scientific
validity and effectiveness of the selected input variables. Experimental results demonstrated that the proposed
method significantly outperforms traditional optimization strategies for DO prediction. Compared to the original
Nadam optimizer, it reduced the mean squared prediction error by 47.8%, exhibiting enhanced adaptability and
robustness in complex pollution scenarios. This study presents an effective optimization strategy to improve LSTM
performance in water quality forecasting, along with a scalable and interpretable intelligent analysis framework. It
provides both theoretical and practical support for water quality forecasting, early warning systems, and intelligent
environmental monitoring.
Keywords: Water quality management; Dissolved oxygen prediction; Hybrid optimization; Nadam; Differential
evolution

1. Introduction ecosystems, biodiversity, and public health. Among
1,2
various water quality indicators, dissolved oxygen (DO)
The accelerating pace of global industrialization and is widely recognized as a core variable for assessing the
urbanization has led to increasingly severe water quality health of water bodies, due to its critical role in regulating
3
deterioration, posing significant threats to aquatic processes such as ecosystem respiration, organic matter

Volume 22 Issue 5 (2025) 65 doi: 10.36922/AJWEP025210165