International Journal of Advanced Research in Chemical Science (IJARCS) Volume 12, Issue 1, 2025, PP 21-29 ISSN No. (Online) 2349-0403 DOI: https://doi.org/10.20431/2349-0403.1201003 www.arcjournals.org International Journal of Advanced Research in Chemical Science (IJARCS) Page | 21 Application of Machine Learning Framework on Heavy Metals Fate in the Coastal Environment Clement O. Obadimu 1 , Ifiok O. Ekwere 1 , Solomon E. Shaibu 2* , Ubong B. Essien 3 , Ruth O. A. Adelagun 4 , Saeed G. Adewusi 5 1 Department of Chemistry, Akwa Ibom State University, Nigeria 2 Department of Chemistry, University of Uyo, Uyo, Nigeria 3 Department of Animal and Environmental Biology, University of Uyo, Uyo, Nigeria 4 Department of Chemical Sciences, Federal University Wukari 5 Department of Chemistry, School of Sciences, Federal University of Education, Zaria, Nigeria 1. INTRODUCTION In recent years, heavy metal pollution stemming from industrial development has become a pressing issue, posing serious threats to food security and ecological safety. Coastal regions are particularly vulnerable to heavy metal contamination, which adversely impacts ecosystems and human health (Bandara & Manage, 2023). The contamination of water sources with heavy metals is now a significant global environmental concern, exacerbated by urbanization, climate change, and industrialization. Key sources of this pollution include mining waste, landfill leachates, industrial and municipal wastewater, urban runoff, and natural processes such as weathering, rock erosion, and volcanic activity. Efforts to develop effective methods for removing heavy metals from wastewater have intensified, as these pollutants jeopardize freshwater supplies and river ecosystems. Heavy metals often accumulate in coastal sediments, which act as major repositories for these contaminants. Coastal environments face continuous metal input from natural, industrial, and urban sources. Once introduced, metals readily bind to particulates and settle into sediments, leading to their accumulation (Ekwere, 2020). The importance of monitoring and addressing heavy metal pollution in these environments has driven innovative approaches, including the application of integrated machine learning techniques. These advanced methods have revolutionized environmental monitoring, providing new insights and strategies for mitigating the effects of pollution and climate change. By leveraging such technologies, researchers can enhance the understanding and management of heavy metal contamination in aquatic ecosystems, contributing to more sustainable solutions (Shaibu et al., 2024 and Ubong et al., 2023). Machine learning models are applied to predict the future (Lu & Li 2024; Obadimu et al., 2024). These *Corresponding Author: Solomon E. Shaibu, Department of Chemistry, University of Uyo, Uyo, Nigeria. Abstract The increasing contamination of aquatic ecosystems by heavy metals poses serious environmental and health risks, exacerbated by urbanization, industrialization, and climate change. This study investigates heavy metal concentrations in water and sediment samples from the Nwaniba River, Akwa Ibom State, Nigeria, using machine learning models—Random Forest (RF), Support Vector Machines (SVM), and Artificial Neural Networks (ANN)—for predictive modeling and ecological risk assessment. The concentrations of Cr, Cu, Pb, Mn, Ni, Zn, and Fe were analyzed using Inductively Coupled Plasma – Atomic Emission Spectroscopy (ICP- AES), revealing significant spatial variability, with sediments serving as critical sinks for metal accumulation. The observed concentration trend in both water and sediment followed Fe > Mn > Cu > Zn > Ni > Cr > Pb, highlighting Fe and Mn as the dominant metals. The study also identified strong correlations among certain metals, indicating shared geochemical origins. Machine learning models exhibited strong predictive performance, with RF outperforming SVM and ANN, based on Mean Absolute Error (MAE) and Mean Squared Error (MSE) values, making it a reliable tool for environmental monitoring. These findings emphasize the need for targeted remediation strategies and stricter environmental regulations to mitigate contamination levels and safeguard public health. Keywords: Machine Learning, Heavy Metals, Water, Sediment, Metal Fate.