Anomaly Detection in Soil Heavy Metal Contamination Using Unsupervised Learning for Environmental Risk Assessment

2026-04-29

AI Summary

This study addresses heavy metal contamination in soils at waste dumpsites in urbanized areas of Ghana by proposing an unsupervised consensus anomaly detection framework that integrates Isolation Forest, PCA reconstruction error, and DBSCAN to identify pollution anomalies from measurements of eight heavy metals across twelve sampling sites. For the first time, multivariate anomaly patterns are quantitatively linked to the Hazard Index (HI) and Incremental Lifetime Cancer Risk (ILCR), revealing three distinct anomaly types. The approach identifies six robust anomalous samples (7.7% of the dataset), all clustered at a single location, exhibiting HI values 70–80% higher than normal samples and uniformly exceeding the HI = 1 threshold. A strong positive correlation (r ≈ 0.8) between PCA reconstruction error and HI underscores the framework’s potential for precise environmental health risk assessment and targeted remediation.

Abstract

Soil contamination by heavy metals poses a persistent environmental and public health concern in rapidly urbanising regions of Ghana, particularly at unregulated waste disposal sites. This study applies an unsupervised machine learning framework to detect and characterise anomalous heavy metal contamination patterns in soils from twelve waste sites and residential controls in the Central Region, of Ghana. Concentrations of eight metals (As, Cd, Cr, Cu, Hg, Ni, Pb, Zn) were analysed alongside standard health risk indices, including the Hazard Index (HI) and Incremental Lifetime Cancer Risk (ILCR). Isolation Forest and PCA reconstruction error each identified $12$ anomalous samples ($15.4\%$ of $78$ samples), while DBSCAN detected no density-isolated noise points. A consensus approach isolated six robust anomalies ($7.7\%)$, all spatially concentrated at a single site (S3). Anomalies exhibited approximately $70$--$80\%$ higher mean HI values than normal samples, with all consensus anomalies exceeding the HI$=1$ threshold. PCA reconstruction error showed a strong positive association with HI ($r \approx 0.8$), indicating consistency between multivariate deviation and health risk. Three distinct anomaly types were identified: extreme Cu enrichment at S3, anomalously low Ni at S4/S5, and moderate multi-metal (Pb--Zn) co-elevation at S9--S12. The results demonstrate that unsupervised machine learning provides granular, objective insight beyond aggregate indices, enabling targeted site prioritisation and risk-informed environmental management.

Problem

• anomaly detection
• soil heavy metal contamination
• environmental risk assessment
• unsupervised learning
• waste disposal sites

Innovation

• unsupervised learning
• anomaly detection
• heavy metal contamination
• health risk assessment
• PCA reconstruction error