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

TL;DR

This study employs unsupervised machine learning techniques to identify and characterize soil heavy metal contamination anomalies in Ghana, revealing specific high-risk sites and metal patterns for environmental health assessment.

Contribution

It introduces a consensus-based anomaly detection approach that combines multiple unsupervised methods to improve soil contamination identification in environmental risk analysis.

Findings

12 anomalous samples identified by isolation forest and PCA, none by DBSCAN

6 robust anomalies concentrated at a single site, S3

Anomalies had 70-80% higher health risk indices than normal samples

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.