Multivariate Analysis of Toxic Contaminants: A Data-Driven Approach to Evaluating Harmful pollutants Accumulated in fish species

Sustainable fish resources are essential for ecological and economic stability, yet many freshwater fish species accumulate toxic contaminants that threaten human health, environment and regional economies. This study analyzes a multi-variable dataset from the Michigan Fish Contaminant Monitoring Program, containing 37 variables across numerous fish species and including key pollutants, such as mercury, perfluorooctane sulfonic acid (PFOS), polychlorinated biphenyls (PCBs), dichlorodiphenyltrichloroethane (DDT), chlordane, and toxaphene. After rigorous preprocessing, including missing-value treatment, outlier removal using the 3-sigma rule, and z-score standardization, principal component analysis (PCA) was applied to characterize contamination patterns. The principal component analysis revealed that the first three principal components explain approximately 55% of total variance, with PC1 reflecting overall contamination and fish size, while PC2 and PC3 distinguish pesticide-driven pollutants from industrial chemicals. These statistically derived contamination regimes highlight biophysical pressures that carry economic consequences. Notably, species such as Lake Whitefish and Lake Trout, which support a $5.1-billion Great Lakes fishery, exhibit contamination patterns with direct implications for market stability and food safety. The findings illustrate how multivariate statistical methods can inform ecological and environmental economic assessments, identifying pollution pathways and supporting circular-economy strategies aimed at reducing contaminant inputs, improving resource efficiency, and safeguarding economically and ecologically valuable fish populations.