# Environmental Drivers and Explainable Modeling to Resolve Trace Metal Dynamics in a Lotic System

## TL;DR

This study uses machine learning to understand how environmental factors influence trace metal levels in a stream affected by human activity.

## Contribution

The study introduces an integrative computational framework to model and explain trace metal dynamics in lotic systems.

## Key findings

- Machine learning models accurately predicted trace metal concentrations with R2 values generally above 0.95.
- Environmental factors like temperature, NO2−, and redox conditions showed metal-specific control over trace metal dynamics.
- Trace metal distributions are primarily influenced by environmental sensitivity rather than uniform pollution sources.

## Abstract

Trace metal contamination in lotic freshwater systems exhibits pronounced heterogeneity arising from coupled hydrological connectivity, geochemical partitioning, and anthropogenic forcing, complicating exposure characterization in urban and peri-urban catchments. Addressing this complexity requires integrative analytical approaches capable of deciphering system-level controls, prompting an investigation of the environmental structuring and governing controls of dissolved trace metal signatures in a human-impacted stream using a system-oriented computational framework. To capture temporal variability associated with seasonal hydrological contrasts and heterogeneous pollution inputs, a station-based, season-resolved sampling strategy was implemented during the wet and dry seasons. Physicochemical gradients (pH, temperature, dissolved oxygen, and electrical conductivity), inorganic nitrogen species (NH3, NO2−, and NO3−), and phosphorus fractions (total phosphorus, TP; total orthophosphate, TOP; soluble reactive P, SRP) were jointly analyzed with dissolved concentrations of chromium (Cr), copper (Cu), nickel (Ni), lead (Pb), cadmium (Cd), mercury (Hg), and arsenic (As). Regression-based machine learning models were used to quantify element-specific sensitivities to hydrochemical drivers under wet–dry periods and to identify optimal predictive configurations. Predictive performance was consistently high for trace metals (R2 generally >0.95), with Random Forest providing the best accuracy for Cr, Ni, Pb, Cd, As, and Hg, whereas Cu was most reliably captured by an XGBoost tree ensemble (R2 = 0.994). Explainability analyses revealed heterogeneous, metal-specific control regimes: Cr was primarily driven by temperature, Ni by NO2− and redox-sensitive conditions, Cd by NH3 and temperature, and As by Hg in combination with phosphorus-related and redox-linked proxies, while Pb showed comparatively lower predictability relative to other metals. Trace metal distributions are therefore structured primarily by differential environmental sensitivity rather than uniform source-driven inputs, reinforcing the need for integrative computational frameworks when interpreting freshwater contamination under intensifying anthropogenic and climatic pressures.