Biomagnetic monitoring combined with support vector machine: a new opportunity for predicting particle-bound-heavy metals

Abstract

Biomagnetic monitoring includes fast and simple methods to estimate airborne heavy metals. Leaves of Osmanthus fragrans Lour and Ligustrum lucidum Ait were collected simultaneously with PM10 from a mega-city of China during one year. Magnetic properties of leaves and metal concentrations in PM10 were analyzed. Metal concentrations were estimated using leaf magnetic properties and meteorological factors as input variables in support vector machine (SVM) models. The mean concentrations of many metals were highest in winter and lowest in summer. Hazard index for potentially toxic metals was 5.77, a level considered unsafe. The combined carcinogenic risk was higher than precautionary value (10−4). Ferrimagnetic minerals were dominant magnetic minerals in leaves. Principal component analysis indicated iron & steel industry and soil dust were the common sources for many metals and magnetic minerals on leaves. However, the poor simulation results obtained with multiple linear regression confirmed strong nonlinear relationships between metal concentrations and leaf magnetic properties. SVM models including leaf magnetic variables as inputs yielded better simulation results for all elements. Simulations were promising for Ti, Cd and Zn, whereas relatively poor for Ni. Our study demonstrates the feasibility of prediction of airborne heavy metals based on biomagnetic monitoring of tree leaves.