Estimation of Heavy Metal Content in Soil Based on Machine Learning Models

Abstract

Heavy metal pollution in soil is threatening the ecological environment and human health. However, field measurement of heavy metal content in soil entails significant costs. Therefore, this study explores the estimation method of soil heavy metals based on remote sensing images and machine learning. To accurately estimate the heavy metal content, we propose a hybrid artificial intelligence model integrating least absolute shrinkage and selection operator (LASSO), genetic algorithm (GA) and error back propagation neural network (BPNN), namely the LASSO-GA-BPNN model. Meanwhile, this study compares the accuracy of the LASSO-GA-BPNN model, SVR (Support Vector Regression), RF (Random Forest) and spatial interpolation methods with Huanghua city as an example. Furthermore, the study uses the LASSO-GA-BPNN model to estimate the content of eight heavy metals (including Ni, Pb, Cr, Hg, Cd, As, Cu, and Zn) in Huanghua and visualize the results in high resolution. In addition, we calculate the Nemerow index based on the estimation results. The results denote that, the simultaneous optimization of BPNN by LASSO and GA can greatly improve the estimation accuracy and generalization ability. The LASSO-GA-BPNN model is a more accurate model for the estimate heavy metal content in soil compared to SVR, RF and spatial interpolation. Moreover, the comprehensive pollution level in Huanghua is mainly low pollution. The overall spatial distribution law of each heavy metal content is very similar, and the local spatial distribution of each heavy metal is different. The results are of great significance for soil pollution estimation.

Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management

“…Visible and near-infrared reflectance spectroscopy is an environmentally friendly and cost-efficient technique that shows promise for estimating concentrations of various heavy metals in soil. Additionally, it offers a viable alternative for assessing heavy metal levels across large areas and for an extended period (Shi et al, 2022).…”

“…AI can also integrate data from multiple sources, such as sensors, satellite imagery, and public health records. By combining diverse datasets, AI algorithms provide a holistic understanding of the distribution, movement, and impacts of hazardous substances (Wu et al, 2011;Hurlbert et al, 2019;Shafique et al, 2022;Shi et al, 2022). In addition, AI can offer decision support tools for human operators engaged in hazardous substance monitoring.…”

Heavy metals concentration and availability of serpentine soils in southwestern Turkey

“…The characteristic vegetation of Ni-containing serpentine soils in northern Europe is Caryophyllaceae, while it is Euphorbiaceae in tropical regions and Brassicaceae family in the temperate Mediterranean belt (Bani et al, 2013). Long-term accumulation of heavy metal elements causes serious damage to the ecological environment (Shi et al, 2022). It is thought that this situation results from the toxic impacts of high heavy metals like Ni, Cr, Mn and Co possessed by serpentine soils (Rajakaruna and Boyd, 2014).…”

Risk Assessment of Agricultural Soil Heavy Metal Pollution Under the Hybrid Intelligent Evaluation Model

“…With the rise of artificial intelligence, in recent years, an increasing number of researchers have started to explore the use of artificial intelligence methods for soil heavy metal content prediction and pollution risk assessment. Shi et al [14] estimated the content of eight heavy metals in Huanghua area using the LASSO-GA-BPNN model and visualized the results at high resolution. Cao et al [15] proposed a parallel integrated neural network system and applied this model to simulate the soil heavy metal content data in Yinchuan, Ningxia Province, China and Wuhan, Hubei Province, China, demonstrating its high predictive accuracy.…”