Predicting Bioaccumulation of Potentially Toxic Element in Soil–Rice Systems Using Multi-Source Data and Machine Learning Methods: A Case Study of an Industrial City in Southeast China

Abstract

Potentially toxic element (PTE) pollution in farmland soils and crops is a serious cause of concern in China. To analyze the bioaccumulation characteristics of chromium (Cr), zinc (Zn), copper (Cu), and nickel (Ni) in soil-rice systems, 911 pairs of top soil (0–0.2 m) and rice samples were collected from an industrial city in Southeast China. Multiple linear regression (MLR), support vector machines (SVM), random forest (RF), and Cubist were employed to construct models to predict the bioaccumulation coefficient (BAC) of PTEs in soil–rice systems and determine the potential dominators for PTE transfer from soil to rice grains. Cr, Cu, Zn, and Ni contents in soil of the survey region were higher than corresponding background contents in China. The mean Ni content of rice grains exceeded the national permissible limit, whereas the concentrations of Cr, Cu, and Zn were lower than their thresholds. The BAC of PTEs kept the sequence of Zn (0.219) > Cu (0.093) > Ni (0.032) > Cr (0.018). Of the four algorithms employed to estimate the bioaccumulation of Cr, Cu, Zn, and Ni in soil–rice systems, RF exhibited the best performance, with coefficient of determination (R2) ranging from 0.58 to 0.79 and root mean square error (RMSE) ranging from 0.03 to 0.04 mg kg−1. Total PTE concentration in soil, cation exchange capacity (CEC), and annual average precipitation were identified as top 3 dominators influencing PTE transfer from soil to rice grains. This study confirmed the feasibility and advantages of machine learning methods especially RF for estimating PTE accumulation in soil–rice systems, when compared with traditional statistical methods, such as MLR. Our study provides new tools for analyzing the transfer of PTEs from soil to rice, and can help decision-makers in developing more efficient policies for regulating PTE pollution in soil and crops, and reducing the corresponding health risks.

Mapping soil organic matter and identifying potential controls in the farmland of Southern China: Integration of multi‐source data, machine learning and geostatistics

“…A large number of regression trees (ntree) ensure model stability (ntree was set as 500 in current study). RF shows a clear advantage on capturing complicated linear and non‐linear relationships between dependent variables and covariates, as well as quantifying the relative importance of predictors (Xie et al, 2021).…”

Evaluate the Impact of Soil Contamination on Vegetables and Fruits

“…Through BCF, the concentration of metals in plant tissues is determined in relation to their growth medium, while TF determines way metals are translocated in the aerial vegetative parts of plants [12,[19][20][21]. As plant species used to remove metals from the environment, they can be listed: peas [1,22], lettuce [23], wood species (poplar, willow, ash) [24], oleander [25], flax and hemp [26], jute, rooster crest, field thyme [27], rapeseed and Indian mustard [28], sunflower and corn [29], cucumber [22,30], cherry tomato [15], sweet pepper [31], cabbage and broccoli [32], spinach [33,34].…”

“…In a statistical analysis [30] which describes the modeling of heavy metals in the soil-plant system, rice was used in the study and was used as algorithms: multiple linear regression (MLR), support vector machines (SVM), random forest (RF), and cubist. They have helped predict the bioaccumulation coefficient of metals in rice and to identify the potential for transfer of metals into the tissues of rice plants.…”

“…They have helped predict the bioaccumulation coefficient of metals in rice and to identify the potential for transfer of metals into the tissues of rice plants. The flow diagram of the study [30] carried out in China is shown in Figure 2.…”

An Integrated Approach for Source Apportionment and Health Risk Assessment of Heavy Metals in Subtropical Agricultural Soils, Eastern China

“…Heavy metals (HMs) in soil are characterized by high toxicity, nondegradability, weak mobility, and strong bioaccumulation [1,2]. With rapid urbanization, HMs pollution in agricultural soil caused by anthropogenic activities is becoming increasingly prominent and has become a global issue [3][4][5][6].…”