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

Rapid identification of high and low cadmium (Cd) accumulating rice cultivars using machine learning models with molecular markers and soil Cd levels as input data

Excessive accumulation of cadmium (Cd) in rice grains threatens food safety and human health. Growing low Cd accumulating rice cultivars is an effective approach to produce low-Cd rice. However, field screening of low-Cd rice cultivars is laborious, time-consuming, and subjected to the influence of environment × genotype interactions. In the present study, we investigated whether machine learning-based methods incorporating genotype and soil Cd concentration can identify high and low-Cd accumulating rice cultivars. One hundred and sixty-seven locally adapted high-yielding rice cultivars were grown in three fields with different soil Cd levels and genotyped using four molecular markers related to grain Cd accumulation. We identified sixteen cultivars as stable low-Cd accumulators with grain Cd concentrations below the 0.2 mg kg^-1 food safety limit in all three paddy fields. In addition, we developed eight machine learning-based models to predict low- and high-Cd accumulating rice cultivars with genotypes and soil Cd levels as input data. The optimized model classifies low- or high-Cd cultivars (i.e., the grain Cd concentration below or above 0.2 mg kg^-1) with an overall accuracy of 76%. These results indicate that machine learning-based classification models constructed with molecular markers and soil Cd levels can quickly and accurately identify the high- and low-Cd accumulating rice cultivars.

Content of Cadmium and Nickel in Soils and Assimilatory Organs of Park Woody Species Exposed to Polluted Air

The rising level of pollutant emissions is becoming one of the most pressing environmental problems of our time. Therefore, this work is focused on evaluating Cd and Ni contamination of soils and assimilatory organs of two native (Acer platanoides L., Taxus baccata L.) and two non-native (Negundo aceroides Moench, Thuja occidentalis L.) woody species in urban parks of SW Slovakia. The contents of Cd and Ni in soils were determined by the AAS method and, in the assimilatory organs of trees, by the AAS-ETA method. The studied soils (Fluvisol, Phaeozem) have neutral soil reactions and a moderate organic matter content. Cadmium soil contamination is considerable to very high; in the case of Ni, it is moderate to low. Cadmium levels detected in leaves were 31% higher than in needles, while Ni levels were 27% lower. Significant ecological factors in relation to the studied woody species were evaluated using PCA. The first three principal components of PCA significantly correlated with Cd (PC1) and Ni (PC3) contents in soils and Cd content in assimilatory organs (PC2), thus suggesting that these elements could especially originate from industrial and vehicular sources. Knowledge of the factors affecting the accumulation of risk elements in the assimilatory organs of park woody species can be successfully used, especially in the assessment of the quality of the urban environment and the selection of suitable cultivars for planting in areas with air pollution.

Modeling Cadmium Contents in a Soil–Rice System and Identifying Potential Controls

Cadmium (Cd) pollution in a soil–rice system is closely related to widely concerning issues, such as food security and health risk due to exposure to heavy metals. Therefore, modeling the Cd content in a soil–rice system and identifying related controls could provide critical information for ensuring food security and reducing related health risks. To archive this goal, in this study, we collected 217 pairs of soil–rice samples from three subareas in Zhejiang Province in the Yangtze River Delta of China. All soil–rice samples were air-dried and conducted for chemical analysis. The Pearson’s correlation coefficient, ANOVA, co-occurrence network, multiple regression model, and nonlinear principal component analysis were then used to predict the Cd content in rice and identify potential controls for the accumulation of Cd in rice. Our results indicate that although the mean total concentration of Cd in soil samples was higher than that of the background value in Zhejiang Province, the mean concentration of Cd in rice was higher than that of the national regulation value. Furthermore, a significant difference was detected for Cd content in rice planted in different soil groups derived from different parental materials. In addition, soil organic matter and total Cd in the soil are essential factors for predicting Cd concentrations in rice. Additionally, specific dominant factors resulting in Cd accumulation in rice planted at different subareas were identified via nonlinear principal component analysis. Our study provides new insights and essential implications for policymakers to formulate specific prevention and control strategies for Cd pollution and related health risks.

Using an ensemble model coupled with portable X-ray fluorescence and visible near-infrared spectroscopy to explore the viability of mapping and estimating arsenic in an agricultural soil

Increasing concentrations of potentially toxic elements (PTE) in agricultural soils remain a major source of public concern. Monitoring PTEs in an agricultural field with no history of contaminants necessitate adequate analysis utilizing a robust model to accurately uncover hidden PTEs. Detecting and mapping the distribution of soil properties using portable X-ray fluorescence (pXRF) and proximal sensing techniques is not only rapid, but also relatively inexpensive. In this study, an ensemble model, consisting of partial least square regression (PLSR), support vector machine (SVM), random forest (RF) and cubist, was used for the prediction and mapping of soil As content in an agricultural field with no history of pollution. The datasets were collected using pXRF and field spectroscopy techniques. The main goal was to compare the ensemble model to each of the calibration techniques in terms of prediction accuracy of As content in such a field. Other components [e.g., soil organic carbon (SOC), Mn, S, soil pH, Fe] that are known to influence As levels in the soil were also retrieved to assess their correlation with soil As. The models were evaluated using the root mean squared error (RMSE_CV), the coefficient of determination (R²_CV) and the ratio of performance to interquartile range (RPIQ). In terms of prediction accuracy, the ensemble model outperformed each of the individual techniques (R²_CV = 0.80/0.75) and obtained the least error margin (RMSE_CV = 1.91/2.16). Overall, all the predictive techniques were able to detect both low and high estimated values of soil As within the study field, but with the ensemble model resembling the measurements better. The ensemble model, a promising tool as demonstrated by the current study, is highly recommended to be included in future studies for more accurate estimation of As and other PTEs in other agricultural fields.

Pollution Characteristics, Spatial Patterns, and Sources of Toxic Elements in Soils from a Typical Industrial City of Eastern China

Soil pollution due to toxic elements (TEs) has been a core environmental concern globally, particularly in areas with developed industries. In this study, we sampled 300 surface (0–0.2 m) soil samples from Yuyao City in eastern China. Initially, the geo-accumulation index, potential ecological risk index, single pollution index, and Nemerow composite pollution index were used to evaluate the soil contamination status in Yuyao City. Ordinary kriging was then deployed to map the distribution of the soil TEs. Subsequently, indicator kriging was utilized to identify regions with high risk of TE pollution. Finally, the positive matrix factorization model was used to apportion the sources of the different TEs. Our results indicated that the mean content of different TEs kept the order: Zn > Cr > Pb > Cu > Ni > As > Hg ≈ Cd. Soil pollution was mainly caused by Cd and Hg in the soil of Yuyao City, while the content of other TEs was maintained at a safe level. Regions with high TE content and high pollution risk of TEs are mainly located in the central part of Yuyao City. Four sources of soil TEs were apportioned in Yuyao City. The Pb, Hg, and Zn contents in soil were mainly derived from traffic activities, coal combustion, and smelting. Meanwhile, Cu was mainly sourced from industrial emissions and atmospheric deposition, Cr and Ni mainly originated from soil parental materials, and Cd and As were produced by industrial and agricultural activities. Our study provides important implications for improving the soil environment and contributes to the development of efficient strategies for TE pollution control and remediation.

Human risk associated with the ingestion of artichokes grown in soils irrigated with water contaminated by potentially toxic elements, Junin, Peru

The contamination of water, air and soil with potentially toxic elements (PTE) compromises the supply of contaminant free food. Vegetables grown in contaminated soils can absorb and accumulate PTE at concentrations that are toxic to human health. In this context, the human risk associated with the intake of artichokes grown in soils irrigated with PTE contaminated water was assessed. 120 samples of surface soil and artichoke heads were collected and the concentrations of Cu, Fe, Pb, Zn and As were determined. The results showed that the concentrations of Cu, Fe and Zn in soil did not exceed the standards of the Ministry of Environment of Peru, but they did exceed those of Pb (125.45 mg kg^-1) and As (28.70 mg kg^-1). The decreasing order of mean PTE concentration in artichoke heads was Fe > Zn > Cu > Pb > As, exceeding the permissible levels of FAO/WHO CODEX Alimentarius. However, the concentrations of As comply with the maximum limits of inorganic contaminants in vegetables (0.3 mg kg^-1) established in the MERCOSUR regulations. The non-carcinogenic and carcinogenic risk of Pb and As indicated that the ingestion of artichoke heads does not represent a health risk.

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

Unreasonable human activities may cause the accumulation of heavy metals (HMs) in the agricultural soil, which will ultimately threaten the quality of soil environment, the safety of agricultural products, and human health. Therefore, the accumulation characteristics, potential sources, and health risks of HMs in agricultural soils in China’s subtropical regions were investigated. The mean Hg, Cu, Zn, Pb, and Cd concentrations of agricultural soil in Jinhua City have exceeded the corresponding background values of Zhejiang Province, while the mean concentrations of determined 8 HMs were less than their corresponding risk-screening values for soil contamination of agricultural land in China. The spatial distribution of As, Cr, Ni, Cu, and Pb were generally distributed in large patches, and Hg, Zn, and Cd were generally sporadically distributed. A positive definite matrix factor analysis (PMF) model had better performance than an absolute principal component–multiple linear regression (APCS-MLR) model in the identification of major sources of soil HMs, as it revealed higher R2 value (0.81–0.99) and lower prediction error (−0.93–0.25%). The noncarcinogenic risks (HI) of the 8 HMs to adults and children were within the acceptable range, while the carcinogenic risk (RI) of children has exceeded the safety threshold, which needs to be addressed by relevant departments. The PMF based human health risk assessment model indicated that industrial sources contributed the highest risk to HI (32.92% and 30.47%) and RI (60.74% and 61.5%) for adults and children, followed by agricultural sources (21.34%, 29.31% and 32.94% 33.19%). Therefore, integrated environmental management should be implemented to control and reduce the accumulation of soil HMs from agricultural and industrial sources.