Prediction heavy metals accumulation risk in rice using machine learning and mapping pollution risk

Ensemble learning-assisted quantitative identifying influencing factors of cadmium and arsenic concentration in rice grain based multiplexed data

Rapid and accurate prediction of rice Cd (rCd) and rice As (rAs) bioaccumulation are important for assessing the safe utilization of rice. Currently, there is lack of comprehensive and systematic exploration of the factors of rCd and rAs. Herein, ensemble learning (EL) was first used to analysis the 23 factors in 8 categories (heavy metal pollution characteristics, soil properties, geographical characteristics, meteorological factors, socio-economic factors, environmental factors, rice type, and nutrient element) in typical regions of China based on the results of 193 research papers from 2000 to 2024 in Web of Science database. Three machine learning methods were used to predict rCd and rAs concentrations and identify the key factors in each region, and explored the mechanism of Cd and As uptake in rice. The results showed that there were large differences in the factors affecting rice enrichment for the same heavy metal in different regions. For Cd, rice type (48.30 %), soil characteristics (28.14 %), and environmental factors (61.30 %) were the most important factors in Central South, East China, and Southwest China, respectively. For As, soil properties (34.01 %) and geographical characteristics (50.22 %) had the greatest influence in Central South and East China, respectively. Our study provided valuable insights into the prediction of rCd and rAs, thus contributing to ensuring food safety and preventing Cd and As exposure-associated health risks.

Research progress on the environmental risk assessment and remediation technologies of heavy metal pollution in agricultural soil

Controlling heavy metal pollution in agricultural soil has been a significant challenge. These heavy metals seriously threaten the surrounding ecological environment and human health. The effective assessment and remediation of heavy metals in agricultural soils are crucial. These two aspects support each other, forming a close and complete decision-making chain. Therefore, this review systematically summarizes the distribution characteristics of soil heavy metal pollution, the correlation between soil and crop heavy metal contents, the presence pattern and migration and transformation mode of heavy metals in the soil-crop system. The advantages and disadvantages of the risk evaluation tools and models of heavy metal pollution in farmland are further outlined, which provides important guidance for an in-depth understanding of the characteristics of heavy metal pollution in farmland soils and the assessment of the environmental risk. Soil remediation strategies involve multiple physical, chemical, biological and even combined technologies, and this paper compares the potential and effect of the above current remediation technologies in heavy metal polluted farmland soils. Finally, the main problems and possible research directions of future heavy metal risk assessment and remediation technologies in agricultural soils are prospected. This review provides new ideas for effective assessment and selection of remediation technologies based on the characterization of soil heavy metals.

Predicting cadmium enrichment in crops/vegetables and identifying the effects of soil factors based on transfer learning methods

Cadmium (Cd) is present in soils and can easily migrate into plants due to its various forms. This mobility allows it to be absorbed by plant roots and accumulate in edible parts, entering the food chain and posing health risks. In some regions, insufficient sampling and research, or the limited cultivation of specific vegetables and crops, make it challenging to gather adequate data for modeling. A total of 353 pairs of soil and crop/vegetable samples were collected across three regions using a unified measurement method. These samples were utilized to build predictive models to study the relationship between soil factors and cadmium (Cd) absorption in six different crops/vegetables, followed by a unified comparison. This study compares regression and probability models and determines the best feature combination, which can retain enough information to accurately predict and prevent over-fitting caused by too many features. The best feature combination is used to apply transfer learning to cadmium enrichment in crops/vegetables. The results show that the best accuracy of the random forest probability model in the rice dataset is 0.89. The best feature combination of prediction results was found by feature optimization. This feature combination has a very good effect on the prediction of cadmium in corn / vegetables by transfer learning. The accuracy of corn, rape and radish is 0.93,0.89 and 0.81, respectively. In the case of good prediction effect of transfer learning, available Cd is the most critical function, and available Cd is positively correlated with Cd in plants. It suggests that available heavy metal significantly influence predictions in crops/vegetables. In areas with less sampling and research, selecting relevant features and using transfer learning methods is more appropriate for constructing predictive models.

Natural factor-based spatial prediction and source apportionment of typical heavy metals in Chinese surface soil: Application of machine learning models

Predicting the natural distribution of heavy metals (HMs) in soil is important to understand the potential risk of pollution. However, suitable technologies are still lacking for wide scale due to the large spatial heterogeneity. In this study, we developed machine learning models for predicting natural contents of five typical HMs in soil, including As, Cd, Cr, Hg and Pb. It was found that the optional random forest (RF) model had the best performance with the R2 up to 0.64. Based on this model, potential distribution of the five HMs explored that elevated contents were mainly concentrated in the southwest and south central of China. Feature analysis illustrated that importance of natural factors followed the order of geological attributes > soil properties > climatic conditions > ecological functions. In particular, lithology of the parent material dominated the content of metals, with the contributions of 18-25%. Moreover, soil properties of pH, cation exchange capacity, profile depth of soil and vegetation coverage had different influences on HMs, due to the variability in the properties of different HMs. This study developed a mapping relationship between natural factors and soil HMs by data science method, which may provide instructive information for pollution control and planning decisions.

Machine learning-supported determination for site-specific natural background values of soil heavy metals

Heavy metal natural background values play a crucial role in distinguishing anthropogenic sources from natural sources to assess human impacts in polluted areas, thereby accurately formulating environmental policies. However, due to limitations imposed by human activities, research methods, and regional constraints, the determination of heavy metal background values, particularly on site or profile scale, is often challenging, highlighting the urgent need for new methodologies. To establish a comprehensive dataset containing heavy metal concentrations and soil properties, the study systematically collected and screened 82 soil profiles from areas minimally affected by human activities, resulting in a total of 2185 data sets. Using soil depth, pH, organic matter, weathering indices (SAF, BA), Fe2O3, MgO, Na2O, CaO, and K2O as model input variables, the predictive performance for site-specific background levels of Cd, Cr, Cu, Ni, Pb, and Zn was compared across four advanced machine learning models (RF (random forest), XGBoost (extreme gradient boosting), ANN (artificial neural network), SVR (support vector regression)). The results indicated that the optimal model for predicting background values of Cd, Cr, and Ni was XGBoost (MAE = 0.14 - 0.17; MSE = 0.04 - 0.06; R² = 0.82 - 0.87), while RF was used for Cu, Pb, and Zn (MAE = 0.01 - 0.18; MSE = 0.02 - 0.06; R² = 0.89 - 0.95). Importance assessments using RF and SHAP revealed that pH is a key controlling factor for Cd and Ni, Fe2O3 significantly impacts Cr, Cu, and Zn background levels, and K2O is the main controlling factor for Pb. The machine learning models developed can effectively predict the background levels of these six heavy metals based on major elemental and soil physicochemical properties, particularly achieving accurate predictions for Cu and Zn using just two input variables. This machine learning prediction framework is based on major elemental compositions and the physical/chemical properties of soil, enables precise and cost-effective point-to-point environmental assessments, thereby offering significant potential for practical applications.

Machine learning models with innovative outlier detection techniques for predicting heavy metal contamination in soils

Machine learning (ML) models for accurately predicting heavy metals with inconsistent outputs have improved owing to dataset outliers, which influence model reliability and accuracy. A comprehensive technique that combines machine learning and advanced statistical methods was applied to assess data outlier's effects on ML models. Ten ML models with three outlier detection methods predicted Cr, Ni, Cd, and Pb in Narayanganj soils. XGBoost with density-based spatial clustering of applications with noise (DBSCAN) improved model efficacy (R2). The R2 of Cr, Ni, Cd, and Pb was considerably enhanced by 11.11 %, 6.33 %, 14.47 %, and 5.68 %, respectively, indicating that outliers affected the model's HM prediction. Soil factors affected Cr (80 %), Ni (72.61 %), Cd (53.35 %), and Pb (63.47 %) concentrations based on feature importance. Contamination factor prediction showed considerable contamination for Cr, Ni, and Cd. LISA revealed Cd (55.4 %), Cr (49.3 %), and Pb (47.3 %) as the significant pollutant (p < 0.05). Moran's I index values for Cr, Ni, Cd, and Pb were 0.65, 0.58, 0.60, and 0.66, respectively, indicating strong positive spatial autocorrelation and clusters with similar contamination. Finally, this work successfully assessed the influence of data outliers on the ML model for soil HM contamination prediction, identifying crucial regions that require rapid conservation measures.

Evaluating heavy metals-related risk in staple crops and making financing strategy for corresponding soil remediation across China

China's staple crops face heavy metal (HMs) contamination, a widespread issue lacking a national assessment. We used machine learning (ML) to assess risks of 8 HMs in rice, wheat, and maize, and estimated a financing strategy for soil remediation via linear optimization and computable general equilibrium (CGE). The accumulation of HMs in crops depends on Soil-HMs, climate, soil properties, and crop types. Cd and Hg pose major soil pollution risks, while Cr, Pb, and Cd are the most threatening in crops. High-risk zones are located at the warm temperature and subtropical zones, with wheat most vulnerable. Over a quarter (26.77 %) of the nation's croplands are classified as high-risk, with a significant 60.89 % falling into the medium-risk category, leaving merely 12.34 % of the agricultural land in a safe condition. The estimated remediation cost is 58596.73 billion RMB and the crop loss is 808.03 billion RMB in a ten-year remediation period at the context of secure crop supply. The reallocation of social investment rather than raising new taxation for the remediation is beneficial to the GDP increase and social welfare despite some loss in the household income and enterprise income. This study provides a comprehensive evaluation for Crop-HMs risk and remediation policy, crucial for national crop security.

Environment-compatible heavy metal risk prediction method created with multilevel ensemble learning

Accurate health risk prediction (HRP) is an effective means of reducing the hazards of heavy metal (HM) exposure. It can address the drawbacks of lag and passivity faced by health risk assessment. This study innovatively proposed an HRP method, MEL-HR, based on multilevel ensemble learning (MEL) technology and environment compatibility. We conducted point and interval prediction experiments on health risks using 490 sets of data covering 17 environment factors. The point prediction results indicated that when the model predicts HI and TCR, the R2 values were 0.707 and 0.619, respectively. For P5, P50, and P95 in interval prediction, the R2 values of the model were 0.706, 0.703, and 0.672 for HI, and that for TCR were 0.620, 0.607, and 0.616, respectively. The analysis of feature importance indicated that, in addition to HM factors, longitude, mining area coefficient, and soil organic matter were key environmental factors affecting the MEL-HR model. Comparative experiments showed that compared to soil HMs-based MEL-HR, environment compatibility-based MEL-HR has improved the accuracy for HI and TCR by 19.83 % and 40.36 % for the point prediction and 22.06 % and 40.01 % for interval prediction. This study can provide technical support for targeted and resilient prevention and control of health risks.

Machine learning and structural equation modeling for revealing the influence factors and pathways of different water management regimes acting on brown rice cadmium

Excessive cadmium (Cd) in brown rice has detrimental effects on rice growth and human health. Water management is a cost-effective, eco-friendly measure to suppress Cd accumulation in rice. However, there is no acknowledged water management regime that reduces Cd accumulation in brown rice without compromising the yield. Meanwhile, the major factors affecting brown rice Cd and the pathways of water management affecting rice Cd are not clear. This study explored major factors affecting brown rice Cd using machine learning (ML) and examined the pathways of water management affecting rice Cd using a structural equation model (SEM). Three water management systems were set up, namely flooding, water-saving, and wetting irrigation. Results showed that water-saving irrigation increased dry matter and reduced Cd content and translocation. Root uptake during the grain filling stage and Cd remobilization before the grain filling stage contributed 36 % and 64 % of the Cd accumulation in brown rice, respectively. ML explained 97 % of the variance, suggesting that crop covariates were the most important (e.g., the brown rice bioconcentration factor (12 %), stem Cd (9 %), root-to-stem translocation factor (7 %)), followed by soil covariates (e.g., reducing substances 12 %) and water management (3 %). All SEM explanatory variables collectively explained 94 % of the variation, with a predictive power of 76 %. Water treatments indirectly affected soil available Fe and Mn (indirect effect coefficient = 0.909), iron plaques (indirect effect coefficient = 0.866), soil available Cd (indirect effect coefficient = -0.671), and Cd intensity of xylem sap (BICd, indirect effect coefficient = -0.664) via pH and reducing substances. BICd significantly positively affected stem Cd (path coefficient = 0.445). These findings provide insight into the agronomic and environmental effects of water management on brown rice Cd and influence pathways in soil-rice systems, suggesting that water-saving irrigation may alleviate Cd contamination in the paddy soil.

Predicting Cd accumulation in crops and identifying nonlinear effects of multiple environmental factors based on machine learning models

The traditional prediction of the Cd content in grains (Cdg) of crops primarily relies on the multiple linear regression models based on soil Cd content (Cds) and pH, neglecting inter-factorial interactions and nonlinear causal links between external environmental factors and Cdg. In this study, a comprehensive index system of multi-type environmental factors including soil properties, geology, climate, and anthropogenic activity was constructed. The machine learning models of the tree-based ensemble, support vector regression, artificial neural network for predicting Cdg of rice and wheat based on the environmental factor indexes significantly improved the accuracy than the traditional models of linear regression based on soil properties. Among them, the tree-based ensemble models of XGboost and random forest exhibited highest accuracies for predicting Cdg of rice and wheat, with R2 in the test dataset of 0.349 and 0.546, respectively. This study found that soil properties, including Cds, pH, and clay, have greater impacts on Cdg of rice and wheat, with combined contribution rates accounting for 65.2 % and 29.7 % respectively. Since wheat sampling areas are located in central and northern China, they are more constrained by precipitation and temperature than rice sampling areas in the south. Geologic and climate factors have a greater impact on Cdg of wheat, with a combined contribution rate of 49.9 %, which is higher than the corresponding rate of 20.9 % in rice. Furthermore, the Cdg of rice and wheat did not exhibit an absolute linear relationship with Cds, and excessively high Cds can reduce the bioconcentration factor of Cd accumulation in crops. Meanwhile, other environmental factors such as temperature, precipitation, elevation have marginal effects on the increase of Cdg of crops. This study provides a novel framework to optimize traditional soil plant transfer models, as well as offer a step towards realizing high precision prediction of Cd content in crops.

Identifying heavy metal sources and health risks in soil-vegetable systems of fragmented vegetable fields based on machine learning, positive matrix factorization model and Monte Carlo simulation

Urban fragmented vegetable fields offer fresh produce but pose a potential risk of heavy metal (HM) exposure. Thus, this study investigated HM sources and health risks in the soil-vegetable systems of Chongqing's central urban area. Results indicated that Cd was the primary pollutant, with 28.33 % of soil samples exceeding the screening value. Amaranth was particularly problematic, exceeding thresholds for Cd, Hg, and Cr, and both amaranth and celery showed significantly higher HM accumulation (p < 0.05). The HM pollution level in the soil-vegetable system was moderate or above. The sources of HMs identified via Positive matrix factorization (PMF) model included agricultural activities (18.19 %), natural soil parent material (25.88 %), mixed metal smelting and transportation (30.72 %), and coal combustion (25.21 %). Furthermore, evaluations using the Random Forest (RF) model revealed an intricate interaction of factors influencing the presence of HMs, where enterprise density, population density, and road density played significant roles in HMs accumulation. Monte Carlo assessments revealed higher non-carcinogenic risks for children (Pb, As) and greater carcinogenic risks for adults (Cd). Therefore, the issue of HM pollution in soils and vegetables from fragmented fields in industrial urban areas need attention, given the potential for elevated health risks with long-term vegetable consumption.

Improved mapping of heavy metals in agricultural soils using machine learning augmented with spatial regionalization indices

The accurate spatial mapping of heavy metal levels in agricultural soils is crucial for environmental management and food security. However, the inherent limitations of traditional interpolation methods and emerging machine-learning techniques restrict their spatial prediction accuracy. This study aimed to refine the spatial prediction of heavy metal distributions in Guangxi, China, by integrating machine learning models and spatial regionalization indices (SRIs). The results demonstrated that random forest (RF) models incorporating SRIs outperformed artificial neural network and support vector regression models, achieving R2 values exceeding 0.96 for eight heavy metals on the test data. Hierarchical clustering for feature selection further improved the model performance. The optimized RF models accurately predicted the heavy metal distributions in agricultural soils across the province, revealing higher levels in the central-western regions and lower levels in the north and south. Notably, the models identified that 25.78 % of agricultural soils constitute hotspots with multiple co-occurring heavy metals, and over 6.41 million people are exposed to excessive soil heavy metal levels. Our findings provide valuable insights for the development of targeted strategies for soil pollution control and agricultural soil management to safeguard food security and public health.

Accurate prediction of spatial distribution of soil potentially toxic elements using machine learning and associated key influencing factors identification: A case study in mining and smelting area in southwestern China

Accurate prediction of spatial distribution of potentially toxic elements (PTEs) is crucial for soil pollution prevention and risk control. Achieving accurate prediction of spatial distribution of soil PTEs at a large scale using conventional methods presents significant challenges. In this study, machine learning (ML) models, specially artificial neural network (ANN), random forest (RF), and extreme gradient boosting (XGB), were used to predict spatial distribution of soil PTEs and identify associated key factors in mining and smelting area located in Yunnan Province, China, under the three scenarios: (1) natural + socioeconomic + spatial datasets (NS), (2) NS + irrigation pollution index (IPI) datasets, (3) NS + IPI + deposition (DEPO) datasets. The results highlighted the combination of NS+IPI+DEPO yielded the highest predictive accuracy across ML models. Particularly, XGB exhibited the highest performance for As (R2 =0.7939), Cd (R2 =0.6679), Cu (R2 =0.8519), Pb (R2 =0.8317), and Zn (R2 =0.7669), whereas RF performed the best for Ni (R2 =0.7146). The feature importance and Shapley additive explanation (SHAP) analysis revealed that DEPO and IPI were the pivotal factors influencing the distribution of soil PTEs. Our findings highlighted the important role of DEPO in spatial distribution prediction of soil PTEs, which has often been ignored in previous studies.

Machine learning-driven source identification and ecological risk prediction of heavy metal pollution in cultivated soils

To overcome challenges in assessing the impact of environmental factors on heavy metal accumulation in soil due to limited comprehensive data, our study in Yangxin County, Hubei Province, China, analyzed 577 soil samples in combination with extensive big data. We used machine learning techniques, the potential ecological risk index, and the bivariate local Moran's index (BLMI) to predict Cr, Pb, Cd, As, and Hg concentrations in cultivated soil to assess ecological risks and identify pollution sources. The random forest model was selected for its superior performance among various machine learning models, and results indicated that heavy metal accumulation was substantially influenced by environmental factors such as climate, elevation, industrial activities, soil properties, railways, and population. Our ecological risk assessment highlighted areas of concern, where Cd and Hg were identified as the primary threats. BLMI was used to analyze spatial clustering and autocorrelation patterns between ecological risk and environmental factors, pinpointing areas that require targeted interventions. Additionally, redundancy analysis revealed the dynamics of heavy metal transfer to crops. This detailed approach mapped the spatial distribution of heavy metals, highlighted the ecological risks, identified their sources, and provided essential data for effective land management and pollution mitigation.

Health Risk Assessment of Heavy Metals in Agricultural Soils Based on Multi-Receptor Modeling Combined with Monte Carlo Simulation

The spatial characteristics, pollution sources, and risks of soil heavy metals were analyzed on Hainan Island. The results showed that the heavily polluted points accounted for 0.56%, and the number of mildly and above polluted points accounted for 15.27%, respectively, which were mainly distributed in the northern part of the study area. The principal component analysis-absolute principal component score-multiple linear regression (APCS-MLR) and the positive matrix factorization (PMF) revealed four sources of heavy metals: agricultural pollution sources for cadmium, (Cd), industrial and mining pollution sources for arsenic, (As), transportation pollution sources for zinc and lead (Zn and Pb), and natural pollution sources for chromium, nickel, and copper (Cr, Ni, and Cu). The human health risk assessment indicated that the average non-carcinogenic risk (HI) for both adults and children was within the safe threshold (<1), whereas Cr and Ni posed a carcinogenic risk (CR) to human health. In addition, the total non-carcinogenic risk (THI) indicated that heavy metals posed a potential non-carcinogenic risk to children, while the total carcinogenic risk (TCR) remained relatively high, mainly in the northern part of the study area. The results of the Monte Carlo simulation showed that the non-carcinogenic risk (HI) for all heavy metals was <1, but the total non-carcinogenic risk index (THI) for children was >1, indicating a potential health risk above the safe threshold. Meanwhile, nearly 100% and 99.94% of the TCR values exceeded 1 × 10-4 for children and adults, indicating that Cr and Ni are priority heavy metals for control. The research results provide the necessary scientific basis for the prevention and control of heavy metals in agricultural soils.

Development and application of machine learning models for prediction of soil available cadmium based on soil properties and climate features

Identifying the key influencing factors in soil available cadmium (Cd) is crucial for preventing the Cd accumulation in the food chain. However, current experimental methods and traditional prediction models for assessing available Cd are time-consuming and ineffective. In this study, machine learning (ML) models were developed to investigate the intricate interactions among soil properties, climate features, and available Cd, aiming to identify the key influencing factors. The optimal model was obtained through a combination of stratified sampling, Bayesian optimization, and 10-fold cross-validation. It was further explained through the utilization of permutation feature importance, 2D partial dependence plot, and 3D interaction plot. The findings revealed that pH, surface pressure, sensible heat net flux and organic matter content significantly influenced the Cd accumulation in the soil. By utilizing historical soil surveys and climate change data from China, this study predicted the spatial distribution trend of available Cd in the Chinese region, highlighting the primary areas with heightened Cd activity. These areas were primarily located in the eastern, southern, central, and northeastern China. This study introduces a novel methodology for comprehending the process of available Cd accumulation in soil. Furthermore, it provides recommendations and directions for the remediation and control of soil Cd pollution.

Tracking the impact of heavy metals on human health and ecological environments in complex coastal aquifers using improved machine learning optimization

The rising heavy metal (HM) pollution in coastal aquifers in rapidly urbanizing areas such as Dammam leads to significant risks to public health and environmental sustainability, challenging compliance with Environmental Protection Agency (EPA) guidelines, World Health Organization (WHO) standards, and Sustainable Development Goals (SDGs) related to clean water and life on land. This study developed the predictive-based monitoring of HM concentrations, including cadmium (Cd), chromium (Cr), and mercury (Hg) in the coastal aquifers of Dammam, influenced by industrial, agricultural, and urban activities. For this purpose, dynamic system identification and machine learning (ML) models integrated with three ensemble techniques, namely, simple averaging (SAE), weighted averaging (WAE), and neuro-ensemble (N-ESB), were employed to enhance the accuracy, reliability, and efficiency of environmental monitoring systems. The experimental data were calibrated and validated in addition to k-fold cross-validation to ensure the predictive skills of the models. The methodology integrates extensive data collection across varied land uses in Dammam and accurate model calibration and validation phases to develop highly accurate predictive models. The findings proved that the N-ESB and Hammerstein-Wiener (HW) models surpassed other models in predicting the concentrations of all HM. For Cd, the N-ESB model achieved a root mean square error (RMSE = 0.0010 mg/kg). Similarly, Cr demonstrated superior performance (RMSE = 0.0179 mg/kg). Further numerical results indicated that the HW algorithm proved the most effective for Hg, with RMSE = 0.0000 mg/kg. The quantitative comparison suggested that the N-ESB model's consistently high performance and low error rates make it an optimal choice for real-time, precise monitoring and management of HM pollution in coastal aquifers. The outcomes of this research highlighted the importance of integrating advanced predictive modeling techniques in environmental science, providing significant and practical implications for policymaking and ecological management.

A novel prediction approach driven by graph representation learning for heavy metal concentrations

The potential risk of heavy metals (HMs) to public health is an issue of great concern. Early prediction is an effective means to reduce the accumulation of HMs. The current prediction methods rarely take internal correlations between environmental factors into consideration, which negatively affects the accuracy of the prediction model and the interpretability of intrinsic mechanisms. Graph representation learning (GraRL) can simultaneously learn the attribute relationships between environmental factors and graph structural information. Herein, we developed the GraRL-HM method to predict the HM concentrations in soil-rice systems. The method consists of two modules, which are PeTPG and GCN-HM. In PeTPG, a graphic structure was generated using graph representation and communitization technology to explore the correlations and transmission paths of different environmental factors. Subsequently, the GCN-HM model based on the graph convolutional neural network (GCN) was used to predict the HM concentrations. The GraRL-HM method was validated by 2295 sets of data covering 21 environmental factors. The results indicated that the PeTPG model simplified correlation paths between factor nodes from 396 to 184, reducing by 53.5 % graph scale by eliminating the invalid paths. The concise and efficient graph structure enhanced the learning efficiency and representation accuracy of downstream prediction models. The GCN-HM model was superior to the four benchmark models in predicting the HM concentration in the crop, improving R2 by 36.1 %. This study develops a novel approach to improve the prediction accuracy of pollutant accumulation and provides valuable insights into intelligent regulation and planting guidance for heavy metal pollution control.

Theoretical assessment of influential factors and application in chlorinated hydrocarbon detection with membrane interface probe

The membrane interface probe (MIP) is an efficient and economical in-situ tool for chlorinated hydrocarbon (CH) contaminated site investigation. Given that the interpretation of MIP test is currently limited to a qualitative level, a theoretical model considering multiphase flow and multifield coupling is firstly proposed to simulate MIP test process. This model can consider phase change, membrane effect, adsorption and dissolution of the CH liquid, gas diffusion, and evaporation. Then, the model is used to study the changes in soil temperature and soil CH concentration during MIP test, as well as the influences of soil CH concentration and soil properties (initial water saturation, soil intrinsic permeability, and thermal properties) on MIP response. Finally, a simplified MIP interpretation model is developed based on parametric analysis results and verified against field and laboratory test data. It is found that the soil CH concentration, rather than soil properties, dominates the MIP response. The simplified interpretation model can deliver practical prediction of the CH concentration through the detected results by MIP, which may improve the applicability of MIP.

Global prevalence of microplastics in tap water systems: Abundance, characteristics, drivers and knowledge gaps

Tap water is a main route for human direct exposure to microplastics (MPs). This study recompiled baseline data from 34 countries to assess the current status and drivers of MP contamination in global tap water systems (TWS). It was shown that MPs were detected in 87 % of 1148 samples, suggesting the widespread occurrence of MPs in TWS. The detected concentrations of MPs spanned seven orders of magnitude and followed the linearized log-normal distribution (MSE = 0.035, R2 = 0.965), with cumulative concentrations at 5th, 50th and 95th percentiles of 0.028, 4.491 and 728.105 items/L, respectively. The morphological characteristics were further investigated, indicating that particles smaller than 50 μm dominated in global TWS, with fragment, polyester and transparent as the most common shape, composition and color of MPs, respectively. Subsequently, the SHapley Additive exPlanations (SHAP) algorithm was implemented to quantify the importance of variables affecting the MP abundance in global TWS, showing that the lower particle size limit was the most important variables. Subgroup analysis revealed that the concentration of MPs counted at the size limit of 1 μm was >20 times higher than that above 1 μm. Ultimately, current knowledge gaps and future research needs were elucidated.

Controlling factors of heavy metal(loid) accumulation in rice: Main and interactive effects

Identifying the key determinants of heavy metal(loid) accumulation in rice and quantifying their contributions are critical for precise prediction of heavy metal(loid) concentrations in rice and the formulation of effective pollution control strategies. The accumulation of heavy metal(loid)s in rice can be influenced by both natural and anthropogenic factors, which may interact with each other. However, distinguishing the independent roles (main effects) from interactive effects and quantifying their impacts separately pose challenges. To address this knowledge gap, we employed TreeExplainer-based SHAP and random forest algorithms in this study to quantitatively estimate the primary influencing factors and their main and interactive effects on heavy metal(loid)s in rice. Our findings reveal that soil cadmium (SCd) and rice cultivation time (C_TIME) were the primary contributors to rice cadmium (RCd) and rice arsenic (RAs), respectively. Soil lead (SPb) and sampling distances from roads significantly contributed to rice lead (RPb). Additionally, we identified significant interactive effects of SCd and C_TIME, C_TIME and RCd, and RCd and rice variety on RCd, RAs, and RPb, respectively, emphasizing their significance. These insights are pivotal in improving the accuracy of heavy metal(loid) concentration predictions in rice and offering theoretical guidance for the formulation of pollution control measures.

Effects of remediation agents on rice and soil in toxic metal(loid)s contaminated paddy fields: A global meta-analysis

Toxic metal(loid)s contamination of paddy soil is a nonnegligible issue and threatens food safety considering that it is transmitted via the soil-plant system. Applying remediation agents could effectively inhibit the soil available toxic metal(loid)s and reduce their accumulation in rice. To comprehensively quantify how remediation agents impact the accumulation of Cd/Pb/As in rice, rice growth and yield, the accumulation of available Cd/Pb/As in paddy soil, and soil characteristics, 50 peer-reviewed publications were selected for meta-analysis. Overall, the application of remediation agents exhibited significant positive effects on rice plant length (ES = 0.05, CI = 0.01-0.08), yield (ES = 0.20, CI = 0.13-0.27), peroxidase (ES = 0.56, CI = 0.18-0.31), photosynthetic rate (ES = 0.47, CI = 0.34-0.61), and respiration rate (ES = 0.68, CI = 0.47-0.88). Among the different types of remediation agents, biochar was the most effective in controlling the accumulation of Cd/Pb/As in all portions of rice, and was also superior in inhibiting the accumulation of Pb in rice grains (ES = -0.59, 95 % CI = -1.04-0.13). This study offers an essential contribution for the remediation strategies of toxic metal(loid)s contaminated paddy fields.

Deciphering silver nanoparticles perturbation effects and risks for soil enzymes worldwide: Insights from machine learning and soil property integration

Globally extensive research into how silver nanoparticles (AgNPs) affect enzyme activity in soils with differing properties has been limited by cost-prohibitive sampling. In this study, customized machine learning (ML) was used to extract data patterns from complex research, with a hit rate of Random Forest > Multiple Imputation by Chained Equations > Decision Tree > K-Nearest Neighbors. Results showed that soil properties played a pivotal role in determining AgNPs' effect on soil enzymes, with the order being pH > organic matter (OM) > soil texture ≈ cation exchange capacity (CEC). Notably, soil enzyme activity was more sensitive to AgNPs in acidic soil (pH < 5.5), while elevated OM content (>1.9 %) attenuated AgNPs toxicity. Compared to soil acidification, reducing soil OM content is more detrimental in exacerbating AgNPs' toxicity and it emerged that clay particles were deemed effective in curbing their toxicity. Meanwhile sand particles played a very different role, and a sandy soil sample at > 40 % of the water holding capacity (WHC), amplified the toxicity of AgNPs. Perturbation mapping of how soil texture alters enzyme activity under AgNPs exposure was generated, where soils with sand (45-65 %), silt (< 22 %), and clay (35-55 %) exhibited even higher probability of positive effects of AgNPs. The average calculation results indicate the sandy clay loam (75.6 %), clay (74.8 %), silt clay (65.8 %), and sandy clay (55.9 %) texture soil demonstrate less AgNPs inhibition effect. The results herein advance the prediction of the effect of AgNPs on soil enzymes globally and determine the soil types that are more sensitive to AgNPs worldwide.

Prediction of heavy metal removal performance of sulfate-reducing bacteria using machine learning

A robust modeling approach for predicting heavy metal removal by sulfate-reducing bacteria (SRB) is currently missing. In this study, four machine learning models were constructed and compared to predict the removal of Cd, Cu, Pb, and Zn as individual ions by SRB. The CatBoost model exhibited the best predictive performance across the four subsets, achieving R2 values of 0.83, 0.91, 0.92, and 0.83 for the Cd, Cu, Pb, and Zn models, respectively. Feature analysis revealed that temperature, pH, sulfate concentration, and C/S (the mass ratio of chemical oxygen demand to sulfate) had significant impacts on the outcomes. These features exhibited the most effective metal removal at 35 °C and sulfate concentrations of 1000-1200 mg/L, with variations observed in pH and C/S ratios. This study introduced a new modeling approach for predicting the treatment of metal-containing wastewater by SRB, offering guidance for optimizing operational parameters in the biological sulfidogenic process.

Heavy metals prediction in coastal marine sediments using hybridized machine learning models with metaheuristic optimization algorithm

This study proposes different standalone models viz: Elman neural network (ENN), Boosted Tree algorithm (BTA), and f relevance vector machine (RVM) for modeling arsenic (As (mg/kg)) and zinc (Zn (mg/kg)) in marine sediments owing to anthropogenic activities. A heuristic algorithm based on the potential of RVM and a flower pollination algorithm (RVM-FPA) was developed to improve the prediction performance. Several evaluation indicators and graphical methods coupled with visualized cumulative probability function (CDF) were used to evaluate the accuracy of the models. Akaike (AIC) and Schwarz (SCI) information criteria based on Dickey-Fuller (ADF) and Philip Perron (PP) tests were introduced to check the reliability and stationarity of the data. The prediction performance in the verification phase indicated that RVM-M2 (PBAIS = -o.0465, MAE = 0.0335) and ENN-M2 (PBAIS = 0.0043, MAE = 0.0322) emerged as the best model for As (mg/kg) and Zn (mg/kg), respectively. In contrast with the standalone approaches, the simulated hybrid RVM-FPA proved merit and the most reliable, with a 5 % and 18 % predictive increase for As (mg/kg) and Zn (mg/kg), respectively. The study's findings validated the potential for estimating complex HMs through intelligent data-driven models and heuristic optimization. The study also generated valuable insights that can inform the decision-makers and stockholders for environmental management strategies.

Predicting Cd accumulation in rice and identifying nonlinear effects of soil nutrient elements based on machine learning methods

The spatial mismatch of Cd content in soil and rice causes difficulties in environmental management for paddy soil. To investigate the influence of soil environment on the accumulation of Cd in rice grain, we conducted a paired field sampling in the middle of the Xiangjiang River basin, examining the relationships between soil properties, soil nutrient elements, Cd content, plant uptake factor (PUFCd), and translocation factors in different rice organs (root, shoot, and grain). The total soil Cd (CdT) and available Cd (CdA) contents and PUFCd showed large spatial variability with ranges of 0.31-6.19 mg/kg, 0.03-3.07 mg/kg, and 0.02-3.51, respectively. Soil pH, CdT, CdA, and the contents of soil nutrient elements (Mg, Mn, Ca, P, Si, and B) were linearly correlated with grain Cd content (Cdg) and PUFCd. The decision tree analysis identified nonlinear effects of Si, Zn and Fe on rice Cd accumulation, which suggested that low Si and high Zn led to high Cdg, and low Si and Fe caused high PUFCd. Using the soil nutrient elements as predictor variables, random forest models successfully predicted the Cdg and PUFCd and performed better than multiple linear regressions. It suggested the impacts of soil nutrient elements on rice Cd accumulation should receive more attention.

Influence of landform, soil properties, soil Cd pollution and rainfall on the spatial variation of Cd in rice: Contribution and pathway models based on big data

Landform, soil properties, soil cadmium (Cd) pollution and rainfall are the important factors affecting the spatial variation of rice Cd. In this study, we conducted big data mining and model analysis of 150,000 rice-soil sampling sites to examine the effects by the above four factors on the spatial variation of rice Cd in Hunan Province, China. Specifically, the variable coefficient of rice Cd in space was significantly correlated with the partition scale according to the logistic fitting. The improved random forest results suggested that elevation (DEM) and pH were the two most important factors affecting the spatial variation of rice Cd, followed by relief, soil Cd content and rainfall. Typically, variance partitioning analysis (VPA) revealed that both the soil property and the interactive effects between the soil property and Cd pollution were the principal contributors to the rice-Cd variation, with the respective contributing rates of 30.5 % and 29.0 %. Meanwhile, the partial least square-structural equation modelling (PLS-SEM) elucidated 4 main paths of specific indirect effects on rice-Cd variation. They were landform → physicochemical property → soil acidity → rice-Cd variation, landform → soil acidity → rice-Cd variation, physicochemical property → soil acidity → rice-Cd variation, and soil texture → soil acidity → rice-Cd variation. This work can provide a general guidance for scientific zoning, accurate prediction and prevention of Cd pollution in paddy fields.

Spatial and variety distributions, risk assessment, and prediction model for heavy metals in rice grains in China

In this study, 6229 brown rice grains from three major rice-producing regions were collected to investigate the spatial and variety distributions of heavy metals in rice grains in China. The potential sources of heavy metals in rice grains were identified using the Pearson correlation matrix and principal component analysis, and the health risks of dietary exposure to heavy metals via rice consumption were assessed using the hazard index (HI) and total carcinogenic risk (TCR) method, respectively. Moreover, 48 paired soil and rice samples from 11 cities were collected to construct a predicting model for Cd accumulation in rice grains using the multiple linear stepwise regression analysis. The results indicated that Cd and Ni were the main heavy metal pollutants in rice grains in China, with approximately 10% of samples exceeding their corresponding maximum allowable limits. The Yangtze River basin had heavier pollution of heavy metals than the Southeast Coastal Region and Northeast Plain, and the indica rice varieties had higher heavy metal accumulation abilities compared with the japonica rice. The Cu, Pb, and Cd mainly originated from anthropogenic sources, while As, Hg, Cr, and Ni originated from both natural and anthropogenic sources. The mean HI and TCR values of dietary exposure to heavy metals via rice consumption ranged from 2.92 to 4.31 and 9.74 × 10-3 to 1.44 × 10-2, respectively, much higher than the acceptable range, and As and Ni were the main contributor to the HI and TCR for Chinese adults and children, respectively. The available Si (ASi), total Cd (TCd), available Mo (AMo), and available S (AS) were the main soil factors determining grain Cd accumulation. A multiple linear stepwise regression model was constructed based on ASi, TCd, AMo, and AS in soils with good accuracy and precision, which could be applied to predict Cd accumulation in rice grains and guide safe rice production in contaminated paddy fields.

Prediction of cadmium contents in rice grains from Quaternary sediment-distributed farmland using field investigations and machine learning

The Quaternary sediment-distributed regions of South China are suitable for rice cultivation, which is crucial for ensuring food security. Spatial correlations between soil cadmium (Cd) and rice Cd contents are generally poor, making the evaluation of rice quality and associated health risks challenging. In this study, we developed machine learning algorithms for predicting rice Cd contents using 654 data pairs of soil-rice samples collected in Guangxi province, China. After a comprehensive comparison, our results showed that the random forest (RF) had the better performance than artificial neural network (ANN) based on all the data (RMSEtesting 0.066 vs. 0.099 and R2testing 0.860 vs. 0.688). The feature importance analysis showed that soil CaO, Cd, elevation, and rainfall were the four most important features affecting the rice Cd contents in the study area. Using the established RF-predicated model, the rice Cd contents were predicted at the provincial level with an additional dataset of 1176 paddy soil samples. The prediction result revealed about 23 % of farmland cultivated rice with Cd content over 0.2 mg kg-1 in the study area. Therefore, it is recommended to implement strict measures by local agricultural departments to reduce rice Cd contents and ensure food safety in these areas. Our study provides valuable insights into the prediction of rice Cd contents, thus contributing to ensuring food safety and preventing Cd exposure-associated health risks.

Carbonate rocks as natural buffers: Exploring their environmental impact on heavy metals in sulfide deposits

Carbonate rocks are closely related to the genesis and spatial distribution of polymetallic sulfide deposits. The natural buffering of carbonate rocks can reduce the ecological impact of heavy metals produced by mining and smelting. Ignoring the buffering effect of carbonate rocks on the heavy metals in the mine environment leads to inaccurate ecological risk assessment, wasting land resources and funds. This study investigates Cd, Zn, and Pb distribution and speciation in the water and soil-rice system in the polymetallic sulfide deposit at Daxin, Guangxi. The study aims to reveal the effects of the natural buffering of carbonate rocks on the migration and transformation of heavy metals. The results show that the water Zn and Cd concentrations decreased from 1857.0 to 0.9 mg L-1 to 0.16 and 0.001 mg L-1, respectively, from the mining area to 4 km downstream. The natural buffering of carbonate increases the water pH from 2.80 to 7.64, resulting in a tendency for Cd, Zn, and Pb to separate from the aqueous phase and enrich the sediments. Soil Cd content in the mining area reached 110.0 mg kg-1 (mean value 55.88 mg kg-1), and rice Cd seriously exceeded the maximum limit. However, the weathering of carbonate reduces the migration ability and bioavailability of Cd. Soil Cd is mainly in the Fe-Mn bound and carbonate-bound fractions, resulting in lower Cd content in downstream soils (mean value 2.73 mg kg-1). Soil CaO, tFe2O3, and Mn hindered the uptake of soil Cd by rice rendering a lower exceedance of Cd in downstream rice. Therefore, this study recommends a farmland management plan under the premise of rice Cd content and integrated soil Cd content, which ensures food safety and fully utilizes farmland resources. This result provides a scientific basis for ecological risk assessment, mine environmental protection, and management in the carbonatite sulfide mine environment.

Machine learning: Next promising trend for microplastics study

Microplastics (MPs), as an emerging pollutant, pose a significant threat to humans and ecosystems. However, traditional MPs characterization methods are limited by sample requirements and characterization time. Machine Learning (ML) has emerged as a vital technology for analyzing MPs pollution due to its accuracy, broad application, and powerful feature extraction. Nevertheless, environmental scientists require threshold knowledge before using ML, restricting the ML application in MPs research. Furthermore, imbalanced development of ML in MPs research is a pressing concern. In order to achieve a wide ML application in MPs research, in this review, we comprehensively discussed the size and sources of MPs datasets in relevant literature to help environmental scientists deepen their understanding of the construction of MPs datasets. Commonly used ML algorithms are analyzed from the perspective of interpretability and the need for computer facilities. Additionally, methods for improving and evaluating ML model performance, such as dataset pre-processing, model optimization, and model assessment metrics, are discussed. According to datasets and characterization techniques, MPs identification using ML was divided into three categories in this work: spectral identification, image identification, and spectral imaging identification. Finally, other applications of ML in MPs studies, including toxicity analysis, pollutants adsorption, and microbial colonization, are comprehensively discussed, which reveals the great application potential of ML. Based on the discussion above, this review suggests an algorithm selection strategy to assist researchers in selecting the most suitable ML algorithm in different situations, improving efficiency and decreasing the costs of trial and error. We believe that this work sheds light on the application of ML in MPs study.

Heavy metals distribution characteristics, source analysis, and risk evaluation of soils around mines, quarries, and other special areas in a region of northwestern Yunnan, China

In this study, based on the assessment of soil heavy metals (HMs) pollution using relevant indices, a comprehensive approach combined network environ analysis (NEA), human health risk assessment (HHRA) method and positive definite matrix factor (PMF) model to quantify the risks among ecological communities in a special environment around mining area in northwest Yunnan, calculated the risk to human health caused by HMs in soil, and analyzed the pollution sources of HMs. The integrated risks for soil microorganisms, vegetations, herbivores, and carnivores were 2.336, 0.876, 0.114, and 0.082, respectively, indicating that soil microorganisms were the largest risk receptors. The total hazard indexes (HI_T) for males, females, and children were 0.542, 0.591, and 1.970, respectively, revealing a relatively high and non-negligible non-carcinogenic risks (NCR) for children. The total cancer risks (TCR) for both females and children exceeded 1.00E-04, indicating that soil HMs posed carcinogenic risks (CR) to them. Comparatively, Pb was the high-risk metal, accounting for 53.76%, 57.90%, and 68.09% of HI_T in males, females, and children, respectively. PMF analysis yielded five sources of pollution, F1 (industry), F2 (agriculture), F3 (domesticity), F4 (nature), and F5 (traffic).

Recent progress on the microbial mitigation of heavy metal stress in soybean: overview and implications

Plants are adapted to defend themselves through programming, reprogramming, and stress tolerance against numerous environmental stresses, including heavy metal toxicity. Heavy metal stress is a kind of abiotic stress that continuously reduces various crops' productivity, including soybeans. Beneficial microbes play an essential role in improving plant productivity as well as mitigating abiotic stress. The simultaneous effect of abiotic stress from heavy metals on soybeans is rarely explored. Moreover, reducing metal contamination in soybean seeds through a sustainable approach is extremely needed. The present article describes the initiation of heavy metal tolerance mediated by plant inoculation with endophytes and plant growth-promoting rhizobacteria, the identification of plant transduction pathways via sensing annotation, and contemporary changes from molecular to genomics. The results suggest that the inoculation of beneficial microbes plays a significant role in rescuing soybeans under heavy metal stress. They create a dynamic, complex interaction with plants via a cascade called plant-microbial interaction. It enhances stress metal tolerance via the production of phytohormones, gene expression, and secondary metabolites. Overall, microbial inoculation is essential in mediating plant protection responses to heavy metal stress produced by a fluctuating climate.

Improving the mapping accuracy of soil heavy metals through an adaptive multi-fidelity interpolation method

Soil heavy metal pollution poses a serious threat to environmental safety and human health. Accurately mapping the soil heavy metal distribution is a prerequisite for soil remediation and restoration at contaminated sites. To improve the accuracy of soil heavy metal mapping, this study proposed an error correction-based multi-fidelity technique to adaptively correct the biases of traditional interpolation methods. The inverse distance weighting (IDW) interpolation method was chosen and combined with the proposed technique to form the adaptive multi-fidelity interpolation framework (AMF-IDW). In AMF-IDW, sampled data were first divided into multiple data groups. Then one data group was used to build the low-fidelity interpolation model through IDW, while the other data groups were treated as high-fidelity data and used for adaptively correcting the low-fidelity model. The capability of AMF-IDW to map the soil heavy metal distribution was evaluated in both hypothetical and real-world scenarios. Results showed that AMF-IDW provided more accurate mapping results compared with IDW and the superiority of AMF-IDW became more evident as the number of adaptive corrections increased. Eventually, after using up all data groups, AMF-IDW improved the R² values for mapping results of different heavy metals by 12.35-24.32%, and decreased the RMSE values by 30.35%-42.86%, indicating a much higher level of mapping accuracy relative to IDW. The proposed adaptive multi-fidelity technique can be equally combined with other interpolation methods and provide promising potential in improving the soil pollution mapping accuracy.