Discriminative algorithm approach to forecast Cd threshold exceedance probability for rice grain based on soil characteristics

Bayesian risk prediction model: An accessible strategy to predict cadmium contamination risk in wheat grain grown in alkaline soils

Excessive cadmium (Cd) concentration in wheat grain is becoming a widespread concern in China. Considering the complexity of Cd transfer in the soil-wheat system, how the Cd risk in wheat grain be accurately predicted from the limited details available is of great significance for the risk management of Cd. Bayes' theory could leverage existing data by combining prior information and observational data, providing a promising strategy with which to calculate a more robust posterior probability of a grain sample exceeding the food safety standard (FSS) for Cd (0.1 mg kg-1). In the current study, a risk prediction model, based on Bayes' theory, was established to achieve a more accurate prediction of the wheat grain Cd risk from a limited number of soil parameters. The risk prediction model could predict the risk probability of wheat grain with a Cd concentration exceeding the FSS under a given soil concentration of either total Cd or diethylenetriaminepentaacetic acid (DTPA)-extractable Cd. Soil total Cd concentration proved to be a better variable for the model with greater predictive accuracy. The model predicted that fewer than 5% of the wheat grain would have a Cd concentration exceeding the FSS when grown in soil with a total Cd concentration of less than 0.299 mg kg-1. The risk probability rose significantly to 50% when the soil total Cd reached 0.778 mg kg-1. The accuracy of the model was greater than the widely applied multiple linear regression model, whereas previously published data from similar soil conditions also confirmed that the Bayesian model could predict wheat Cd risk with minimal error. The proposed model provides an accurate, accessible and cost-effective methodology for predicting Cd risk in wheat grown in alkaline soils before harvest. The wider application to other soil conditions, crops or contaminants using the Bayesian model is also promising for risk management authorities.

Accurate derivation and modelling of criteria of soil extractable and total cadmium for safe wheat production

It is significant to establish an accurate model to predict cadmium (Cd) criteria for safe wheat production. More importantly, for better evaluation of the risk of Cd pollution in high natural background areas, the soil extractable Cd criteria are needed. In the present study, the soil total Cd criteria were derived using the method of cultivars sensitivity distribution integrated with soil aging and bioavailability as affected by soil properties. Firstly, the dataset that meet the requirements was established. Dataset from thirty-five wheat cultivars planted in different soils published in literature of five bibliographic databases were screened using designated search strings. Then, the empirical soil-plant transfer model was used to normalize the bioaccumulation data. Afterwards, the soil Cd concentration for protecting 95 % (HC₅) of the species was calculated from species sensitivity distribution curves, and the derived soil criteria were obtained from HC₅ prediction models that based on pH. The process of derivation for soil EDTA-extractable Cd criteria was the same way as the soil total Cd criteria. Soil total Cd criteria ranged from 0.25 to 0.60 mg/kg and soil EDTA-extractable Cd criteria ranged from 0.12 to 0.30 mg/kg. Both the criteria of soil total Cd and soil EDTA-extractable Cd were further validated to be reliable using data from field experiments. The results suggested that the criteria of soil total Cd and soil EDTA-extractable Cd in the study can ensure the safety of Cd in wheat grains and thereby enable local agricultural practitioners to develop appropriate management for croplands.

Prediction of cadmium bioavailability in the rice-soil system on a county scale based on the multi-surface speciation model

Relative to total cadmium (Cd) content, bioavailable Cd in paddy soil is regarded as a more reasonable indicator for the risk of Cd bioaccumulation in rice. However, there is still a lack of approach to accurately predict the content of bioavailable Cd in paddy soil due to its heterogeneity and complexity. Here, multi-surface speciation model (MSM) was employed to predict the bioavailable Cd and Cd immobilization effect. Moreover, a precise remediation strategy was designed based on screening and scenario simulation of the sensitive factors with MSM. The results demonstrated that MSM can well predict Cd bioaccumulation risk in rice. The contribution of pH to Cd bioavailability was quantified under three analysis scenarios, accounting for 87.51% of the total variance of bioavailable Cd. In addition, the pH alert value (6.31 ± 0.52) for Cd risk was acquired for each rice field on a county scale. A precise map for the application amount of lime materials was constructed by taking CaCO₃ (3.38-15.75 t ha^-1) as a recommended economical and green immobilization agent. This study provides a potentially effective approach for risk assessment of Cd contamination in rice and important reference for precise Cd remediation in paddy soil.

Chain modeling for the biogeochemical nexus of cadmium in soil-rice-human health system

This paper presents a novel chain model named soil-food-human (SFH) for clarifying the biogeochemical cascades among the triple challenges of cadmium contamination, food safety, and related public health effect. The model was developed based on the integration of spatial distribution pattern of soil environment and the biogeochemical process of cadmium in soil-rice-human health, and it was validated through a case study. In soil environment terms, SFH predicted the spatial distribution of soil properties with an average prediction accuracy of 82.28%. In food production terms, the SFH can identify the safe production zones for planting rice and unsafe area for adjusting croppingsystems with a relative error of 39.41%. In food consumption terms, SFH mapped the high-resolution map of cadmium exposure dose, which gives a new solution to assess the food safety risks for self-sufficient populations. For the health effect of rice cadmium exposure, SFH simulated the spatiotemporal pattern of urinary cadmium based on toxicokinetic which revealed the health effect of rice cadmium exposure. The chain model provides a new insight in understanding the biogeochemical cascades between food production, food safety, and public health, making it possible to develop a comprehensive strategy to tackle cadmium pollution in soil-rice-human health system.

Transforming approach for assessing the performance and applicability of rice arsenic contamination forecasting models based on regression and probability methods

Probability models are preferred over regression models recently in contamination evaluation but lacking proper performance comparison between two model types. Linear regression, logistic regression, XGBoost-based regression, and probability models were built considering soil arsenic and certain soil physicochemical properties of 287 samples to predict arsenic in rice grains. The outputs of all models were binarily classified uniformly for comparison. The complex algorithm-based models--XGBoost-based regression (R² =0.046 ± 0.036) and probability models (cross-entropy = 0.697 ± 0.020)-did not surpass the simple linear regression (R² =0.046 ± 0.031) and logistic regression models (cross-entropy = 0.694 ± 0.021). Accuracy, sensitivity, specificity, precision, and F1 score showed that the probability models exhibit no advantage on regression models, although the indicators above did not serve as proper scoring rules for the probability model. When discretizing the contaminant concentration in grains for probabilistic modeling, the limit concentration was considered as the splitting point but not the structure of the datasets, which would reduce the inherent advantage of the probability model. When predicting the contamination of crops, the probability model cannot eliminate the regression model, and simple but robust algorithm-based models are preferred when the quality and quantity of the dataset are undesirable.

Modeling the spatial relationship between rice cadmium and soil properties at a regional scale considering confounding effects and spatial heterogeneity

Most previous studies have indicated inconsistent relationships between rice cadmium (Cd) and the soil properties of paddy fields at a regional scale under the adverse effects of confounding factors and spatial heterogeneity. In order to reduce these effects, this study integrates Geodetector, a stepwise regression model, and a hierarchical Bayesian method (collectively called GDSH). The GDSH framework is validated in a large typical rice production area in southeastern China. According to the results, significant stratified heterogeneity of the bioaccumulation factor is observed among different subregions and pH strata (q = 0.23, p < 0.01). Additionally, the soil-rice relationships and dominant factors vary by the subregions, and the available soil Cd and pH are found to be the dominant factors in 64% and 50% of subregions, respectively. In the entire region, when the pH < 6, the dominant factors are organic matter and available Cd, and when pH ≥ 6 they are organic matter, pH, and available Cd. Furthermore, these factors presented different sensitivity to the spatial heterogeneity. The results indicate that, at the subregional level, the GDSH framework can reduce the confounding effects and accurately identify the dominant factors of rice Cd. At the regional level, this model can evaluate the sensitivity of the dominant factors to spatial heterogeneity in a large area. This study provides a new scheme for the complete utilization of regional field survey data, which is conducive to formulating precise pollution control strategies.