Using big data searching and machine learning to predict human health risk probability from pesticide site soils in China

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.

Analysis of nationwide soil pesticide pollution: Insights from China

China is a typical agricultural country that heavily relies on pesticides. Some pesticides can remain in the soil after application and thus pose a significant threat to human health. In order to characterize the status and hazards of nationwide soil contamination, this study extracted concentration data from published literature and analyzed them by a scoring approach, standard comparison and health risk assessment. For the soil pollution score, northern regions got the highest values, such as Henan (0.63), Liaoning (0.55), Heilongjiang (0.54) and Jilin (0.53), which implies high soil pesticide residues in these provinces. In contrast, Qinghai (-0.77), Guizhou (-0.64) and Tibet (-0.63) had lower scores. China's soil pesticide standards cover only 16 pesticides, and these pesticide concentrations were all below the corresponding standards. Direct exposure to soil pesticides in this study generally posed a negligible risk to children. Furthermore, pesticide dissipation and usage intensity in each province were analyzed as they were possible influences on pollution. The result showed that soil in the northern regions could accumulate more pesticides than those in the southern regions, and this geographic pattern was basically consistent with the distribution of soil pollution. However, the relationship between agricultural activities and soil pollution was less well characterized. It is recommended to establish a long-term monitoring database for pesticides and include more pesticides in regulatory frameworks. Additionally, efforts to accelerate pesticide degradation and shift the planting structure to reduce pesticide usage can help alleviate the pressure on soil from pesticides. This study can serve as a critical reference for policymakers and stakeholders in the field of agriculture.

Regulating pathway for bacterial diversities toward improved ecological benefits of thiencarbazone-methyl·isoxaflutole application: A field experiment

Herbicide abuse has a significantly negative impact on soil microflora and further influences the ecological benefit. The regulating measures and corresponding mechanisms mitigating the decreased bacterial diversity due to herbicide use have rarely been studied. A field experiment containing the application gradient of an efficient maize herbicide thiencarbazone-methyl·isoxaflutole was performed. The relationship between soil bacterial community and thiencarbazone-methyl·isoxaflutole use was revealed. Modified attapulgite was added to explore its impacts on soil microflora under the thiencarbazone-methyl·isoxaflutole application. Based on the analytic network process-entropy weighting method-TOPSIS method model, the ecological benefit focusing on microbial responses was quantitatively estimated along with technical effectiveness and economic benefit. The results showed that the diversity indices of soil microflora, especially the Inv_Simpson index, were reduced at the recommended, 5 and 10 times the recommended dosages of thiencarbazone-methyl·isoxaflutole use. The Flavisolibacter bacteria was negatively correlated with the residues in soils based on the random forest model and correlation analysis, indicating a potential degrader of thiencarbazone-methyl·isoxaflutole residues. The structural equation model further confirmed that the high soil water content and soil pH promoted the function of Flavisolibacter bacteria, facilitated the dissipation of thiencarbazone-methyl·isoxaflutole residues and further improved the diversity of soil microflora. In addition, the presence of modified attapulgite was found to increase the soil pH, which may improve bacterial diversity through the regulating pathway. This explained the high ecological benefits of the treatment where the thiencarbazone-methyl·isoxaflutole was applied at the recommended dosage rates in conjunction with modified attapulgite addition. Therefore, the comprehensive benefits of thiencarbazone-methyl·isoxaflutole application with a focus on ecological benefits can be improved by regulating the soil pH with modified attapulgite.

Spatiotemporal assessment and scenario simulation of the risk potential of industrial sites at the regional scale

Spatiotemporal risk and future evolutionary distribution characteristics of industrial sites are crucial for regional environmental supervision. However, traditional site survey methods have long cycles, high costs, and small coverage and usually only consider the static risk of a single industrial site to a single receptor. Low-cost, large-scale, and long-term multi-source data can compensate for the shortcomings of traditional site surveys. Previous studies have rarely considered the spatiotemporal heterogeneity of industrial sites and assessed their dynamic risks at the regional scale. This study used China's Yangtze River Delta Urban Agglomeration as the study area. We assessed the risk potential of industrial sites from 2000 to 2020 using multi-source and multiperiod data. We also simulated the risk potential for 2030 and 2050 using a patch-generating land use simulation (PLUS) model under different scenarios. The results indicated that the proportion of medium- and high-risk potential grids from 2000 to 2020 ranged from 2.53 % to 5.61 % in the study area, with the vast majority of areas (94.39 %-97.47 %) having low- or no-risk potential. The PLUS model exhibited remarkable reliability from 2005 to 2020, with the overall accuracy, Kappa coefficient, and Moran's index ranging from 83 % to 89 %, 0.38 to 0.59, and 0.34 to 0.56, respectively. The future prediction results indicated that the number of high-risk potential grids (>5 %) showed an upward trend under natural development scenarios in 2030 and 2050 and a downward trend under the ten-chapter soil pollution action plan or strict control scenarios. This study provides vital information for addressing the challenges of industrial site management and environmental risks in similar regions.

Identifying multiple soil pollutions of potentially contaminated sites based on multi-gate mixture-of-experts network

With the rapid increase in the amount and sources of big data, using big data and machine learning methods to identify site soil pollution has become a research hotspot. However, previous studies that used basic information of sites as pollution identification indexes mainly have problems of low accuracy and efficiency when conducting complex model predictions for multiple soil pollution types. In this study, we collected the environmental data of 199 sites in 6 typical industries involving heavy metal and organic pollution. After feature fusion and selection, 10 indexes based on pollution sources and pathways were used to establish the soil pollution identification index system. The Multi-gate Mixture-of-Experts network (MMoE) were constructed to carry out the multi-tasks of soil heavy metals, VOCs and SVOCs pollution identification simultaneously. The SHAP framework was used to reveal the importance of pollution identification indexes on the multiple outputs of MMoE and obtain their driving factors. The results showed that the accuracies of MMoE model were 0.600, 0.783 and 0.850 for soil heavy metals, VOCs and SVOCs pollution identifications, respectively, which were 0-20 % higher than their accuracies of BP neural networks of single tasks. The indexes of raw material containing organic compounds, enterprise scale, soil pollution traces and industry types have the different significant importance on site soil pollutions. This study proposed a more efficient and accurate method to identify site soil pollutions and their driving factors, which offers a step towards realizing intelligent identification and risk control of site soil pollution globally.

Feature fusion improves performance and interpretability of machine learning models in identifying soil pollution of potentially contaminated sites

Owing to the rapid development of big data technology, use of machine learning methods to identify soil pollution of potentially contaminated sites (PCS) at regional scales and in different industries has become a research hot spot. However, due to the difficulty in obtaining key indexes of site pollution sources and pathways, current methods have problems such as low accuracy of model predictions and insufficient scientific basis. In this study, we collected the environmental data of 199 PCS in 6 typical industries involving heavy metal and organic pollution. Then, 21 indexes based on basic information, potential for pollution from product and raw material, pollution control level, and migration capacity of soil pollutants were used to established the soil pollution identification index system. We fused the original indexes into the new feature subset with 11 indexes through the method of consolidation calculation. The new feature subset was then used to train machine learning models of random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP), and tested to determine whether it improved the accuracy and precision of soil pollination identification models. The results of correlation analysis showed that the four new indexes created by feature fusion have the correlation with soil pollution is similar to the original indexes. The accuracies and precisions of three machine learning models trained on the new feature subset were 67.4%- 72.9% and 72.0%- 74.7%, which were 2.1%- 2.5% and 0.3%- 5.7% higher than these of the models trained on original indexes, respectively. When the PCS were divided into typical heavy metal and organic pollution sites according to the enterprise industries, the accuracy of the model trained on the two datasets for identifying soil heavy metal and organic pollution were significantly improve to approximately 80%. Owing to the imbalance in positive and negative samples in the prediction of soil organic pollution, the precisions of soil organic pollution identification models were 58%- 72.5%, which were significantly lower than their accuracies. According to the factors analysis based on the model interpretability of SHAP, most of the indexes of basic information, potential for pollution from product and raw material, and pollution control level had different degrees of impact on soil pollution. However, the indexes of migration capacity of soil pollutants had the least effect in the classification task of soil pollution identification of PCS. Among the indexes, traces of soil pollution, industrial utilization years/start-up time, pollution control risk scores and enterprise scale having the greatest effects on soil pollution with the mean SHAP values of 0.17-0.36, which reflected their contribution rate on soil pollution and could help to optimize the current index scoring of the technical regulation for identifying site soil pollution. This study provides a new technical method to identify soil pollution based on big data and machine learning methods, in addition to providing a reference and scientific basis for environmental management and soil pollution control of PCS.

Screening priority pesticides for drinking water quality regulation and monitoring by machine learning: Analysis of factors affecting detectability

Proper selection of new contaminants to be regulated or monitored prior to implementation is an important issue for regulators and water supply utilities. Herein, we constructed and evaluated machine learning models for predicting the detectability (detection/non-detection) of pesticides in surface water as drinking water sources. Classification and regression models were constructed for Random Forest, XGBoost, and LightGBM, respectively; of these, the LightGBM classification model had the highest prediction accuracy. Furthermore, its prediction performance was superior in all aspects of Recall, Precision, and F-measure compared to the detectability index method, which is based on runoff models from previous studies. Regardless of the type of machine learning model, the number of annual measurements, sales quantity of pesticide for rice-paddy field, and water quality guideline values were the most important model features (explanatory variables). Analysis of the impact of the features suggested the presence of a threshold (or range), above which the detectability increased. In addition, if a feature (e.g., quantity of pesticide sales) acted to increase the likelihood of detection beyond a threshold value, other features also synergistically affected detectability. Proportion of false positives and negatives varied depending on the features used. The superiority of the machine learning models is their ability to represent nonlinear and complex relationships between features and pesticide detectability that cannot be represented by existing risk scoring methods.