Biochar is crucial for agricultural output and plays a significant role in effectively eliminating heavy metals (HMs) from the soil, which is essential for maintaining a soil–plant environment. This work aimed to assess machine learning models to analyze the impact of soil parameters on the transformation of HMs in biochar–soil–plant environments, considering the intricate non-linear relationships involved. A total of 211 datasets from pot or field experiments were evaluated. Fourteen factors were taken into account to assess the efficiency and bioavailability of HM–biochar amendment immobilization. Four predictive models, namely linear regression (LR), partial least squares (PLS), support vector regression (SVR), and random forest (RF), were compared to predict the immobilization efficiency of biochar-HM. The findings revealed that the RF model was created using 5-fold cross-validation, which exhibited a more reliable prediction performance. The results indicated that soil features accounted for 79.7% of the absorption of HM by crops, followed by biochar properties at 17.1% and crop properties at 3.2%. The main elements that influenced the result have been determined as the characteristics of the soil (including the presence of different HM species and the amount of clay) and the quantity and attributes of the biochar (such as the temperature at which it was produced by pyrolysis). Furthermore, the RF model was further developed to predict bioaccumulation factors (BAF) and variations in crop uptake (CCU). The R² values were found to be 0.7338 and 0.6997, respectively. Thus, machine learning (ML) models could be useful in understanding the behavior of HMs in soil–plant ecosystems by employing biochar additions.

Three successive vegetable pot experiments were conducted to assess the effects on the long-term immobilization of heavy metals in soil and crop yield improvement after the addition of peanut shell biochar and an alkaline mineral to an acidic soil contaminated with lead and cadmium. Compared with the CK treatment, the change rates of biomass in the edible parts of the three types of vegetables treated with B0.3, B1, B3, B9, R0.2 and B1R0.2 were −15.43%~123.30%, 35.10%~269.09%, 40.77%~929.31%, −26.08%~711.99%, 44.14%~1067.12% and 53.09%~1139.06%, respectively. The cadmium contents in the edible parts of the three vegetables treated with these six additives reduced by 2.08%~13.21%, 9.56%~24.78%, 9.96%~35.61%, 41.96%~78.42%, −4.19%~57.07% and 12.43%~65.92%, respectively, while the lead contents in the edible parts reduced by −15.70%~59.47%, 6.55%~70.75%, 3.40%~80.10%, 55.26%~89.79%, 11.05%~70.15% and 50.35%~79.25%, respectively. Due to the increases in soil pH, soil cation-exchange capacity and soil organic carbon content, the accumulation of Cd and Pb in the vegetables was most notably reduced with a high dosage of 9% peanut shell biochar alone, followed by the addition of a low dosage of 1% peanut shell biochar blended with 0.2% alkaline mineral. Therefore, the addition of a low dosage of 1% peanut shell biochar blended with 0.2% alkaline mineral was the best additive in increasing the vegetable biomass, whereas the addition of 9% peanut shell biochar alone was the worst. Evidently, the addition of 0.2% alkaline mineral can significantly reduce the amount of peanut shell needed for passivating heavy metals in soil, while it also achieves the effect of increasing the vegetable yield.

Sorption is the most important process influencing the amount of herbicide retained in soils. The special properties of biochar could influence the soil retention of pollutants through adsorption. However, the detailed sorption mechanisms as influenced before and after applying biochar to soils with different properties are unclear. This study examined the sorption characteristics of metolachlor using soil samples collected from South China. Sorption experiments were conducted using a batch equilibration method. After comparing the metolachlor sorption constants observed for all soil samples, our results showed that the application of biochar significantly increased the capacity of metolachlor adsorption. Without biochar, sorption capacity (K_f) was positively related to soil organic matter and to a soil particle size of 0.002–0.02 mm in soils developed from granite, of 0.002–0.02 mm in soils developed from delta shockwaves, and of 0.002–0.02 mm, together with complex iron oxide and total iron content, in soils developed from arenaceous shale. Moreover, sorption capacity (K_f) with biochar was positively related to peroxidase in soils developed from granite and to dissociative iron oxide and total iron content in soils developed from arenaceous shale. Our results show that biochar greatly affects metolachlor sorption behavior, probably because of qualitative differences in the structural characteristics of soils with different developmental parent materials and properties.