Method for predicting heavy metal concentration in soil colloid solution based on machine learning model
By using machine learning models, especially random forests and gradient boosting regression tree models, combined with soil colloid extraction parameters, the problem of predicting heavy metal concentration in soil colloidal solutions that is difficult to predict using traditional methods has been solved, and accurate prediction of heavy metal concentration has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA UNIV OF MINING & TECH
- Filing Date
- 2026-06-02
- Publication Date
- 2026-07-24
AI Technical Summary
Traditional statistical analysis methods are insufficient to fully capture the complex nonlinear relationships in the process of heavy metal release mediated by soil colloids, and cannot effectively predict the concentration of heavy metals in soil colloidal solutions.
Machine learning models, especially random forest models, were used to construct a set of feature variables by combining experimental and property parameters extracted from soil colloids. Heavy metal concentrations were predicted using a random forest classifier and a gradient boosting regression tree model, and the XGBoost model was used for optimization.
It enables accurate prediction of heavy metal concentration in soil colloidal solutions, provides a reliable technical method, and improves the accuracy and reliability of prediction results.
Smart Images

Figure CN122449099A_ABST