Improved classification of soil As contamination at continental scale: Resolving class imbalances using machine learning approach

• Published in: Chemosphere (Oxford) 2024-09, Vol.363, p.142697, Article 142697
• Main Authors: Hu, Tao, Li, Kechao, Ma, Chundi, Zhou, Nana, Chen, Qiusong, Qi, Chongchong
• Format: Article
• Language: English
• Subjects: As contamination; Continental identification; Imbalance resampling; Machine learning; Soil hyperspectral
• ISSN: 0045-6535; 1879-1298; 1879-1298
• DOI: 10.1016/j.chemosphere.2024.142697

The identification of arsenic (As)-contaminated areas is an important prerequisite for soil management and reclamation. Although previous studies have attempted to identify soil As contamination via machine learning (ML) methods combined with soil spectroscopy, they have ignored the rarity of As-contaminated soil samples, leading to an imbalanced learning problem. A novel ML framework was thus designed herein to solve the imbalance issue in identifying soil As contamination from soil visible and near-infrared spectra. Spectral preprocessing, imbalanced dataset resampling, and model comparisons were combined in the ML framework, and the optimal combination was selected based on the recall. In addition, Bayesian optimization was used to tune the model hyperparameters. The optimized model achieved recall, area under the curve, and balanced accuracy values of 0.83, 0.88, and 0.79, respectively, on the testing set. The recall was further improved to 0.87 with the threshold adjustment, indicating the model's excellent performance and generalization capability in classifying As-contaminated soil samples. The optimal model was applied to a global soil spectral dataset to predict areas at a high risk of soil As contamination on a global scale. The ML framework established in this study represents a milestone in the classification of soil As contamination and can serve as a valuable reference for contamination management in soil science. [Display omitted] •The imbalance classification of soil As contamination was studied continentally.•Modeling consisted of spectral preprocessing, resampling, Bayesian optimization.•The optimal XGBoost model achieved a recall of 0.866 on the testing set.•The optimal model was used to identify potential soil As contamination globally.