Accurately identifying groundwater contamination sites is vital for groundwater protection and restoration. This study aims to use a machine learning (ML) approach to identify groundwater contamination sites with total petroleum hydrocarbons (TPH) as target contaminants in a case study of gas stations in China. Firstly, six classical ML algorithms, including logistic regression, decision tree, gradient boosting decision tree (GBDT), random forest, multi-layer perceptron, and support vector machine, were applied to develop the identification models of TPH-contaminated groundwater with 40 features and the performances were compared. The comparison results showed that the GBDT model achieves the best prediction performance, with F1 score of 1 and AUC value of 1. Next, Bayesian optimization optimized GBDT (BO-GBDT) was conducted to further decrease the training time from 19,125 s to 513 s while maintaining the same prediction performance (F1 score = 1, AUC = 1). Finally, Shapley additive explanations (SHAP) analysis was performed on the BO-GBDT model. The SHAP results displayed that the critical feature variables in the BO-GBDT model include wind, population, evaporation, total potassium in the soil, precipitation, and leakage accident. This study demonstrated that BO-GBDT is one satisfactory model to identify groundwater TPH-contamination at gas stations. The method proposed in this study has the potential to be applied to other types of groundwater contamination sites.

Methane reforming with carbon dioxide (DRM) is one promising way to achieve carbon neutrality and convert methane to syngas for high-value chemical production. Catalyst development with better performance is the key to its potential large-scale industrial application due to its deactivation caused by carbon deposition and metal sintering. Hence, a Ni/CeO₂ catalyst (Ni/CeO₂-M) with higher CO₂ conversion and better stability is prepared, supported on CeO₂ precipitated via a novel microimpinging stream reactor. A series of ex-situ or in-situ characterizations, such as CO titration measurements, two-step transient surface reaction (two-step TSR), CO₂ and CH₄ temperature-programmed surface reaction (CO₂-TPSR and CH₄-TPSR), X-ray absorption fine structure (XAFS), and in-situ Raman spectroscopy study, were used to investigate its structure and mechanism. In contrast to Ni supported on commercial CeO₂ (Ni/CeO₂-C), the Ni/CeO₂-M catalyst with stronger lattice oxygen mobility and higher oxygen storage capacity enhances its CO₂ activation ability and carbon deposition. The Ni particle size of the Ni/CeO₂-M catalyst decreased, and a higher oxidation state was obtained due to the strong metal–support interaction. Besides the reaction performance improvement of the Ni/CeO₂-M catalyst, the novel microimpinging stream reactor could achieve catalyst continuous production with a high preparation efficiency. This work provides a novel method for the high-performance catalyst preparation for DRM reaction and its mechanism study gives a deep insight into high-performance catalyst development via bottom-up study.