Zhijun Ren

Coal transportation terminals produce wastewater containing high concentrations of chloride, which can cause corrosion of equipment and be hazardous to the environment. Capacitive deionisation (CDI) has been discussed as an alternative to conventional dechlorination methods, given that it consumes low energy and avoids secondary pollution. This paper involved the development of a KOH-modified activated carbon (KOH-AC) electrode, which must be used to improve the chloride removal performance of CDI. The obtained characterization results showed that, under the activation of KOH, the specific surface area of activated carbon (104.48 m ² /g to 1390.88 m ² /g) was greatly intensified, the pore structure became more uniform, and plentiful oxygen-containing functional groups were formed, improving electrochemical activity and ion adsorption capacity. In optimal operating conditions (1.2 V, 20 mL/min), the KOH-AC electrode obtained a chloride ion removal efficiency of more than 80% and was extremely stable even after numerous adsorption-desorption cycles. Moreover, the CatBoost exhibited high accuracy in predicting chloride removal efficiency (R ² = 0.9114). The shap analysis revealed that the flow rate and influent NaCl concentration were the most significant factors for dechlorination. This study provides insights for the efficient removal of chlorinated wastewater in coal transportation terminals, while the constructed model offers a reference for precise treatment.

Anaerobic digestion of straw is a crucial method for agricultural waste valorization, yet its efficiency is limited by complex factors. This study employed machine learning to predict methane yield and optimize process parameters in biochar-amended straw digestion. A comprehensive dataset integrating experimental and literature data (100 samples, 15 input variables) was constructed, incorporating operational conditions, straw characteristics, and biochar properties (e.g., dosage, particle size, specific surface area, and elemental composition). Prediction models were developed using Random Forest (RF), XGBoost, and Support Vector Machine (SVM). Results indicated that the RF model achieved the best predictive accuracy, with an R² of 0.81 and RMSE of 36.9, significantly surpassing other models. Feature importance analysis identified feeding load, biochar dosage, and biochar carbon content (C%) as the key governing factors, collectively accounting for 65.7% of the total contribution. The model-predicted optimal ranges for practical operation were 15–30 g for feeding load and 5–20 g/L for biochar dosage. This study provides data-driven validation of biochar’s enhancement mechanisms and demonstrates the utility of RF in predicting and optimizing anaerobic digestion performance, offering critical support for sustainable agricultural waste recycling and clean energy generation.

Using a thiol–ene click chemistry method, GO and TiO ₂ are grafted to the silicone resin matrix coating for creating high dispersion and interfacial compatibility. This coating composite displayed an anti-corrosion feature and self-cleaning property.