Machine-Learning-Guided Discovery of CH ₄ Combustion Catalysts Operating in the Presence of SO ₂

Methane (CH 4 ) combustion under lean conditions is a critical reaction for controlling unburned hydrocarbon emissions in natural gas engines. However, the development of highly active and sulfur-tolerant catalysts remains a major challenge due to the severe deactivation caused by sulfur compounds such as SO 2 . In this study, we adopted a machine-learning (ML)-guided strategy to accelerate the discovery of CH 4 combustion catalysts that are tolerant to sulfur poisoning. Starting from 16 initial catalysts and conducting 24 cycles of a closed-loop discovery system (ML prediction + experiment), a total of 300 multielemental catalysts were experimentally evaluated under identical conditions in the presence of SO 2 . Through this approach, over 30 catalysts exhibiting high CH 4 conversion and excellent sulfur tolerance were identified. Among them, Pd(2)–Ru(0.4)–Ir(0.3)–Pt(0.3)/ZrO 2 _JRC3_RC-100 demonstrated the highest catalytic performance. Control experiments and comprehensive characterizations, including in situ/ operando spectroscopy, revealed the individual and synergistic roles of each component in enhancing both activity and resistance to sulfur poisoning.