The solid oxide electrolysis cell (SOEC) holds great promise to efficiently convert renewable energy into hydrogen. However, traditional modeling methods are limited to a specific or reported SOEC system. Therefore, four machine learning models are developed to predict the performance of SOEC processes of various types, operating parameters, and feed conditions. The impact of these features on the SOEC's outputs is explained by the Shapley additive explanations and partial dependency plot analyses. The preferred model is integrated with a genetic algorithm to determine the optimal values of each input feature. Results show the improved extreme gradient enhanced regression (XGBoost) algorithm is the core of the machine learning model of the process since it has the highest R² (> 0.95) in the three outputs. The electrolytic cell descriptors have a greater impact on the system performance, contributing up to 54.5%. The effective area, voltage, and temperature are the three most influential factors in the SOEC system, contributing 21.6%, 16.6%, and 13.0% to its performance. High temperature, high pressure, and low effective area are the most favorable conditions for H₂ production rate. After conducting multi-objective optimization, the optimal current intensity and hydrogen production rate were determined to be 1.61 A/cm² and 1.174 L/(h·cm²).

A hammer-like Co₃O₄ was firstly prepared by using metal–organic framework-74 as a template, and then compounded with elemental Ag to fabricate a highly active catalyst with an improved electronic conductivity. The Li–O₂ battery with this prepared catalyst has a specific discharge capacity of 13945 mA·h/g at a current density of 100 mA/g. Even at a high current density of 1000 mA/g, the battery can still maintain a specific discharge capacity of 4476.3 mA·h/g, indicating that it has an excellent rate performance. Also, the cycle performance is greatly improved. For the limited specific capacity of 1000 mA·h/g at the current density of 500 mA/g, the battery with Ag/Co₃O₄ catalyst can be used for 195 cycles, while that with Co₃O₄ catalyst can be used for only 42 cycles.

Electrocatalysts with high efficiency are crucial for improving the storage capacity and electrochemical stability of lithium–oxygen batteries (LOBs). In this work, through a facile hydrothermal method, cobalt–nitrogen-doped carbon nanocubes (Co–N/C), the calcination products of zeolitic imidazolate framework (ZIF–67) are encapsulated by ultrathin C–MoS₂ nanosheets to obtain Co–N/C@C–MoS₂ composites which are used as host materials for the oxygen cathode. The synergistic effect between Co–N_x active sites and Mo–N coupling centers effectively promotes the formation and decomposition of Li₂O₂ during repeated discharge and charge process. The mesoporous C–MoS₂ nanosheets with delicately designed morphology facilitate charge transfer and account for improved reaction kinetics and more importantly, suppressed side reactions between the carbon materials and the electrolyte. The oxygen cathode with the Co–N/C@C–MoS₂ host shows a high initial discharge specific capacity of 21197 mA h g⁻¹ and a long operation life of 332 cycles. Theoretical calculation provides in-depth explanation for the reaction mechanism and offers insights for the rational design of electrocatalysts for LOBs.