Application of Multi-Task Learning in Analysing the Methane Working capacity of Metal-Organic Frameworks

Key Points

• The research aims to optimize methane capture performance in metal-organic frameworks using multi-task learning.
• Utilized multi-task learning algorithms for screening MOFs.
• Focused on analyzing methane adsorption characteristics.
• Implemented a rational design approach to identify optimal frameworks.
• Identified several MOFs with significantly improved methane capture capacities.
• Demonstrated the efficiency of multi-task learning in predicting adsorption performance.