Abstract: The development of efficient catalysts is crucial for achieving energy-efficient chemical transformations and meeting our environmental sustainability goals. However, the computational modeling of heterogeneous catalysis, which accounts for 80% of industrial catalyst processes, presents significant complexities. In this invited talk, we will delve into recent research topics, such as carbon reutilization and bio-feedstock conversion, to explore how the integration of Machine Learning-accelerated Quantum Mechanical modeling and insights from high throughput experiments is shaping industrial catalyst design. This talk aims to provide young scientists with a grounded understanding of the practical applications and opportunities in this multidisciplinary field.