My Ph.D. was focused on the fundamental investigation of fluid and particle dynamics in particle-laden flows using high-fidelity numerical methods. It was completed in 2022 with a Dean's Commendation for Doctoral Thesis Excellence.Since completion, my research has concentrated on integrating machine learning (ML) with low-fidelity computational fluid dynamics (CFD) tools to enhance their predictive capabilities for multiphase flow solutions. Specifically, this work involves developing and training ML models using fluid and particle data, as well as physical information from high-fidelity simulations, to improve the accuracy and efficiency of low-fidelity CFD simulations. These innovations enable more reliable and computationally efficient predictions for large-scale industrial applications.In parallel, my work targets sustainable energy applications, emphasising the simulation and optimisation of net-zero industrial processes such as limestone calcination and hydrogen production from methane pyrolysis. By leveraging advanced CFD and ML-augmented CFD methodologies, I am working on developing efficient and scalable hydrodynamic solutions to improve the conversion efficiency of these decarbonisation technologies, directly supporting the advancement of low-carbon energy systems.