I'm Olanrewaju (Ola) Muili, a Computational Materials Scientist and DOE Marine Energy Fellow working at the intersection of energy materials, atomistic simulation, and machine learning. My path runs through geoscience and computer science: I hold an M.S. in Geosciences from Georgia State University, an M.S. in Computer Science from the University of Colorado Boulder, and a B.S. in Geology from the University of Ibadan, Nigeria. Across these stages, a common thread has been using quantitative tools to understand and improve the physical world.

Today, my research is centered on metal halide perovskites and the problem of why they break down under real operating conditions. I use first-principles density functional theory (DFT) with Quantum ESPRESSO to study how oxygen and defects—especially iodide vacancies—modify the local structure and electronic properties of MAPbI₃ and related materials. As part of a Department of Defense–relevant DOE Marine Energy project, I'm interested in how stresses such as moisture, temperature, and bias accelerate degradation in energy materials, and how machine learning models built on top of simulations and experiments can help us predict and ultimately mitigate these failure pathways.

Before turning my focus to perovskite energy materials, I worked as an Exploration Geologist, building 3D geological models and data-driven workflows for mining and natural resource projects. I combined field observations, geophysical data, geostatistics, and custom code to interpret complex subsurface environments and support operational decisions. That experience continues to shape how I think about research: models have to be rigorous, but they also have to be usable by people making real-world choices.

My work at the interface of AI and geoscience has been recognized with the Microsoft Top 2 AI Innovator Award, and I was named a finalist for the Presidential Management Fellowship (PMF). I stay active in professional communities, including the Association for the Advancement of Artificial Intelligence (AAAI), the American Institute of Professional Geologists (AIPG), and the International Association for Mathematical Geosciences (IAMG). Looking ahead, I'm focused on bringing together first-principles modeling, machine learning, and domain expertise to design more reliable and sustainable energy materials and technologies.