Entalpic | From Trial and Error to AI-Driven Materials Discovery

Materials discovery is still largely driven by trial and error. Current computational simulation methods are costly and slow, limiting the number of candidates that can be evaluated before moving to the experimental phase. AI offers a way to accelerate this process and increase the hit rate: explore a much larger number of candidates computationally, identify the most promising ones, and focus experimental efforts on where it is worth investigating. Lucile Ritchie, Director of Product & Solutions at Entalpic, explains how the company’s Atomistic Discovery Engine combines generative and predictive machine learning models with physics-based simulations to explore chemical space and rank candidates for experimental validation. Focusing mainly on semiconductor materials and catalysis, the session explores how AI and computational chemistry can help researchers navigate a vast chemical space and focus experimental efforts on the most promising candidates.