Abstract: Inspired by the recent advancements and successes of artificial intelligence (AI) and machine learning (ML), several materials intelligence ecosystems are emerging. These include the design of materials that meet target property requirements, either by closed-loop active-learning strategies or by inverting the prediction pipeline using advanced generative algorithms. AI and ML concepts are also transforming the computational and physical laboratory infrastructural landscapes—surrogate models that can outperform physics-based simulations (on which they are trained) by several orders of magnitude in speed while preserving their accuracy are being actively developed. Integration of such AI/ML approaches with high-throughput experimentation can facilitate autonomous materials discovery with enormous efficiency.

In this talk, I will cover my research experience on a range of computational and AI/ML approaches for materials design, including search for novel ferroelectric binary oxides, polymers for high temperature high energy capacitor applications, self-assembling peptides, among others. I will demonstrate how AI/ML can be used to screen promising candidates from intractable materials chemical spaces, reveal novel material structure-property relationships, and/or overcome prevailing human-researcher biases. I will also discuss my future plans to utilize materials modeling and AI/ML techniques to accelerate (or automate) several experimental activities within CNM, design biodegradable polymers and discover synthetic pathways for realization of metastable phases of inorganic materials.