Sergei V. Kalinin

Abstract

Closing the Materials Discovery Loop via ML-Assisted Characterization: Building Optimized Rewards

The lesson of the past two decades is that scaling computation or synthesis individually by many orders of magnitude is insufficient to expedite materials discovery. The key is accelerating the iterative loop between theory and hypothesis making, experiment planning, synthesis, and characterization with subsequent update of theoretical models. Theory scales independently of material classes and can be leveraged universally through high performance computing and machine learning, fueling the recent advances from Google, Microsoft, and Meta. Synthesis can be scaled within certain material classes (or more specifically, within the synthesis method); whereas characterization remains a highly heterogeneous process with various tools, latencies, costs, and types of data generated. Currently, characterization is the bottleneck – while synthesis can be scaled to 1000s compositions per day, the sequential structural, functional, and chemical probing still require hours and days. However, this latency bottleneck is also intrinsically connected with the interpretability bottleneck, namely integration of the multidimensional measurement and imaging results back into theoretical predictive frameworks. This challenge is almost unaddressed by the AI4Science community of today.
We explore the bottom-up approach to build the single- and multi-instrument synthesis and characterization workflows based on the reward function concept. We present our latest advancements in the development of autonomous research systems based on electron and scanning probe microscopy, as well as for automated materials synthesis. We identify several categories of reward functions that are discernible during the experimental process, encompassing fundamental physical discoveries, the elucidation of correlative structure-property relationships, and the optimization of microstructures. The operationalization of these rewards function on autonomous microscopes is demonstrated, as well as the need and strategies for human in the loop intervention. Utilizing these classifications, we construct a framework that facilitates the integration of multiple optimization workflows, demonstrated through the synchronous orchestration of diverse characterization tools across a shared chemical space, and the concurrent navigation of costly experiments and models that adjust for epistemic uncertainties between them. Our findings lay the groundwork for the integration of multiple discovery cycles, ranging from rapid, laboratory-level exploration within relatively low-dimensional spaces and strong basic physics priors to more gradual, manufacturing-level optimization in highly complex parameter spaces underpinned by poorly known and phenomenological physical models. The very tempting opportunity this research opens is further use of the LLMs for creation of the probabilistic reward functions.

Biography

Sergei Kalinin is a Weston Fulton chair professor at the University of Tennessee, Knoxville. In 2022 – 2023, he has been a principal scientist at Amazon special projects (moon shot factory). Before then, he has spent 20 years at Oak Ridge National Laboratory where he was corporate fellow and group leader at the Center for Nanophase Materials Sciences. He received his MS degree from Moscow State University in 1998 and Ph.D. from the University of Pennsylvania (with Dawn Bonnell) in 2002. His research focuses on the applications of machine learning and artificial intelligence methods in materials synthesis, discovery, and optimization, automated experiment and autonomous imaging and characterization workflows in scanning transmission electron microscopy and scanning probes for applications including physics discovery, atomic fabrication, as well as mesoscopic studies of electrochemical, ferroelectric, and transport phenomena via scanning probe microscopy. When at ORNL, he led several major programs integrating the ML and physical sciences and instrumentation, including the Institute for Functional Imaging of Materials (IFIM 2014-2019), the first program in DOE integrating ML and physical sciences, and the microscopy effort in INTERSECT program that realized first ML-controlled scanning probe and electron microscopes. At UTK MSE, he participated in building one of the first efforts in the country on ML-driven materials exploration. At UTK, his team has now realized fully AI-controlled SPM and STEM systems and co-orchestration workflows between multiple characterization tools for scientific discovery. He has also taught multiple courses on the ML for materials science and microscopy including Bayesian optimization methods. Sergei has co-authored >650 publications, with a total citation of ~55,000 and an h-index of ~116. He is a fellow of AAAS, RSC, AAIA, MRS, APS, IoP, IEEE, Foresight Institute, and AVS; a recipient of the Adler Lectureship (APS 2025), Duncumb Award (MSA 2024), Medard Welch Award (AVS 2023), Orton Lectureship (ACerS 2023), Feynmann Prize of Foresight Institute (2022), Blavatnik Award for Physical Sciences (2018), RMS medal for Scanning Probe Microscopy (2015), Presidential Early Career Award for Scientists and Engineers (PECASE) (2009); Burton medal of Microscopy Society of America (2010); 5 R&D100 Awards (2008, 2010, 2016, 2018, and 2023); and a number of other distinctions. As part of his professional services, he organized many professional conferences and workshops at MRS, APS and AVS; for 15 years organized workshop series on PFM, and served/s on multiple Editorial Boards including NPJ Comp. Mat., J. Appl. Phys, and Appl. Phys Lett.