This event will take place in the Physics/Astronomy Auditorium 102 (PAA A102) on the University of Washington campus.

“Functional data analysis tools for autonomous experimentation”

Authors: Kiran Vaddi, Kacper Lachowski, Huat Thart-Chiang, Karen Li, and Lilo D. Pozzo

Abstract: Artificial intelligence (AI), when interfaced with laboratory automation, can accelerate materials optimization and scientific discovery. For example, it may be used to efficiently map a phase diagram with intelligent sampling along phase boundaries, or in ‘retrosynthesis’ problems where a material with a target structure is desired but its synthetic route is unknown. These AI-driven laboratories are especially promising in polymer physics, where design parameters (e.g. chemical composition, molecular weight, topology, processing) are vast, and properties and functions are intimately tied to design features. However, for AI to operate efficiently in these spaces, they must be ‘encoded’ with domain expertise specific to the problems being tackled. In this talk, we focus on the problem of defining appropriate ‘distance’ metrics to describe differences between functions sampled within a design space. Such functions may be spectroscopic (e.g. UV-Vis absorption, fluorescence, impedance) or scattering profiles (SAXS, SANS) of materials. Traditional ‘distance’ metrics, such as Euclidean and parametric definitions, often fail when important features of the measured functions are subtle and/or when sampling takes place far from the target. We have thus developed a new shape-based similarity metric using Riemannian geometry (Amplitude-Phase Distance) that has been successfully implemented in both retrosynthesis and phase mapping problems. This talk will introduce the audience to the functional data analysis framework by first discussing the definition of the Amplitude-Phase Distance metric. We then demonstrate its implementation in an autonomous batch retrosynthesis problem using spectroscopic signatures in a model system of metallic nanostructures. We then showcase example implementations of the new distance metric in phase-mapping problems involving block-copolymers, polymer blends, and inorganic materials and extraction of design rules from novel material synthesis spaces.

Biography: Kiran Vaddi is a postdoctoral scholar at the Department of Chemical Engineering at the University of Washington. He obtained his bachelor’s and master’s in Mechanical Engineering from the Indian Institute of Technology Madras. His current research interests are accelerated material design and discovery with emphasis on topological and geometrical representations of data. At UW, he focuses on building computational tools to automate the design of high-throughput experiments using techniques such as reinforcement learning and active learning.

The UW Data Science Seminar is an annual lecture series at the University of Washington that hosts scholars working across applied areas of data science, such as the sciences, engineering, humanities and arts along with methodological areas in data science, such as computer science, applied math and statistics. Our presenters come from all domain fields and include occasional external speakers from regional partners, governmental agencies and industry.

The 2022-2023 seminars will be held in person, and are free and open to the public.