Speaker: Mahshid Ahmadi, The University of Tennessee, Knoxville
Abstract: The convergence of automated high-throughput (HT) synthesis and advanced characterization has fundamentally reshaped the pace and philosophy of materials research. By enabling parallelized experimentation, precise control of processing conditions, and rapid data acquisition, HT platforms allow us not only to accelerate materials optimization, but also to probe underlying chemical and physical mechanisms that were previously inaccessible through conventional methods. When combined with machine learning and large language models (LLMs), these autonomous workflows evolve into powerful closed-loop systems capable of guiding discovery with unprecedented intelligence.
In this talk, I will highlight how AI-driven hypothesis generation, property prediction, and experiment selection have enabled more informed and efficient navigation of complex synthesis and compositional spaces. I will discuss recent efforts in integrating agentic LLMs that simultaneously perform peak analysis, extract mechanistic signatures, and orchestrate the full experimental cycle—from hypothesis formulation to execution, real-time data interpretation, and feedback-driven adaptation of the next experiment. Together, these capabilities create a self-refining scientific engine that accelerates the discovery of new materials and deepens our understanding of their formation pathways and functional behavior. Looking ahead, the integration of autonomous experimentation, multimodal AI, and scalable knowledge frameworks will play a central role in shaping the next generation of self-driving laboratories and transforming how we design, understand, and deploy advanced materials.
Biography: Mahshid Ahmadi is an Associate Professor in the Department of Materials Science and Engineering at the University of Tennessee, Knoxville. She earned her Ph.D. in 2013 from Nanyang Technological University, Singapore. She leads a program that combines autonomous high-throughput experimentation, hypothesis-driven synthesis, and interpretable machine learning to accelerate halide perovskites discovery and extract fundamental insights from complex datasets. Her work sits at the forefront of AI-driven materials science and aims to establish a predictive understanding of structure–property relationships in halide perovskites. She is the recipient 2021 NSF CAREER Award, 2022 Alfred P. Sloan Fellowship in Chemistry, and 2025 Scialog Fellowship in Automated Chemical Laboratories from the Research Corporation for Science Advancement (RCSA). She was named a 2024 Early Career Rising Star in Materials Science by ACS Materials Au, 2024 UTK Tickle College of Engineering Professional Promise in Research Award, and the 2022 UTK MSE Faculty Award for Excellence in Research. She serves as an Associate Editor for APL Machine Learning and has authored or co-authored more than 100 peer-reviewed publications.
