Zhou Lin (Physical Seminar)
Title: "Physics-Informed Machine Learning and Quantum Mechanics for Electronic Structures and Molecular Spectroscopy"
Zhou Lin, Assistant Professor of Chemistry
University of Massachusetts Amherst
Host: Xueyu Song/Rui Sun
Abstract: Our research encompasses forward structure-to-property prediction and inverse property-to-structure inference and provides essential tools for predicting and interpreting molecular structures and dynamics. We are developing computational models that combine physics-informed machine learning with quantum mechanics for these goals.
To achieve high-throughput inference of spectroscopic signals without trial and error, we created Spec2D, an encoder–decoder architecture that translates spectroscopic signals into molecular identity and connectivity. This process uses pre-trained large language models, such as transformers and GPT, to treat the task as a form of language translation. Spec2D demonstrates state-of-the-art accuracy in inferring the structures of single molecules and binary mixtures from calculated and experimental IR, NMR, and mass spec signatures.
To predict electronic structures and UV–vis spectra of organic semiconducting molecules and radicals, we developed ML-ωPBE, a machine-learned, range-separated density functional. This functional determines the range separation parameter, ω, directly from semi-empirical geometric and electronic features through regression and graph neural network models. ML-ωPBE outperforms all widely used functionals in predicting spectroscopic properties and requires no modifications when adopted to molecular aggregates and radicals.
To analyze fragment–fragment and fragment–environment interactions of complex systems, we developed FB-GNN-MBE, a hybrid quantum mechanics/machine learning method. This approach evaluates energies, forces, and energy components of a system using many-body expansion theory and fragment-based graph neural networks. FB-GNN-MBE accurately reproduces first-principles full-dimensional and reduced-dimensional potential energy surfaces of non-covalently bonded molecular clusters within chemical accuracy.
Bio: Zhou Lin is an Assistant Professor of Chemistry at the University of Massachusetts Amherst, where she leads the Zhou Lin Group in Quantum Chemistry. Her research lies at the intersection of quantum chemistry, artificial intelligence, spectroscopy, and materials chemistry, with an emphasis on developing new computational methods for understanding complex chemical systems. Her group develops fragment-based quantum chemistry and AI-accelerated approaches and applies them to problems including photochemistry, catalysis, molecular spectroscopy, and the computational design of molecules and materials. [umass.edu], [Zhou Lin Q...stry Group]
Dr. Lin earned her B.S. in Chemical Physics from the University of Science and Technology of China and her Ph.D. in Chemical Physics from The Ohio State University. She subsequently held postdoctoral appointments at the Massachusetts Institute of Technology and the University of California, Berkeley before joining UMass Amherst in 2020. In 2026, she was named a Cottrell Scholar by the Research Corporation for Science Advancement and received the OpenEye Cadence Molecular Sciences Outstanding Junior Faculty Award in Computational Chemistry from the American Chemical Society, recognizing her contributions to computational spectroscopy.