Collaborative Research: D3SC: CDS&E: Predictive Discovery of Porphyrin Molecules and their Response Properties using Smart Objects-Enabled Machine Learning

点击翻译按钮获取中文摘要

With this award from the Chemical Theory, Models and Computational Methods program in the Division of Chemistry, Andre Clayborne (George Mason University) and Kim Lewis (Howard University) are supported to use artificial intelligence to predict porphyrin molecules suitable for molecular materials. Porphyrin molecules have electrical and optical properties that are tailorable for molecular materials and quantum information technologies. However, time-consuming experiments and challenges with traditional simulations limit researchers and industries from wide-spread use of porphyrin-based materials. The collaborative team will combine cutting-edge conductance experiments and theoretical calculation techniques along with machine learning and cognitive computing. The multidisciplinary research project also incorporates summer industrial immersion experiences for graduate students with Performigence, an industrial partner, to prepare for careers beyond academia. This collaborative research project aims to accelerate the discovery of porphyrin molecules, their response properties (i.e., conductance, UV-vis spectra, etc.), and molecular materials using data-centered graph-based neural networks and cognitive computing. Porphyrins are promising components in molecular-based devices in quantum information technologies and opto-electronic devices. Andre Clayborne and Kim Lewis will integrate data from quantum-mechanical computations, molecular dynamics simulations, scanning tunneling microscope molecular break junctions, and conductive atomic force microscopy with artificial intelligence techniques. The highly integrative work will construct a comprehensive database for porphyrins and metal-porphyrins with experimental and theoretical values including response functions, such as conductance curves, and will develop a cognitive computing protocol for predicting porphyrin molecules and their response properties. In addition, the research team will develop a web-based application programming interface to use the Porphyrin Project database with an industrial partner, Performigence.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.