Shengli (Bruce) Jiang

PhD Candidate

University of Wisconsin-Madison

Curriculum Vitae

Biography

I am a PhD Candidate at the University of Wisconsin-Madison. I work on geometric deep learning, uncertainty quantification, and topological data analysis for sustainability-related applications, including contaminant sensor design, plastic waste sorting, and molecular property prediction.

Research Area

Geometric Deep Learning
Uncertainty Quantification
Topological Data Analysis
Sustainability

Education

PhD in Chemical Engineering, 2023

University of Wisconsin-Madison
BSc in Chemical Engineering, 2018

University of California, San Diego

Selected Publications (View All)

Capturing Molecular Interactions in Graph Neural Networks: A Case Study in Multi-Component Phase Equilibrium

Shiyi Qin, Shengli Jiang, Jianpin Li, Prasanna Balaprakash, Reid C Van Lehn, Victor M Zavala

PDF Website

Sensing Gas Mixtures by Analyzing the Spatiotemporal Optical Responses of Liquid Crystals using 3D Convolutional Neural Networks.

Nanqi Bao, Shengli Jiang, Alexander D Smith, James J Schauer, Manos Mavrikakis, Reid C Van Lehn, Victor M Zavala, Nicholas L Abbott

PDF Website

Graph Neural Network Architecture Search for Molecular Property Prediction

Shengli Jiang, Prasanna Balaprakash

PDF Website

Fast Predictions Of Liquid-phase Acid-catalyzed Reaction Rates Using Molecular Dynamics Simulations And Convolutional Neural Networks

Alex K Chew, Shengli Jiang, Weiqi Zhang, Victor M Zavala, Reid C Van Lehn

PDF Website

Shengli (Bruce) Jiang

PhD Candidate

University of Wisconsin-Madison

Biography

Research Area

Education

Selected Publications (View All)

Capturing Molecular Interactions in Graph Neural Networks: A Case Study in Multi-Component Phase Equilibrium

Sensing Gas Mixtures by Analyzing the Spatiotemporal Optical Responses of Liquid Crystals using 3D Convolutional Neural Networks.

Graph Neural Network Architecture Search for Molecular Property Prediction

Fast Predictions Of Liquid-phase Acid-catalyzed Reaction Rates Using Molecular Dynamics Simulations And Convolutional Neural Networks

Contact