Summary

I am a Ph.D. candidate with a focus in machine learning (ML) and quantum-chemical simulation at the Department of Chemical Engineering, Virginia Tech, Blacksburg, VA. I am seeking a full time or internship job position in the fields of Data Analytics and Machine Learning for immediate employment. The 4 years of rigorous doctoral training has brought me solid advanced data analytic skills, domain expertise in the material informatics theory and high-level curiosity for the innovative fronts. Most of my ML-related work has been successfully published by the peer-reviewed academic journals. Besides my research, I am self-motivated to learn sophisticated ML techniques, e.g., Image Recognition with deep learning Convolutional Neural Networks (CNNs) and Natural Language Processing (NLP), and try to implement those techniques for solving real-life or science problems.

Education

Ph.D., Chemical Engineering, Virginia Tech University, 2019, Blacksburg, VA, United States

(Advisor: Prof. Hongliang Xin)

B.S., Chemical Engineering, Washington State University, 2014, Pullman, WA, United States

Doctoral dissertation

Title: Accelerating Energy Materials Discovery via Ab Initio Machine Learning

Supervisors: Prof. Hongliang Xin and Prof. Luke E. Achenie

Description: Facilitating catalytic materials discovery in the quantum mechanical simulations and kinetic modeling by developing multi-functional machine-learning frameworks with novel physically intuitive material fingerprinting methods. Accomplished this in accordance with domain knowledge in the molecular orbital theory and through writing Python packages for task-specific data processing, machine learning analysis, and visualizations.

Work experience

Virginia Tech University, Blacksburg, VA, United States

Graduate Research Assistant (Jan, 2015 – present)

Works on versatile research projects on the development of Articial Intelligence (AI) platform by integrating ab initio quantum mechanical modeling and machine learning algorithms for high through-put screening of energy materials.

• Developed novel material fingerprinting/feature methods (e.g., DOS entropy indices, compositional descriptor, molecular graphs, etc.) for transforming the complex and semi-structured materials DFT-calculated electronic structure informatics into algorithm interpretable language;
• Wrote Python packages for task-specific data processing, machine learning analysis and visualizations, including database query systems, material fingerprinting engines, data cleansing filters, advanced machine-learning ensemble platforms, automatic feature selection algorithms, kinetic models, and result visualization tools;
• Used insightful knowledge from the first-principle datasets to on the material’s structure-activity relationships by using advanced machine-learning analytics methods, including global variance-based sensitivity analysis, and hierarchical clustering analysis;
• Collaborated with experiment professionals for fundamentally understanding the materials activity in the chemical reactions, e.g. oxygen evolution reaction by using the first principle thermodynamic method;
• Published on 4 high quality peer-reviewed scientific journals, including 3 first-author and 1 second-author publications, 1 news & views review article on Nature, and designed the magazine back cover for Journal of Materials Chemistry A (Royal Society of Chemistry). Another 2 first-authored manuscripts are under review.

DENTSPLY International, Milford, DE, United States

Research Technical Intern (Jun, 2014 – Aug, 2014)

Worked on the development of a novel polymerizable antibacterial resin for dental application.

• Organic synthesis, composite formulation, and physical/mechanical property evaluation;
• Improved the antibacterial property of nanogel in the microwave-assisted polymerization reaction by introducing a charged nitrogen heterocyclic structure into the conventional monomer composite.

Pfizer, Dalian, China

Research Technical Intern (Jun, 2013 – Aug, 2013)

Inspected drug quality for the oral products.

• Determined the functional components of drugs using High Performance Liquid Chromatography (HPLC);
• Examinined the effective ingredients of drugs using the method of Thin Layer Chromatography (TLC);
• Measured the moisture content of the new drugs using Karl Fischer method.

Washington State University, Pullman, WA, United States

Undergraduate Laboratory Assistant (Professor Oscar Marin's catalyst team) (Feb, 2012 – Apr, 2013)

• Converted biomass to liquid hydrocarbon fuels using zeolites as catalytic material;
• Thermodynamic analysis of the liquid-phase alkylation process and mathematical modeling of fuel cell systems.

Undergraduate Peer Tutor (Jan, 2011 – Apr, 2013)

• Helped undergraduate students academically in engineering courses for Math/Chemistry/physics on a weekly basis.

Peer-reviewed publications

• Z. Li, S. Wang, H. Xin. Toward artificial intelligence in catalysis, Nature Catalysis, News & Views, 2018, 1 (9), 641–642.
• Z. Li, N. Omidvar, W.S. Chin, E. Robb, A. Morris, L. Achenie, H. Xin. Machine-Learning Energy Gaps of Porphyrins with Molecular Graph Representations, Journal of Physical Chemistry A, 2018, 122, 4571–4578.
• Z. Li, S. Wang, W.S. Chin, L.E. Achenie, H. Xin. High-throughput screening of bimetallic catalysts enabled by machine learning. Journal of Material Chemistry A, 2017, 5 (46), 24131-24138.
• Z. Li, X. Ma, H. Xin. Feature engineering of machine-learning chemisorption models for catalyst design, Catalysis Today. 2017, 280, 232–238.
• X. Ma, Z. Li, L.E.K. Achenie, H. Xin, Machine-Learning-Augmented Chemisorption Model for CO2 Electroreduction Catalyst Screening, Journal of Physical Chemistry Letters, 2015, 6, 3528–3533.

Conference papers

• Z. Li, Q. Zheng, N. Omidvar, L. Achenie, H. Xin, Large-Scale Exploration of Perovskites for Oxygen Evolution Via Adaptive Machine Learning. 2018 AIChE Annual Meeting, Pittsburgh, PA. (Oral presentation)
• Z. Li, N. Omidvar, L. Achenie, H. Xin, Stacking Machine-Learning Workflow for Accelerating Discovery of Perovskite Electrocatalysts. 2018 Southeastern Catalysis Society Symposium, Atlanta, GA. (Oral presentation)
• Z. Li, L. Achenie, H. Xin, Machine Learning Guided Design of Perovskites for Oxygen Evolution. 2018 ChE Graduate Symposium, Blacksburg, VA. (Oral presentation)
• Z. Li, H. Xin, Feature Engineering of Machine-Learning Models for Metal Oxides. 2017 AIChE Annual Meeting, Minneapolis, Mn. (Oral presentation)
• Z. Li, S. Wang, H. Xin, Developing a Machine-Learning Approach for Catalyst Discovery. 2017 25th North American Catalysis Society Meeting, Denver, CO. (Oral presentation)
• Z. Li, W.S. Chin, S. Wang, S.H. Wang, H. Xin, A Bayesian-Learned Newns-Anderson Model for Understanding Hydrogen Evolution on Metals, 2017 ChE Graduate Symposium, Blacksburg, VA. (Oral presentation)
• Z. Li, S. Wang, L. Achenie, H. Xin, A Data-driven Machine-Learning Approach for Bifunctional Electrocatalyst Design. 2016 AIChE Annual Meeting, San Francisco, CA. (Oral presentation)
• Z. Li, H. Xin, Machine-Learning-Augmented Chemisorption Model for Metal Oxides. 2016 AIChE Annual Meeting, San Francisco, CA. (Poster)
• Z. Li, H. Xin, Development of Machine-Learning Chemisorption Models for Oxide Electrocatalysis. 2016 Fall American Chemical Society Annual Meeting, Philadelphia, PA. (Poster)
• Z. Li, X, Ma, S. Wang, L. Achenie, H. Xin, Development of Machine-Learning Approach for Electrocatalyst Discovery. 2016 Southeastern Catalysis Society Symposium, Asheville, NC. (Oral presentation)
• Z. Li, X, Ma, H. Xin, Electronic Factors Governing Direct Photochemistry on Metal Surfaces. 2015 New York Catalysis Society Symposium, Newark, NJ. (Poster)
• Z. Li, H. Xin, Generalized Catalyst Design Approach with Linear-Scaling Relationships and Machine Learning of Ab Initio Adsorption Energies. 2015 SUNCAT Summer Institute Conference, Stanford University, CA. (Poster)

Awards & honors

• Hord Graduate Fellowship Award in Chemical Engineering Department, 2019.
• Second place for student talk competition award in Southeastern Catalysis Society, 2016.
• American Chemical Society conference travel award, 2016.
• Journal of Materials Chemistry A, Back cover design honor, 2017.

Technical skills

Programming: Python, Java, R, Matlab Operating systems: Unix/Linux

Database: MySQL, Hadoop, Spark ML library: scikit-learn, Keras, PyMC3

Applications: Photoshop, Adobe Illustrator, LaTeX, Atomic Simulation Environment (ASE)

Advanced ML modeling: Artificial Neural networks (Tensorflow), Bayesian statistics, Tree-based models, Gradient Boosting Machines (GBM), Gaussian process model, Kernel-based models, Stacking ensemble models, etc.

Languages

English: Excellent in professional written and oral presentation.

Chinese: Native speaker.

Contact information

Email: zhengl@vt.edu