About me

I am a PhD student and Research Assistant at the University of Toronto. My research is focused on accelerating the discovery of novel materials and medicines using machine learning and quantum chemistry. Before joining the Clean Energy Lab at UofT, I earned a Bachelor of Science degree in Physics from Taras Shevchenko National University of Kyiv. During the Bachelor studies, I worked on projects in computational nuclear and high-energy physics.

My Research

  • I work on accelerating the discovery of materials and medicines. In my research I use Python (including libraries like PyTorch, Pandas, Scikit-learn, etc) to develop machine learning models and analyze chemical and biological data. I also extensively use Density Functional Theory (DFT) and Semiempirical Tight-Binding methods (xTB) for Quantum Chemistry calculations and Molecular Dynamics (MD) simulations.

  • Graph Neural Network for Materials Density of States prediction

  • Navigate Materials Space with ML-generated Electronic Fingerprints

  • Efficient Biological Data Acquisition through Inference Set Design

Publications

  • Efficient Biological Data Acquisition through Inference Set Design  ICLR
    I. Neporozhnii, J. Roy, E. Bengio, J. Hartford
  • Navigating Materials Space with ML-Generated Electronic Fingerprints  Preprint
    I. Neporozhnii, Z. Wang, R. Bajpai, C. Gomez, N. Chakraborty, I. Tamblyn, O. Voznyy
  • Machine learning models for the discovery of direct band gap materials for light emission and photovoltaics  Computational Materials Science
    F. Dinic, I. Neporozhnii, O. Voznyy
  • Strain data augmentation enables machine learning of inorganic crystal geometry optimization  Patterns
    F. Dinic, Z. Wang, I. Neporozhnii, U. Bin Salim, R. Bajpai, N. Rajiv, V. Chavda, V. Radhakrishnan, and O. Voznyy
  • Insertion of MXene-Based Materials into Cu–Pd 3D Aerogels for Electroreduction of CO2 to Formate  Advanced Energy Materials
    M. Abdinejad, S. Subramanian, M. K. Motlagh, M. Noroozifar, S. Duangdangchote, I. Neporozhnii, D. Ripepi, D. Pinto, M. Li, K. Tang, J. Middelkoop, A, Urakawa, O. Voznyy, H.-B. Kraatz, T. Burdyny
  • Mesoscopic self-ordering in oxygen doped Ce films adsorbed on Mo(112)  Surface Science
    T. Afanasieva, A. Fedorus, A. Goriachko, A. Naumovets, I. Neporozhnii, and D. Rumiantsev

Conference Presentations

Talks

  • Accelerated discovery of battery materials using ML-predicted Density of States
    Climate Positive Energy Research Day, Toronto, Canada (August 2023)
  • Navigating Material Space with ML-Generated Electronic Fingerprints
    Canadian Chemistry Conference and Exhibition, Vancouver, Canada (June 2023)
  • Machine learning methods for predicting density of states
    MRS Fall Meeting & Exhibit, Boston, United States, (December 2022)
  • Machine learning methods for predicting density of states
    Canadian Chemistry Conference and Exhibition, Calgary, Canada (June 2022)
  • Spatio-temporal correlation between Gamma-ray bursts and High-energy neutrino
    Week of Doctoral Students, Prague, Czech Republic (September 2020)

Posters

  • Navigating Material Space with ML-Generated Electronic Fingerprints
    Materials for Sustainable Development Conference (MATSUS24), Barcelona, Spain (March 2024)
  • Navigating Material Space with ML-Generated Electronic Fingerprints
    Accelerate Conference, Toronto, Canada (August 2023)
  • Machine learning methods for predicting density of states
    Accelerate Conference, Toronto, Canada (August 2022)
  • Machine learning methods for predicting density of states
    The Canadian Symposium on Theoretical and Computational Chemistry, Kelowna, Canada, (June 2022)

Awards & Scholarships

  • Climate Positive Energy Graduate Scholarship

  • Connaught Scholarship for Doctoral Students

Side Projects

  • Ainfer

    A web application for research paper analysis with Large Language models.

  • Satellite tracker

    Code for live tracking of satellites and space debris. Developed for NASA Space Apps hackathon