Research and software

Overview

I am excited to showcase two research projects prior to joining Stanford University. These projects remain on-going. They advance scientific software development and materials informatics under the braod themes of open science and reproducibility.

Project 1: Enabling scientists to share useful code

Working with Prof. Simon Billinge, I led a project helping scientists share useful code with the broader scientific community. The project, scikit-package, provides a pedagogical framework for scientists to write and share code to maximize impact.

• Paper: https://arxiv.org/abs/2507.03328

• Getting started guide: https://scikit-package.github.io/scikit-package

• GitHub: https://github.com/scikit-package/scikit-package

Academic software developed using scikit-package

• PDFfit2 and PDFgui: Computer programs for studying nanostructure in crystals (J. Phys. Condens. Matter)

• cifkit: A Python package for coordination geometry and atomic site analysis (JOSS)

• Composition and structure analyzer/featurizer for explainable machine learning models to predict solid state structures (Digital Discovery)

• Stretched non-negative matrix factorization (npj Comput. Mater.)

• Real-space texture and pole-figure analysis using the 3D pair distribution function on a platinum thin film (IUCrJ)

Project 2: Access to physics-chemistry elemental data

Working with Prof. Anton Oliynyk, I developed machine learning models using an elemental-compositional database for materials informatics. These models enable prediction and discovery of novel materials with targeted properties.

• Paper: https://doi.org/10.1016/j.dib.2024.110178

• Python API: https://bobleesj.github.io/bobleesj.utils

Papers published using OLED (Oliynyk Elemental Data)

• Copper Gallium Aluminum mixed metal oxides as alternative catalyst candidates for efficient conversion of carbon dioxide to methanol and dimethyl ether (ACS Catal.)

• Design and implementation of sintered NdFeB performance prediction system based on machine learning (ISRIMT 2024)

• Multi-objective optimization of material properties for enhanced battery performance using artificial intelligence (Expert Syst. Appl.)

• Machine learning based investigation of atomic packing effects: chemical pressures at the extremes of intermetallic complexity (JACS)

• Machine learning predictions of thermopower for thermoelectric material screening (ACS Appl. Energy Mater.)

• CALPHAD-based Bayesian optimization to accelerate alloy discovery for high-temperature applications (J. Mater. Res.)

• Machine learning assisted discovery of Cr³⁺-based near-infrared phosphors (Chem. Mater.)

• Thermoelectric material performance (zT) predictions with machine learning (ACS Appl. Mater. Interfaces)

• Explainable recommendation engines to predict complex intermetallics: synthesis and characterization of Gd₁₀RuCd₃, a neutron absorption material (JACS)

What am I working on now?

With Prof. Colin Ophus (https://colab.stanford.edu/) at Stanford, I am working on GPU accelerated algorithms for electron microscopy and ptychography. The goal is to enable real-time imaging at atomic resolution.