I am Logan Sizemore,
Deep Learning Researcher,
Computer Science Teacher.

I am a Computer Science instructor and research associate at Western Washington University with a background in Chemistry, Social Studies, and a Master's in Computer Science. My research focuses on applying machine learning to interdisciplinary challenges in astronomy, climate science, and education. From modeling stellar parameters to emulating global climate systems, I develop AI-driven solutions for complex problems. As an educator, I mentor students in applying machine learning to real-world applications, combining my passions for teaching and research.

My Work

BOSS Net

BOSS Net is a data-driven pipeline designed to determine stellar parameters from both optical and near-infrared spectra, improving upon previous models by extending coverage to brown dwarfs and white dwarfs while providing a self-consistent tool for stellar characterization across multiple surveys.

Skeletonkey

skeletonkey is a simple, lightweight, and flexible configuration management tool that allows you to manage complex configurations for your applications using YAML files. It dynamically loads classes and their arguments at runtime, making it easy to set up and modify your projects.

Chemistry Cardsort

We explore how students organize their knowledge by analyzing a chemistry card sort task using unsupervised learning techniques. We identified nuanced organizational strategies and differences between novice and expert students from the natural language justifications associated with each student's sort.

GCAM Emulation

The Global Change Analysis Model (GCAM) simulates interactions between Earth and human systems, offering insights into the co-evolution of land, water, and energy sectors under various scenarios. To enhance efficiency in large-scale simulations, a neural network emulator was trained to predict GCAM outputs with high accuracy.

• Qiang, H., Kounkel, M., Bass, S., Lingg, R., Sizemore, L., Carroll, D., Hutchinson, B., & Stassun, K. (2025). A spatio-temporal data-cube approach to classification of variable stars: A catalog of candidate variable stars from the TESS FFI raw data. (Under review in The Astronomical Journal).
• Sizemore, L., Llanes, D., Kounkel, M., Hutchinson, B., Stassun, K. G., & Chandra, V. (2024). A self-consistent data-driven model for determining stellar parameters from optical and near-infrared spectra. The Astronomical Journal, 167(4), 173.
• Holmes, A., Jensen, M., Coffland, S., Mitani-Shen, H. M., Sizemore, L., Bassetti, S., Nieva, B., Tebaldi, C., Snyder, A., & Hutchinson, B. (2024). Emulating the Global Change Analysis Model with deep learning. In Tackling Climate Change with Machine Learning Workshop at NeurIPS 2024.
• Hutchinson, B., Holmes, A., Jensen, M., Coffland, S., Shen, H. M., Sizemore, L., Seth Bassetti, Brenna Nieva, Abigail Snyder & Tebaldi, C. (2024). Emulating the Global Change Analysis Model with Deep Learning. AGU24.
• Sizemore, L., Hutchinson, B., & Borda, E. (2024). Use of machine learning to analyze chemistry card sort tasks. Chemistry Education Research and Practice, 25(2), 417-437.
• Holmes, A., Jensen, M., Coffland, S., Mitani-Shen, H., Sizemore, L., Bassetti, S., Nieva, B., Tebaldi, C., Snyder, A., & Hutchinson, B. (2024). Emulating the Global Change Analysis Model with deep learning. In Tackling Climate Change with Machine Learning Workshop at NeurIPS 2024.
• Wolters, P., Sizemore, L., Daw, C., Hutchinson, B., & Phillips, L. (2021). Proposal-based few-shot sound event detection for speech and environmental sounds with perceivers. arXiv preprint arXiv:2107.13616.
• Beck, J. P., Muniz, M. N., Crickmore, C., & Sizemore, L. (2020). Physical chemistry students’ navigation and use of models to predict and explain molecular vibration and rotation. Chemistry Education Research and Practice, 21(2), 597-607.

• Google Scholar