About

Joel Sotelo Flores

I am an undergraduate researcher in computational and physical volcanology at Washington and Lee University. I started out as a physics major with a focus on stellar astronomy, and shifted into earth science with a focus on igneous processes. I love using what i've learned in my physics courses and applying them to understand volcanic systems. I find that the things i've learned in thermodynamics and statistical physics have really transferred from stars to volcanoes well!

Research focus

computational volcanology
physical volcanology
computer vision for eruption imagery
eruption dynamics
high-temperature experimental petrology
machine learning for volcanic analysis and signal processing
micro-CT analysis
pore-network and permeability analysis
scientific software development

Methodological approach

My research combines physics and Earth science with scientific imaging, machine learning, quantitative analysis, and software development to study volcanic systems. This work connects field observation and laboratory data to reproducible computational methods that extract physical measurements from imagery and micro-CT volumes. The nice thing about originally being a physics major first is that I would love being a lab rat! Although being out on fieldwork is super fun.

My current projects span lava-fountain computer vision and pyroclast micro-CT analysis, applying similar end-to-end workflows; collect data, segment structures, and quantify physical properties to different volcanic systems. I've applied my computational skills to volcanic structures large and small, leaving me as a versatile asset.

Current work

Active

Kīlauea Lava-Fountain Computer Vision

Automated Quantification of Lava Fountain Dynamics Using Computer Vision During the 2024-2026 Kīlauea Eruption.

I am developing a computer-vision pipeline to segment Kīlauea lava-fountain video and support quantitative extraction of eruption parameters such as fountain height, projected areas, and eruption rates from field footage. The project combines U-Net machine-learning segmentation, manual labeling, dataset preparation, metadata organization, and field video collection under variable lighting, viewing geometry, and field conditions.

computational volcanology
physical volcanology
computer vision

Active

Kawah Ijen Pyroclast Micro-CT and Pore-Network Analysis

Deep-learning segmentation and stereometric analysis of pyroclastic materials from the 1817 Kawah Ijen eruption.

I conduct computational volcanology research on pyroclastic micro-CT volumes from the 1817 Kawah Ijen eruption. The work uses U-Net-based deep-learning segmentation, stereometric analysis, Dragonfly, OpenPNM, electron microprobe data, and scanning electron microscopy to investigate vesicularity, pore connectivity, permeability, anisotropy, mineral chemistry, fractionation trends, and pressure-temperature constraints.

computational volcanology
pyroclast textures
micro-CT

Contact

Lexington, Virginia