Research
NASA Science Activation grant funded
Co-PI on a NASA Science Activation Grant” Funded amount: $3,628,504.
Hello, and welcome!
I am a computer scientist working at the intersection of artificial intelligence and space science. I build machine learning methods that help us understand complex scientific data, explain their predictions, and learn as new observations arrive.
Much of my work looks toward the Sun: how can we use its images and measurements to better anticipate solar flares and other space weather events? These questions guide my research in explainable AI and continual learning, and the projects I explore with my students.
Recent news
All news →Research
NSF CAIG project funded
Subaward PI on “CAIG: Heterogeneous Learning for Heliophysics with Uncertainties.” Funded amount: $124,719.
Teaching
Teaching Deep Learning and Data Mining this fall
Fall 2026 courses at TCU include COSC 50523: Deep Learning and COSC 50303: Data Mining.
Read moreResearch directions
Overview →Explainable artificial intelligence
Understanding why a model predicts an event—and whether its reasoning is meaningful.
Learning in changing environments
Building models that can adapt as new observations arrive and data distributions shift.
AI for space weather
Forecasting solar flares and geomagnetic disturbances from complex scientific observations.
Selected publications
All publications →SuryaBench: Benchmark dataset for advancing machine learning in heliophysics and space weather prediction
S. Roy, D. V. Hegde, …, C. Pandey, et al. Scientific Data, 2026.
Read publicationOrdinal encoding as a regularizer in binary loss for solar flare prediction
C. Pandey, J. Hong, A. Ji, R. A. Angryk, and B. Aydin. IEEE ICDM Workshops, 2025, pp. 1890–1895.
Read publicationDataset: Bitmap Filtered Line of Sight HMI Active Region Patches with Augmentations →
Explainable deep learning‑based solar flare prediction with post hoc attention for operational forecasting
C. Pandey, R. A. Angryk, M. K. Georgoulis, and B. Aydin, “Explainable deep learning‑based solar flare prediction with post hoc attention for operational forecasting,” in Discovery Science, Springer Nature Switzerland, Oct. 2023, pp. 567–581.
Read publicationPresentations & activities
Conferences, research visits, and moments with the team.