Dr. Ravela develops succinct data-driven computational methods for natural systems that emphasizes the dynamic coupling between phenomenology and physics, simulation and observation, humans and algorithms, and data with models.
Current contributions include in the areas of modeling, inference, uncertainty quantification and cooperative autonomous observation of coherent fluids, fluid imaging, animal biometrics, natural hazard risk assessment and decision support. These contributions are enabled by methodological investigations in machine learning, nonlinear dynamics, stochastic systems science and computational physics.
A. Karpatne, H. A. Babaie, S. Ravela, V. Kumar, I. Ebert-Uphoff (2017), "Machine Learning for the Geosciences - Opportunities, Challenges, and Implications for the ML process", In Mining Big Data in Climate and Environment, SIAM SDM
S. Ravela (2016), A Non-Parametric Framework for Inference Using Dynamically Deformed and Targeted Manifolds, MS41, pp 60, SIAM AM