Machine learning for meteorological time series
We are investigating machine learning methods for time series analysis in the contexts of meteorology and finance.
PiMLB
Physics informed Machine Learning for biological Behavior
Our group blends physics, machine learning and biological behavior to ask how organisms acquire and process complex sensory information from their fluid environment to guide behavior. We deploy state-of-the-art simulations and asymptotic models to portray the fluid flows surrounding living organisms. These data feed machine learning algorithms that model behaviors ranging from sensory predictions and navigation to spore dispersal to the formation of complex bacterial colonies. We are interested in model organisms like mice and bacteria as well as less studied organisms like higher fungi, octopus and jellyfish and real weirdos, like piranhas and sea robins (a fish with legs!)
