Computer models play an essential role in modern society. Learning models from data is not sustainable due to the ever-growing requirement of computational power and training data. I will develop groundbreaking methods that will learning model from data much faster and with a much smaller carbon footprint than currently needed.

Naval vessels are valuable national assets, so it is important to maximize their efficiency, operability, and longevity. These aims can be accomplished by utilizing smart-sensing systems onboard, which keep track of the loading a vessel experiences, the resulting response of a vessel, and the current structural health state due to that loading and response over its lifetime. With these parameters, it is possible to allow for vessel service life extension, to maximize operability using optimized maintenance schedules and to improve the design of future vessels. Such systems allow for leaner and more efficient defense spending and safer operations for crew.