Modeling & AI
Predicting the state of our ocean has remained a challenge despite the advent of mathematical methods that enable the used of remote and in-situ observations to constrain numerical models toward the observations, making ocean models more accurate. Despite these advances, the usefulness of ocean numerical model prediction is limited to 48 hours. In our lab, we have been developing machine learning (AI) based model to predict ocean dynamics and we have pushed the limits of useful forecast to days and weeks. We have also developed AI tools and applications (FADAR) that enable the rapid processing of acoustic data to detect the presence of soniferous species, which can be used to search for fish spawning aggregations in our coastal ocean.
Machine Learning
NSF-CSIRO: Towards Interpretable and Responsible Graph Modeling for Dynamic System. This project strives to build a graph learning and interpretation framework for dynamic systems by combining sensor pattern discovery, node interaction and network functionality analysis, and physics- and knowledge-informed learning. The project will propose new algorithms for modeling and understanding large-scale dynamic systems using graphs, as well as develop a prototype for domain experts to analyze their data, explain what is currently happening in the system, understand the resulting consequences, and provide possible mitigation strategies.
Marine Energy
Research, Development and Education to Accelerate the Transition of Marine Energy Technologies to Market, DoE. This project involves the quantification of the U.S.’s ocean current resource and development of ocean current prediction tools using AI.
Marine Biodiversity
A Machine Learning Framework to Measure Marine Biodiversity at Fish Spawning Aggregation Sites, NOAA. This research is conducted through the development of machine learning research tools to characterize marine resources and their habitat, while improving the usability of passive acoustic observations toward the protection of fish spawning aggregations and the management of marine protected areas.