Summary
Artificial Intelligence (AI) is a key driving force behind the new round of scientific and technological revolutions and industrial transformations, especially in its integration with big data, which has brought significant technological advantages to oceanography. Traditional oceanographic modeling often relies on prior knowledge, but now, we can more reliably and efficiently convert massive amounts of observational data into valuable information through data-driven methods. This transformation enables deeper exploration of marine phenomena and processes in oceanographic research. This seminar will detail the application of AI technology in oceanography, including information extraction on mesoscale eddies, internal waves in the ocean, sea ice, ships, oil spills, and flooding caused by typhoons, among others. Additionally, we will focus on lightweight forecasting in areas such as small-scale internal waves, mesoscale sea level changes, and large-scale equatorial instability wave predictions and modeling. These latest research findings will provide powerful tools and methods for oceanographic research to more comprehensively understand and predict marine and atmospheric phenomena.
Brief biography
Xiaofeng Li earned his Ph.D. in Physical Oceanography at North Carolina State University, Raleigh, NC, USA, in 1997. He was with the National Ocean and Atmospheric Administration (NOAA), USA, from 1997 to 2019, where he developed many operational satellite ocean remote sensing products. He is now in the Institute of Oceanology, Chinese Academy of Sciences. His research interests include ocean remote sensing, the application of artificial intelligence in oceanographic studies, big data analytics, and satellite image processing. Dr. Li has published about 200 peer-reviewed papers and holds editorial positions as an Associate Editor for the IEEE Transactions on Geoscience and Remote Sensing and an Editor for JGR: Machine Learning and Computation. Dr. Li is a Fellow of IEEE. https://www.researchgate.net/profile/Xiaofeng_Li23.