IRES: Track II: The Coastal Processes & Machine Learning Advanced Studies Institute

University Of North Carolina Greensboro, Greensboro NC

Investigators

Abstract

Coastlines host population centers, infrastructure, diverse ecosystems, and provide valuable tourism and recreational opportunities. Coastal regions are also prone to hazards such as storms, sea level rise, and chronic erosion. There is a growing volume of data available to scientists who study coastal processes and the future dynamics of coastlines. A range of new tools and methods that can be used to extract knowledge and insight from these data, especially machine learning techniques. However these new methods are not typically part of the graduate curriculum for coastal scientists. This project is focused on developing an advanced studies institute (ASI) in Auckland, New Zealand to teach machine learning methods to 20 US graduate students studying coastal processes and coastal geomorphology. The ASI participants are the next generation of US coastal scientists, who will get jobs in industry, agency, and academic settings. The ASI is taught by several scientists who focus on applying machine learning methods to coastal problems. The institute directly impacts 20 US graduate student participants, and provides a focused experience for them to develop machine learning skills in a coastal context. The ASI is designed to leverage resources that are unique to New Zealand, including multiple high-fidelity datasets. All course materials for the ASI will be built with open source software and stored in open repositories to facilitate use in other coastal teaching and learning settings beyond this ASI. A project evaluation will investigate the ASI learning goals (post-event and longitudinally). ASI outcomes and learning materials will be disseminated in print, online, and at scientific conferences. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.