Skip to content

Painting the Ocean

David Lindo Atichati edited this page Feb 4, 2018 · 12 revisions

Design software to identify the fate and transport of an oil patch in the surfzone using drone imagery

Background

Unmanned aerial vehicles (UAVs) are relatively small, remotely operated aircraft that are becoming increasingly popular as environmental surveying platforms. Their ability to fly in any direction greatly simplifies launching and landing procedures, making them an ideal instrument for monitoring otherwise difficult-to access and highly dynamic areas, in particular surfzones.

The Surfzone Coastal Oil Pathways Experiment (SCOPE) examined the surfzone control on oil transport on a sandy, rip channeled beach with a crescentic outer bar system was performed on Fort Walton Beach, Okaloosa Island, Florida, in December 2013. Several done missions were flown with varying Rhodamine water tracing dye releases.

Evolution of a dye cloud over a domain of (O)(100 x 100 m). Photo credit to Dr. Reniers and Dr Brouwer

The overarching goal here is to use machine learning and data mining approaches (eg artificial neural networks) to predict dispersion and advection estimates of pollutants in the surfzone.


Solutions

    • A "deep dream" oil spill generator. Can we train a deep learning neural network in such a way as to help better understand images of oil spills?
  • Anything else you can think of!

Resources


Challenge owner: David Lindo