Day 4

Detailed paper information

Back to list

Paper title AI based method for studying the physical changes in the coastal area from Sentinel- 2 imagery. Case study: Swedish coast.
  1. Selima Ben Mustapha Swedish National Space Agency Speaker
  2. Nosheen Abid Luleå University of Technology
  3. Nuria Agues Paszkowsky Research Institutes of Sweden (RISE)
  4. Tim Cedervall Royal Institute of Technology (KTH)
  5. György Kovács Luleå University of Technology (LTU)
  6. Rickard Brännvall Research Institutes of Sweden (RISE)
  7. Tobias Edman Swedish National Space Agency
Form of presentation Poster
  • C1. AI and Data Analytics
    • C1.04 AI4EO applications for Land and Water
Abstract text A novel Artificial Intelligence (AI) method based on Earth Observation (EO) data, for the identification of physical changes along the Swedish coast, especially physical constructions, such as piers and jetties is introduced. Using Sentinel-2 data in an Open DataCube (ODC) environment, we first detect the coastline using advanced convolutional (U-Net) models, then we detect the rate of change (and whether the change is permanent or temporary), lastly, we detect small constructions along the shoreline. Using Bayesian statistical inference, we are able to study time series and discern between temporary changes or noise, and permanent changes. The long-term goal is to transform the methodology into a permanent monitoring service that can help municipalities to combat environmental crime, for example to identify illegal dredging and excavation activities affecting the marine environment and ecosystem. In addition, there is an added value of a Copernicus-based tool for municipalities and regions. This will support marine coastal planning regarding the dynamics of the coastal zone and show the robustness of AI-based technology for coastal and marine research.