This hands-on workshop introduces satellite-derived shorelines as a tool for coastal mapping and shoreline change analysis. Participants will learn how coastlines can be identified from satellite imagery, what factors influence accuracy, and how shoreline datasets can be used to monitor erosion and accretion over time. Participants will work through a guided Jupyter notebook in which they build, train, and evaluate two versions of a simple neural network: one purely data-driven and one incorporating physical constraints. They will compare model outputs, visualize predictions, and discuss the trade-offs between flexibility and physical consistency.

Prerequisites

• Laptop with Python/Jupyter installed.
• Recommended resources: https://github.com/kvos/coastsat

Learning Objectives

By the end of this workshop, the goal is for attendees to be able to:

• Explain how satellite imagery is used to map coastlines.
• Describe the basic principles behind satellite-derived shorelines.
• Visualize and interpret shoreline change through time.
• Recognize the strengths, limitations, and applications of satellite-derived shoreline datasets.

Tools Used

• Python
• Jupyter Notebook
• GitHub
• Pandas