Automated Detection of Hazards
Countless phenomena such as floods, fires, and algae blooms routinely impact ecosystems, economies, and human safety. Your challenge is to use satellite data to create a machine learning model that detects a specific phenomenon and build an interface that not only displays the detected phenomenon, but also layers it alongside ancillary data to help researchers and decision-makers better understand its impacts and scope.
Riganryu
Summary
In Japan, we are told that if you swim in the ocean after mid-August, you will be a victim of being dragged into the sea. It is said that this is because the spirits that return in August try to take you to the other side of the ocean when they return to the other world.But is it true?It was found that about 50% of people who were involved in water-related accidents were often swept away from the shore by the rip current.By finding the traces of the characteristic shape that the rip current leaves on the shore, we thought that we could tell people whether it is a dangerous day or a safe day for the coast by using satellite data.
How We Addressed This Challenge
- Notify whether there is a rip current at the beach and tweets related to the beach.
- About 50% of the people who were involved in accidents at sea in Japan were caused by rip currents.
- As going to the beach in summer is a standard practice, we want to provide information about the rip current so that people can play in the sea safely.
How We Developed This Project
- Collect data on the occurrence of breakaway currents and perform machine learning.
- Collect satellite images of a designated beach every day and have the AI determine whether a rip current has occurred and the degree of danger based on the shape of the rip current.
- Output the information determined by the AI into a JSON file.
- The application reads the JSON file and displays information on the beach and the occurrence of rip currents on the map UI.
How We Used Space Agency Data in This Project
- Collect data on the occurrence of breakaway currents and perform machine learning.
- Collect satellite images of a designated beach every day and have the AI determine whether a rip current has occurred and the degree of danger based on the shape of the rip current.
Project Demo
Data & Resources
- https://apps.sentinel-hub.com/eo-browser/
- https://www.eorc.jaxa.jp/cgi-bin/jasmes/sgli_nrt/index.cgi
Tags
#rip_currents #sentinel #
Judging
This project was submitted for consideration during the Space Apps Judging process.