Newsroom
USF researchers win top prize in the Upscaling Euro Data Cube COVID-19 contest organized by the European Space Agency
October 1, 2020
Mauricio Pamplona Segundo, CSE postdoctoral researcher at the USF Institute for Artificial Intelligence + X (AI+X), Cole Hill, CSE graduate student, and Sudeep Sarkar, CSE Professor and AI+X co-director, partnered up with Rodrigo Minetto, UTFPR Professor (Brazil), Allan Pinto, UNICAMP postdoc researcher (Brazil), and Ricardo Da Silva Torres, NTNU Professor (Norway) to participate and win the COVID-19 Custom Script upscaling competition organized by the European Space Agency (ESA), in coordination with the European Commission.
This content was launched back in April 2020 for ideas on how satellite data could help monitor and mitigate the COVID-19 situation as the world organizes and adapts to get back to normal. The goal was to seek signatures for:
- Economic operators' activity (e.g., factories, supermarkets, transport networks, oil refineries, commercial ports)
- Human activity distribution (e.g., parked car distributions over urban areas, social distancing estimations)
- Agriculture activity (e.g., unattended fields and crops, disruptions due to supply chain issues, things that may contribute to the mitigation of problems appearing in 6 months from now)
The ESA ran the contest in phases. In the first phase, the USF Team had won the prizes for the best weekly and monthly ideas for their script that tracked airplanes in the air and on the ground. In the final phase of the competition, the developed algorithms had to be scaled up and process data across Europe. The solution had to be integrated into the l.
The submitted USF solution entitled "Measuring Airport Activity from Sentinel-2 Imagery to Support Decision-Making during COVID-19 Pandemic" received the top prize - Best Contribution award. The presented solution first uses AI-based pattern recognition to detect flying airplanes over a 2300 square miles area around each of the 30 busiest European airports using satellite images. Then, it analyzes detections over two years to accurately estimate the impact of COVID-19 on human traveling activity.
To learn more about the final phase, go .
See the for the overall details.
partially funded this research and development.