Data-Science competition for ecological data
Scaling-up ecological patterns and processes is crucial to understanding the effects of environmental change on natural systems and human society. We are piloting a Data Science Challenge to help scientist do this better by using remote sensing from low flying airplanes to infer the location and type of trees in forests. This will allow forests to be studied in detail at regional to global scales.
Anyone is welcome to participate. Work as teams or individuals. Sign up.
The competition is now closed. We will be running a new round on Summer 2018!
- Airborne remote sensing: High resolution hyperspectral imagery, higher resolution RGB imagery, and LiDAR data on plant height.
- Ground Data: Ground based measurements of tree size, location, and type
- Individual Tree Crowns: Ground based identification of tree crowns on remote sensing imagery.
- Crown Delineation: Estimate the size, shape, and location of individual tree crowns
- Alignment: Pair trees measured on the ground with those identified in remote sensing
- Classification: determine the species identity of each tree from remotely sensed data
Find out more
- Enter your email to hear more
- Read the full plan for the competition (details subject to change)
- Frequently asked questions
- We will back in touch on Summer 2018. We’ll be running a full version of the challenge next year.
About the Data Science Challenge
- Sponsored by the National Institute of Standards and Technology (NIST) Data Science Evaluation (DSE) Series and the Gordon and Betty Moore Foundation’s Data-Driven Discovery Initiative through grant GBMF4563.
- Organized by the Data Science Research lab, the WEecology lab, and Stephanie Bohlman’s lab all at the University of Florida.
- The data is collected by National Ecological Observatory Network (NEON) from the Ordway-Swisher Biological Station (OSBS) NEON site and by researchers at the University of Florida.