The Call for Code Spot Challenge for Wildfires has completed. The objective was forecast wildfires in Australia during the month of February 2021 in order to better understand the application of machine learning techniques in this domain. We shared an extract from Weather Operations Center Geospatial Analytics component (PAIRS Geoscope) with some of the data going back to 2005, and sessions to help you get started. The challenge kicked off on 12 November 2020, and ran until 1 March 2021, with the final submissions made on 2 February 2021. The challenge had multiple stages (which you can read about on the landing page) to enable the teams to get accustomed to the leader-board and datasets. The final submissions (in the form of a CSV) from the teams were to predict the size of the fire area in km square by region in Australia for each day in February 2021.
We are thrilled to share the a snapshot of final leader-board below and many congratulations to all teams who appear. As you can see the leading teams' results are very close!
We are planning some follow-on activities:
The Contest landing page http://ibm.biz/cfcsc-wildfires
The Contest GitHub https://github.com/Call-for-Code/Spot-Challenge-Wildfires
The Contest leaderboard http://ibm.biz/cfcsc-wildfires-lead
Education materials to get started with the Call for Code Spot Challenge for Wildfires
The Finale : Call for Code Spot Challenge for Wildfires
Call for Code Spot Challenge for Wildfires Predictions: Comparing approaches
Slack Workspace http://callforcode.org/slack Channel #cfcsc-wildfires
Helpful blog https://medium.com/ibm-data-ai/predicting-australian-wildfires-with-weather-forecast-data-8d1cc983c863