Global AI and Data Science

Summary

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:

• Through March 2021 - Publish a blog comparing approaches that  teams use to make the predictions  (if any of the participating teams want to contribute, please contact  malaika@us.ibm.com )
  • https://developer.ibm.com/technologies/artificial-intelligence/blogs/call-for-code-spot-challenge-for-wildfires-predictions-comparing-approaches/
• 5 Apr 2021 - a crowdcast session summarizing and comparing some of the methods used in the challenge. The students who are using the Wildfires Challenge as a case study as part of their class will also join us.
• 26 Apr 2021 - a crowdcast session with Team Prometeo
• Join Call for Code Global Challenge 2021 - Register : https://callforcode.org/global-challenge/
  
  • This year's themes include clean water and sanitation, zero hunger, responsible production, green consumption

Many Congratulations to the Winning Team Data Warriors

The Crowdcasts So Far & Upcoming

• Nov 23 about notebooks and exploring the datasets https://www.crowdcast.io/e/call-for-code-spot/ 
• Nov 30 about datasets and how to submit to leaderboard  https://www.crowdcast.io/e/call-for-code-spot-2/ 
• Dec 7 about how to use AutoAI with the data https://www.crowdcast.io/e/call-for-code-spot-3
• Jan 11 introducing the Contest and Leaderboard https://www.crowdcast.io/e/call-for-code-spot-4/
• Jan 18  hear from Team WildFireNet who participated in another hackathon https://www.crowdcast.io/e/call-for-code-spot-5
• Jan 25  to hear about Hypothesis Testing for Time Series  https://www.crowdcast.io/e/call-for-code-spot-6
• Feb 22 to hear from IBMers building models for the wildfires challenge https://www.crowdcast.io/e/call-for-code-spot-7
• Apr 5 to hear from the leading teams https://www.crowdcast.io/e/predicting-australian/ and from students at the University of Sharjah using the spot challenge as a case study
• Apr 26 to hear from Prometeo – Firefighters Health Platform, a Call for Code Open Source Project https://www.crowdcast.io/e/prometeo-a-call-for-code/
• Join Call for Code Global Challenge 2021 - Register : https://callforcode.org/global-challenge/
  
  • This year's themes include clean water and sanitation, zero hunger, responsible production, green consumption

• 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