DEEP BERLIN AI for Good Hackathon
2.5 days of using machine learning to support climate action by predicting and preventing forest disasters
April 24th – 26th, 2020
Our AI for Good Hackathon is back for its second edition, with the mission of using machine learning to support climate action efforts, using ML models and computer vision to tackle challenges around forest fires and air quality.
Register to attend
Registration closes on 31.03.2020
Our planet is already suffering the consequences of climate change. We have recently seen the devastating consequences of bush fires out of control in Australia, where tens of lives have been lost, 2600 homes have been destroyed, and half a billion animals have been impacted. Researchers have found that as temperature rises, so does the risk of wildfires like this may become common around the world.
There is an evident urgent need to address the effects of climate change, and AI for Good can be a driving force to prevent disasters and help us act at the right time to preserve our planet and save lives.
Satellite imagery and remote sensor data present an opportunity to develop machine learning models that allow to not only predict potential threats and plan accordingly, but also to implement sustainable solutions for the future. By using computer vision and image analysis for instance, robust predictions can be made about forest areas, their risk, and potential within the area.
By modeling predictive actions for fire resilience, we can be able to provide immediate relief in case of disasters and in the best case scenario, prevent them altogether.
- Build machine learning models that would predict the likelihood of a severe disaster occurring: bush fires, etc.
- Predict the impact of those disasters
- Build machine learning models that allow to have preventive measures in place in case of disaster
- Predict the impact of preventive measures in place and formulate best practice approaches
- and more!
You will work in cross-functional teams, to tackle one or more of the following tasks based on your expertise:
- Categorisation of trees based on satellite imagery
- Estimating tree height based on ML models simulating LiDAR
- Presence (or not) of trees and relationship with air quality among other factors
- Trees dependent on time for a given area
- Carbon density
- Fire prediction and developing predictive actons for fire resilience
A list of datasets available can be found here.
What’s in it for you?
- Invitation to Slack workspace to collaborate with your team
- 2 and a half days of coding to help tackle climate change effects
- Collaborative work in teams of AI experts
- Access to AWS ML services rapid prototyping
- Receive guidance from AWS Solution Architects
- Being part of a community using AI for Good
- Fully remote
From 17:00, opening keynotes and introduction to the topic and the challenge, team formation and dinner.
Full day of coding and hacking in teams.
Last hours of coding and hacking, integration and testing, and preparing final presentations starting at 15:00 and ending at 17:00.