## Goal of the Competition

Contrails are clouds of ice crystals that form in aircraft engine exhaust. They can contribute to global warming by trapping heat in the atmosphere. Researchers have developed models to predict when contrails will form and how much warming they will cause. However, they need to validate these models with satellite imagery.

Your work will help researchers improve the accuracy of their contrail models. This will help airlines avoid creating contrails and reduce their impact on climate change.

  

## Context

  

Contrail avoidance is potentially one of the most scalable, cost-effective sustainability solutions available to airlines today. Contrails, short for ‘condensation trails’, are line-shaped clouds of ice crystals that form in aircraft engine exhaust, and are created by airplanes flying through super humid regions in the atmosphere. Persistent contrails contribute as much to global warming as the fuel they burn for flights. This phenomenon was first figured out 75 years ago by military airplanes with the goal to avoid leaving a visible trail. About 30 years ago, climate scientists in Europe began to understand that the contrails blocked heat that normally is released from the earth overnight. They have built powerful models, based on weather data, to identify when contrails will form and how warming they will be. Their research has been validated by other labs as well and it is now well accepted that contrails contribute approximately 1% of all human caused global warming. The motivation behind the use of satellite imagery is to empirically confirm the predictions from these models. With reliable verification, pilots can have confidence in the models and the airline industry can have a trusted way to measure successful contrail avoidance.
![](https://storage.googleapis.com/kaggle-media/competitions/Google-Contrails/waterdroplets.png)
*Image courtesy of Imperial College*

Your work will quantifiably improve the confidence in prediction of contrail forming regions and the techniques to avoid creating them. 

Google Research applies ML to opportunities to mitigate climate change and adapt to the changes we already see.  We have run research projects in fusion energy plasma modeling, wildfire early detection, optimal car routing, and forecasts for climate disasters. 

## Acknowledgments

MIT Laboratory for Aviation and the Environment led by MIT Professor Steven Barrett
Satellite images are from NOAA GOES-16, see more in https://www.goes-r.gov/.
> **This is a Code Competition. Refer to [Code Requirements](https://www.kaggle.com/c/google-research-identify-contrails-reduce-global-warming/overview/code-requirements) for details.**