The EMP2 project set out to create a machine-learning based model that could be used to, for example, make predictions about the weather or track atmospheric dynamics. This model was named AtmoRep.  AtmoRep can be adapted to several uses, including short-term weather forecasting, downscaling, bias corrections, spatio-temporal interpolations and probabilistic nowcasting. The AtmoRep model is now being used in several new projects.

Find out more here:

Improving Weather Predictions with AI and Tackling Global Hunger

Industries this type of project can also apply to:

• Weather forecasting

• Earth observation

• Atmospheric tracking

• Humanitarian sector (crop yield predictions, etc.)

• Insurance (assessment of climate change effects)

• Risk assessment (floods, droughts, fire, etc.)

Key features of the technology:

• One of the first machine-learning based models for earth system modelling

• A unique element is that the model is stochastic, meaning that it can factor in random variables or processes in atmospheric conditions, mimicking the real-life complexity and arbitrary nature of atmosphere dynamics