Building a Digital Twin Application for Climate Extremes: Using the interTwin Digital Twin Engine

Weather Extremes and their impacts are getting a lot of attention lately, because their occurrence, severity and spatial coverage are increasing and will likely increase further towards the mid and end of the century. Many countries are experiencing significant impact of those extremes due to climate change. It becomes more and more important to better assess the change of characteristics of those extremes according to users and society needs.

It is a challenge to detect and characterize weather extremes for the future climate in all available and relevant climate simulations. A novel approach and methodology is being developed to detect and characterize the changes in weather extreme events using Artificial Intelligence (AI). This is a generic method based on Convolutional Variational Autoencoders (CVAE). This deep learning technique, that uses neural networks, can process large climate datasets much faster than traditional analytical methods.

Another big challenge is to develop on-demand real-world applications that users can manipulate to explore what-if scenarios. Data does not necessarily only come from one research infrastructure (RI), but can also come from several RIs because addressing climate extremes involves climate change impacts that depend on other relevant datasets. Developing robust Digital Twin applications takes a lot of development time. In the context of the interTwin project, a very flexible Digital Twin Engine (DTE) is being developed and implemented. It provides Core Components that can be used by several DT applications from very diverse scientific domains. Applications using AI techniques can also benefit from advanced capabilities using minimal development. It also provides almost automatically generic features and capabilities. This DTE framework acts as an accelerator in order to rapidly develop user-oriented DT applications in diverse scientific domains. 

In this presentation, the interTwin DTE will be presented, and it will be shown how it can be easily used to leverage an existing tool in order to create a DT application. Some results of the method applied on Global Coupled Climate Model datasets will be shown for several greenhouse gas scenarios, over Western Europe.

This project (interTwin) has received funding from the European Union’s Horizon Europe research and innovation programme under grant agreement N°101058386.