Introducing the EuMigraTool (EMT)

The EMT is a solution-oriented tool with two main functions: a) predicting migration flows (using the models above) and b) detecting risks of tensions related to migration. CERTH, who is also developing ICTs in the NADINE project, will be the leader of the development of the EMT. The analysis of data conducted in WP3, WP4 and WP5 will be necessary to achieve these two main outcomes.

The backend of EUMigraTool will comprise two complementary approaches to simulation and forecasting. The first approach will be based on agent-based modelling, while the second approach will rely on deep learning, which is currently the predominant paradigm in artificial intelligence. In ITFLOWS specific deep learning architectures will be researched and developed based on recent bibliography that will enable the extraction of semantic information for several sources of information. From a technical perspective, the extraction of semantic information translates to modelling the joint probability distribution of events that drive migration with input signals from information sources.

The EUMigraTool will include analysis of media content from tv-news (video content), web-news and social media (text content) using deep learning and proposing novel deep architectures in generative modelling and forecasting using sequential data. Predictions will incorporate algorithms that consider the two key challenges associated with prediction of migration: (a) Adequate selection of relevant data sources, and (b) correct selection of the potential drivers to be monitored and to the warning thresholds to be set.

The initial design of the visualization maps will be the following:

Join ITFLOWS newsletter

Get up to date newsletters direct to your inbox on events and news

CEPSCITUBOpenMigration PolicyRed CrossOxfamITIBrunelIFWIAIFIZCSDTerracom