DeepCube H2020 RIA

Explainable AI pipelines for big Copernicus data

deepcube logo is just textDeepCube project leverages advances in the fields of artificial intelligence (AI) and semantic web to unlock the potential of big data from Copernicus. DeepCube aims to address problems of high socio-environmental impact and enhance our understanding of Earth’s processes correlated with climate change. The project employs ICT technologies such as the Earth System Data Cube, the Semantic Cube, the Hopsworks platform, and a state-of-the-art visualisation tool, integrating them into an open interoperable platform that can be deployed in cloud infrastructures and high-performance computing. DeepCube will develop deep learning (DL) architectures that extend to non-conventional data, apply hybrid modelling for data-driven AI models that respect physical laws, and open up the DL black box with explainable AI and causality.

INFALIA in DeepCube
INFALIA leads the development of visualization tools for non-EO data. More specifically, Infalia is responsible for the collection of social media data as a complementary non-EO source of information, their automatic analysis to extract high-level knowledge, and their visualization in an intuitive way allowing alternative views, multiple filtering options and advanced visual analytics.

INFALIA aims at developing user interfaces that will demonstrate the collected social media data, offering multiple ways of visualisation and filtering. An online Web application will be designed and developed for displaying the data that will be served by an API. The API will communicate with a database where collected social media data will be stored so as to fetch the posts. Users will be able to visualise the posts either as a scrollable list of posts or as pop-ups on a map. In both views, analysis results, i.e. detected locations and visual concepts, will also be displayed per post. Moreover, the application will provide filtering capabilities, e.g. the option to show data published in a certain time period or to hide posts that do not contain an image.

Call: H2020-SPACE-2020
Budget: € 3 999 687,50
Topic: DT-SPACE-25-EO-2020 - Big data technologies and Artificial Intelligence for Copernicus
Type of action: RIA - Research and Innovation action
Duration: Jan 2021 – Dec 2023