Currently climate change is one of the most challenging issues facing the ; Indeed, the humanity is already experiencing some negative effects of this change. That includes, rising in average temperature, shifts in the seasons and an increase frequency and severity of weather events. Furthermore, some side effects of the climate change are expected to exacerbate the impact of natural hazards. Fortunately, the key actors of the societies (business organisations, authorities, and citizens) are willing to develop strategies and taking appropriate actions for climate adaptation and mitigation. According to EC (European Commission), adaptation in this context “means anticipating the adverse effects of climate change and taking appropriate action to prevent or minimise the damage they can cause, or taking advantage of opportunities that may arise”. However addressing efficiently the climate change requires engineering a smart knowledge englobing reasoning capabilities and the key features, consequences and factors behind nature and human-induced climate change.
The aim of the SKEMACY project is to develop a scalable, open and interoperable knowledge-based framework. The framework will integrate required APIs and facilities for accessing and interacting with third-party platforms such as earth-observation framework: Copernicus, GEOSS, SeaDataNet and EMODnet…
The core of the SKEMACY framework will be structured around a multimodal data analytics toolkit. This toolkit will comprise machine-learning methods for sensing the environment, predicting outcomes of user options and scenarios, delivering recommendations and contextualised information ( causes and effects of different options and scenario). In collaboration with end-users, we will rely on available historical dataset for designing and training AI & machine leaning simulator to assist users (private and public organisation actors, citizens …) in elaborating appropriate strategies and actions for assessing, monitoring and mitigating climate change.
The toolkit will comprise a set of modules including multimodal information extractors, knowledge building and reasoning modules:
Multimodal information extractors (MIE): analyse wide range of raw data (traffic data, climate data …) and fuse the extracted information with already available and third-party information in order to identify consistent patterns and relevant features useful for producing actionable information. The MIE module will contains a set of dedicated tool such as: