CRISP – Crisis Response and Intervention Supported by Semantic Data Pooling

The increasing frequency of natural disasters, caused by severe weather phenomena and fueled by climate change, has become an undeniable reality. It is thus highly likely that in our post-pandemic society disaster and crisis management will face increased challenges in managing such natural disasters. CRISP aims to address these challenges in a data-driven manner, enabling more effective crisis response and intervention, considering both the short-term management of disasters as well as long-term economic impact assessments, at fine-grained regional and temporal granularity. CRISP will shed light on the impact of crisis response and intervention strategies in close to real time by creating rapid feedback loops and ingesting data from multiple heterogeneous sources. The result is a comprehensive and continuously updated data pool, which represents a key asset for semantic modelling and impact forecasting. CRISP will not only increase the transparency of crisis response and intervention processes, but also capture how the resulting outcomes are being perceived by citizens (through community forums, social media, etc.) and professional stakeholders (news, surveys and reports, etc.). These feedback loops are crucial to increase the effectiveness of emergency response services (through realtime data interchange with state warning centers, for example). They will also improve existing workflows by highlighting actions that do not achieve desired outcomes or trigger unintended consequences.

To this end, CRISP will extract and classify disaster signals and perceptions from news and user-generated social media content, leveraging and extending previous work of webLyzard technology for the United Nations Environment Programme and the U.S. Climate Resilience Toolkit of the National Oceanic & Atmospheric Administration (NOAA). CRISP will combine this data with weather and climate observations of Austria’s National Weather and Geophysical Service (ZAMG), providing warnings and forecasts for disaster control authorities and rescue organizations, as well as data from municipalities and regional administrations serviced by the Centre for Public Administration Research (KDZ). The data pool will also include structured and unstructured socio-economic data, from Open Government Data. The semantic integration of these data assets will be performed by means of a unified Knowledge Graph (KG). This unified KG will enable researchers of the Complexity Science Hub (CSH) to build complex systems models and simulations of hypotheticals and counterfactuals in order to derive more precise predictive impact assessment models and prescriptive models for better emergency response effectiveness.

CRISP is conceptualized as an open, inclusive platform that provides a flexible portfolio of information services, based on a decentralized data ecosystem built by nexyo, which enables integrated access to continuously updated sources from various stakeholders, without sacrificing data sovereignty. Active participation of these stakeholders is crucial to the success of CRISP (a Stakeholder Forum will guide the project through all phases, from the co-creation of requirements to the final evaluation of the prototype). Given its inherent flexibility and modular structure, CRISP represents an opportunity to build the basis for a generic and radically new ICT of the Future solution, potentially useful to many different scenarios that require data pooling for joint AI model development – in the public sphere, corporate settings or for Austrian and international research projects.

Project Start: 01 December 2021
Duration: 36 months
The CRISP project is funded by the Austrian Federal Ministry for Climate Action, Environment, Energy, Mobility and Technology (BMK) via the ICT of the Future Program – FFG No 887554.