Akademik Veri Yönetim Sistemi
11th International Conference on Modelling and Simulation for Autonomous Systems, MESAS 2024, Chania, Yunanistan, 1 - 03 Ekim 2024, cilt.15761 LNCS, ss.227-241, (Tam Metin Bildiri)
Decision-makers recognize that strategic shocks (threats) cannot be fully avoided, prompting a shift toward understanding resilience—preparing for, absorbing, recovering from, and adapting to such shocks. In 2022, a prototype model was developed to evaluate a country's resilience using system dynamics. During testing, the need for a strategic shock parametrization mechanism based on open-access data was identified. This led to the development of the Joint Operations Area Resilience Model, which integrates Big Data and Machine Learning into system dynamics, improving the previous model. A key feature of the new model is its open-access data mechanism for strategic shock parameters. This paper focuses on the integration of Big Data and Machine Learning into the model and the development of a web-based application that automatically scrapes real-world data on strategic shocks (e.g., blackouts, pandemics, cyber-attacks) from open sources. The application processes this data and provides shock input values (magnitude, time, and duration) for the system dynamics model. Users can verify and validate the model through experiments and conduct real-time what-if analyses based on actual shock scenarios. Although data availability and reliability remain challenges, the model's potential to support resilience decision-making is enhanced by expert validation, timely feedback, and reliable data. The main benefit of the project is its shift from a solo simulation approach to a real-time decision support system powered by open-access data.