A Guideline for a Resilient and Economically Viable Emergency Response Network: Securing the 15-Minute City Transition (GREAT-15)

Description:

While the 15mC model successfully prioritizes proximity for daily services, its current framework overlooks the essential need for rapid, reliable emergency care for human-made disasters, leaving a dangerous vulnerability in urban safety.

To bridge this gap, this initiative employs a science-backed and rigorous three-stage methodology. In the forecasting phase, collected datasets are analyzed, pre-processed, and then future incidents are forecast via cutting-edge machine learning (ML) tools. Additionally, risk mapping is conducted, and, core uncertainties of the system such as variable travel speeds and path availability are formulated. Then, robust optimization phase generates strategic and tactical plans that are mathematically immunized against predefined uncertainties. Lastly, these plans are subsequently validated by a comprehensive and data-driven simulation framework, which conducts dynamic stress-tests against stochastically generated incident forecasts. This integrated methodology ensures all outputs are cost-minimizing while guaranteeing performance and resilience, providing a scientifically grounded foundation for the transition.

Central to this methodology is a flexible Decision Support System (DSS). Its architecture enables stakeholders to model diverse scenarios by integrating customized inputs, including budget constraints, risk tolerance levels, and specific policy goals. The system processes these parameters to generate compliant, tailored plans. This adaptable framework ensures the resulting strategic and tactical plans are directly aligned with local priorities and are robustly designed to withstand core operational uncertainties.

Requirements:

• A governmental authority that provides real data for the validation phase.

• A governmental authority that is interested to reshape its emergency response network through the project.

• A governmental authority and/or individual expert that is willing to feed the project with know-how and expertise.

• Individual experts need to demonstrate their expertise.

• A partner demonstrating strong scientific and practical background on machine learning such as deep learning, time series mining, etc.

• A partner with solid experience in back-end coding, front-end coding, and/or database building.

• A partner having a strong expertise in environmental issues.