Complex decision-making in fields such as urban planning, forest management, and disaster risk reduction involves multiple, often conflicting criteria, as well as spatial and temporal dynamics. Traditional methods fall short in capturing this complexity, especially under uncertainty and evolving conditions.

This project aims to develop a digital spatio-temporal MCDA tool that integrates Geographic Information Systems (GIS), real-time data processing, and probabilistic methods to enhance decision quality. The tool will support structuring decision problems, applying advanced MCDA methods (e.g., ranking, sorting, clustering), managing uncertainty, and visualizing how spatial patterns evolve over time.

The project follows a three-phase approach:

1. a review of existing methods and tools
2. development of the InSTIM prototype, and
3. validation through real-world case studies in climate-resilient urban planning, energy transition, forest management, and disaster mitigation.

Continuous stakeholder involvement will ensure the tool's usability and practical value.