A1 Refereed original research article in a scientific journal
AI-assisted Real-Time Spatial Delphi : integrating artificial intelligence models for advancing future scenarios analysis
Authors: Calleo, Yuri; Taylor, Amos; Pilla, Francesco; Di Zio, Simone
Publisher: Springer Nature
Publication year: 2025
Journal: Quality and Quantity
Journal name in source: Quality & Quantity
ISSN: 0033-5177
eISSN: 1573-7845
DOI: https://doi.org/10.1007/s11135-025-02073-2
Web address : https://doi.org/10.1007/s11135-025-02073-2
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/484696360
The Real-Time Spatial Delphi represents an innovative method tailored to navigate the complexities of uncertain spatial issues. Adopted in Future Studies contexts, this method excels in developing spatial scenarios and leveraging the collaborative insights of experts within a virtual environment to achieve a consensus regarding territorial dynamics. However, while this method yields invaluable spatial insights and statistical metrics, the final outputs often remain confined to expert circles due to their technical complexity. In addition, the outcomes often lack direct policy implications, as they primarily provide an expansive overview of potential future scenarios. In response to these challenges, this paper proposes integrating text-to-image models and generative pre-trained transformers, into the Real-Time Spatial Delphi process. By adopting these advanced tools during the visioning and planning phases, the method endeavors to transform spatial judgments into visually immersive scenarios, while concurrently crafting actionable policy recommendations suitable for evaluation. To validate the approach, we present a case study in the environmental context, for the cities of Cork, Galway, and Limerick, located in Ireland. Through this application, we contribute to Futures Studies by illustrating the method’s capacity to envision plausible futures in the form of real images, considering the formulation of policies to support decision-making.
Downloadable publication This is an electronic reprint of the original article. |
Funding information in the publication:
Open Access funding provided by the IReL Consortium.
The work carried out in this paper was supported by the project SCORE, which has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 101003534.