A hybrid expert-AI pipeline for constructing and characterising urban resilience indicator dependency networks

Abstract
Characterising the interdependencies among urban resilience indicators is critical for effective governance, yet it remains constrained by the gap between qualitative policy constructs and quantitative system models. This paper presents a hybrid framework for constructing and characterising urban resilience dependency networks that integrates expert knowledge with transformer-based semantic inference. We synthesise 451 measurable sub-indicators from eleven global frameworks into the Urban System Abstraction Hierarchy (USAH), a reproducible graph dataset of 40 indicators across seven socio-economic domains, spanning institutional, economic, and social systems where earlier implementations stop at physical ones. Sentence-transformer embeddings project each indicator into a high-dimensional semantic space, and these are combined with an expert-derived prior to retain only dependencies supported by both semantic and operational evidence, yielding a directed dependency graph. Complex network analysis of the Vancouver case study shows a small-world topology, a modular structure in which governance-related indicators form a tightly coupled core, and a hub-sensitive robustness profile. Combining directional and positional centrality, the analysis assigns each indicator a functional role, anchor, bridge, peripheral driver, stabilizer, or receiver, distinguishing indicators that drive downstream domains from those that accumulate system state. The pipeline produces reproducible, internally consistent system representations that are transferable across cities and applicable to downstream policy analysis and network-based resilience modelling.
Similar content being viewed by others
Acknowledgements
The authors declare that the University Canada West Discovery Research Grant partially funded this research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A The URSA Project
This paper is part of a multi-phase research initiative called the URSA Project, which aims to address socio-economic urban resiliency in Vancouver.Footnote 1 The project has five mosaics, as described in Table A1.
Appendix B Indicators structural roles
Table B2 presents the numerical values of the Driver-Receiver Index (DRI), betweenness centrality ($C_B$), closeness centrality ($C_C$), and the assigned structural roles for each indicator node. These metrics collectively characterise the functional role of each indicator within the constructed dependency graph.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/
About this article
Cite this article
PourmoradNasseri, M., Albadvi, A. A hybrid expert-AI pipeline for constructing and characterising urban resilience indicator dependency networks. Appl Netw Sci (2026). https://doi.org/10.1007/s41109-026-00831-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41109-026-00831-1

* The framework integrates expert knowledge with transformer-based semantic inference to characterize urban resilience dependency networks.
* Forty indicators are synthesized into the Urban System Abstraction Hierarchy (USAH) across seven socio-economic domains.
* The process involves projecting indicators into a high-dimensional semantic space using sentence-transformer embeddings.
* Expert-derived priors are combined with semantic evidence to determine dependencies, yielding a directed dependency graph.
* Network analysis of the Vancouver case study showed a small-world topology and a modular structure.
* Governance-related indicators form a tightly coupled core in the network.
* The analysis identifies functional roles for indicators, including driver, anchor, bridge, peripheral driver, stabilizer, or receiver.
* Metrics used include Driver-Receiver Index (DRI), betweenness centrality ($CB$), closeness centrality ($CC$).

A hybrid framework is presented for constructing and characterizing urban resilience dependency networks by integrating expert knowledge with transformer-based semantic inference. This method synthesizes 451 measurable sub-indicators from eleven global frameworks into the Urban System Abstraction Hierarchy (USAH), a reproducible graph dataset of 40 indicators across seven socio-economic domains. Sentence-transformer embeddings project indicators into a semantic space, which is combined with expert priors to retain only dependencies supported by both semantic and operational evidence, resulting in a directed dependency graph. Analysis of a Vancouver case study reveals a small-world topology with a modular structure where governance-related indicators form a core, exhibiting hub-sensitive robustness. Furthermore, assigning functional roles such as driver, anchor, bridge, stabilizer, or receiver allows for the distinction between indicators that drive downstream domains and those that accumulate system state.

The methodology addresses the gap between qualitative policy constructs and quantitative system models by creating a reproducible pipeline for dependency mapping that bridges abstract knowledge with empirical structure. The key implication lies in moving beyond mere correlation to assign functional roles—driver versus receiver—to indicators, suggesting that understanding resilience requires discerning the mechanism of influence rather than just measuring interconnectedness. The observed small-world topology and modularity in the case study suggest that urban systems are not uniformly connected but possess specialized, tightly coupled governance hubs whose failure has disproportionate systemic consequences. This shifts focus from holistic system monitoring to targeted intervention within these identified cores. A critical question remains whether the semantic embedding captures the nuances of institutional or social dependencies sufficiently to avoid imposing a purely mathematical structure onto complex human-defined concepts. What governance mechanisms are most effectively mapped by assigning roles like 'anchor' versus 'driver'?

A hybrid expert-AI pipeline for constructing and characterising urban resilience indicator dependency networks

Facts Only

Executive Summary

Full Take

A hybrid expert-AI pipeline for constructing and characterising urban resilience indicator dependency networks

Facts Only

Executive Summary

Full Take