Pré-Publication, Document De Travail Année : 2025

Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration

Muhammad Robani
  • Fonction : Auteur
  • PersonId : 1596711

Résumé

Complex systems are increasingly explored through simulation-driven engineering workflows that combine physics-based and empirical models with optimization and analytics. Despite their power, these workflows face two central obstacles: (1) high computational cost, since accurate exploration requires many expensive simulator runs; and (2) limited transparency and reliability when decisions rely on opaque blackbox components. We propose a workflow that addresses both challenges by training lightweight emulators on compact designs of experiments that (i) provide fast, low-latency approximations of expensive simulators, (ii) enable rigorous uncertainty quantification, and (iii) are adapted for global and local Explainable Artificial Intelligence (XAI) analyses. This workflow unifies every simulation-based complex-system analysis tool, ranging from engineering design to agent-based models for socio-environmental understanding. In this paper, we propose a comparative methodology and practical recommendations for using surrogate-based explainability tools within the proposed workflow. The methodology supports continuous and categorical inputs, combines global-effect and uncertainty analyses with local attribution, and evaluates the consistency of explanations across surrogate models, thereby diagnosing surrogate adequacy and guiding further data collection or model refinement. Additional contributions include an algorithmic workflow for coupling designs of experiments, emulator training, uncertainty propagation, and explanation generation, together with guidelines for selecting surrogate families under computational and interpretability constraints. We demonstrate the approach on two contrasting case studies: a multidisciplinary design analysis of a hybrid-electric aircraft and an agent-based model of urban segregation. Results show that the surrogate-XAI coupling enables large-scale exploration in seconds, uncovers nonlinear interactions and emergent behaviors, identifies key design and policy levers, and signals regions where surrogates require more data or alternative architectures. These elements advance scalable, trustworthy, and explainability-driven automated machine learning for complex-system simulation and design exploration.

Fichier principal
Vignette du fichier
Application_of_Explainable_ML-48.pdf (23.76 Mo) Télécharger le fichier

Dates et versions

hal-05321914 , version 1 (20-10-2025)

Licence

Identifiants

Citer

Paul Saves, Pramudita Satria Palar, Muhammad Robani, Nicolas Verstaevel, Moncef Garouani, et al.. Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration. 2025. ⟨hal-05321914⟩
7464 Consultations
207 Téléchargements

Altmetric

Partager

  • More