mlsanityData to 14 Oct 2026

Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics

arXiv 2512.13919 ↗First posted 15 Dec 2025cs.LG cs.NA math.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

This work shows how adaptivity can enhance value realization of digital twins in civil engineering. We focus on adapting the state transition models within digital twins represented through probabilistic graphical models. The bi-directional interaction between the physical and virtual domains is modeled using dynamic Bayesian networks. By treating state transition probabilities as random variables endowed with conjugate priors, we enable hierarchical online learning of transition dynamics from a state to another through effortless Bayesian updates. We provide the mathematical framework to account for a larger class of distributions with respect to the current literature on digital twins. To compute dynamic policies with precision updates we solve parametric Markov decision processes through reinforcement learning. The proposed adaptive digital twin framework enjoys enhanced personalization, increased robustness, and improved cost-effectiveness. We assess our approach on a case study involving structural health monitoring and maintenance planning of a railway bridge.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 96 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

18 of 96 references.

References · 18

  1. 2020A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environmentscited by 62
  2. 2020A Probabilistic Graphical Model Foundation for Enabling Predictive Digital Twins at Scalecited by 58
  3. 2020A Review of Vibration-Based Damage Detection in Civil Structures: From Traditional Methods to Machine Learning and Deep Learning Applicationscited by 33
  4. 2018Managing engineering systems with large state and action spaces through deep reinforcement learningcited by 32
  5. 2022A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologiescited by 28
  6. 2023POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenancecited by 13
  7. 2023Predictive Digital Twin for Optimizing Patient-Specific Radiotherapy Regimens under Uncertainty in High-Grade Gliomascited by 12
  8. 2022Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systemscited by 11
  9. 2023A digital twin framework for civil engineering structurescited by 10
  10. 2021Online structural health monitoring by model order reduction and deep learning algorithmscited by 7
  11. 2023InVAErt networks: a data-driven framework for model synthesis and identifiability analysiscited by 6
  12. 2023On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fieldscited by 3
6 more
  1. 2025Active Digital Twins via Active Inferencecited by 3
  2. 2023High-Fidelity Digital Twins: Detecting and Localizing Weaknesses in Structurescited by 1
  3. 2023Model bias identification for Bayesian calibration of stochastic digital twins of bridgescited by 1
  4. 2024Enhancing Bayesian model updating in structural health monitoring via learnable mappingscited by 1
  5. 2024Mastering truss structure optimization with tree searchcited by 1
  6. 2024A Reduced Order Model conditioned on monitoring features for estimation and uncertainty quantification in engineered systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Machine learning based digital twin for dynamical systems with multiple time-scales
  2. 2026Optimal sequential decision-making for error propagation mitigation in digital twins
  3. 2026Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models
  4. 2025Adaptive Sensor Steering Strategy Using Deep Reinforcement Learning for Dynamic Data Acquisition in Digital Twins
  5. 2026COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
  6. 2025Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach
  7. 2024Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs
  8. 2026Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity