Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 19, 2025

ML-ABC: Machine-learning assisted Approximate Bayesian Computation for efficient calibration of agent-based models for pandemic outbreak analysis

View Full Paper
Ask AI
Bookmark
Share

Authors

TBThomas BayleyTWTony WardFSFabian Sturman

Discussion

Loading...

Member takes

Overview

Machine-learning assisted calibration improves parameter estimates in agent-based models, suggesting robust policy modeling approaches.

Key Points

  • Using ML-ABC, calibration of agent-based models can be achieved 52% faster during the first COVID-19 wave, enhancing efficiency and robustness.
  • ML-ABC effectively quantifies parameter uncertainty, deriving identical posterior distributions similar to traditional methods but with improved speed.
  • The method demonstrated an around 33% time reduction in calibrating parameters for the second COVID-19 wave, ensuring timely data adaptation.
  • This approach indicates potential to make agent-based modeling competitive with traditional calibration methods, crucial for epidemic response.

Cite This Study

Bayley et al. (2025) studied this question.

synapsesocial.com/papers/68d466be31b076d99fa65a36https://doi.org/10.21203/rs.3.rs-2773605/v2
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1ML-ABC: Machine-learning assisted Approximate Bayesian Computation for efficient calibration of agent-based models for pandemic outbreak analysis2025
  2. 2Bayesian calibration of stochastic agent based model via random forest2024
  3. 3Calibration of stochastic, agent-based neuron growth models with Approximate Bayesian Computation2024
  4. 4Trajectory-matching ABC-MCMC for simulating heterogeneous dynamics in mechanistic models2025
  5. 5Stochastic Calibration of Automated Vehicle Car-Following Control: An Approximate Bayesian Computation Approach2025 · 9 citations