Leveraging Digital Twin Simulations to Pretrain Contrastive Encoders for Few-Shot Structural Damage Classification
Journal of geospace science · 2026-06-25 · 6 (01) · 146-156
DOI: 10.71465/jgs59 ↗At a glance
Journal article in Journal of geospace science, published online on 2026-06-25. Written by Michael Anderson and 2 co-authors. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
The classification of structural damage under severely limited labeled data conditions remains a persistent bottleneck in automated infrastructure inspection, where the cost and complexity of expert annotation constrain the scalability of conventional supervised learning pipelines. This paper proposes a framework that integrates digital twin (DT) simulation with contrastive self-supervised pretraining and prototypical few-shot classification to address this bottleneck. High-fidelity finite element models of reinforced concrete (RC) and steel frame structures are used to generate large-scale synthetic image datasets parameterized across a comprehensive range of damage types and severities. A SimCLR-inspired contrastive encoder is pretrained on this synthetic corpus without any human labels, learning transferable structural damage representations that bridge the simulation-to-reality gap. The pretrained encoder is subsequently adapted to real-world inspection imagery using prototypical networks operating in the five-shot and one-shot regimes. Experiments conducted on the PEER Hub ImageNet dataset and a collected bridge inspection corpus demonstrate that the proposed method achieves classification accuracy substantially exceeding ImageNet-pretrained baselines under equivalent few-shot conditions, validating the utility of DT-driven synthetic pretraining for structural health monitoring (SHM) applications.
Cite
APA
Anderson, M., Fisher, N., & Wright, T. (2026). Leveraging Digital Twin Simulations to Pretrain Contrastive Encoders for Few-Shot Structural Damage Classification. Journal of geospace science, 6(01), 146-156. https://doi.org/10.71465/jgs59
Vancouver
Anderson M, Fisher N, Wright T. Leveraging Digital Twin Simulations to Pretrain Contrastive Encoders for Few-Shot Structural Damage Classification. Journal of geospace science. 2026;6(01):146-156. doi:10.71465/jgs59
BibTeX
@article{Anderson2026,
author = {Anderson, Michael and Fisher, Natalie and Wright, Thomas},
title = {Leveraging Digital Twin Simulations to Pretrain Contrastive Encoders for Few-Shot Structural Damage Classification},
journal = {Journal of geospace science},
year = {2026},
volume = {6},
number = {01},
pages = {146--156},
doi = {10.71465/jgs59}
}
EUVIMED