Active learning–based efficient seismic response prediction of base-isolated structures using linear time-history analyses

Deep learning models for seismic response prediction often require extensive datasets generated through repeated time-history analyses. This study investigates uncertainty-driven active learning for training a long short-term memory model to predict complete roof-displacement histories of base-isolated structures. A numerical database comprising 1000 linear time-history simulations was developed using recorded earthquake ground motions and varying isolation parameters. Monte Carlo dropout-based uncertainty acquisition was compared with random and diversity-based sampling across 10 matched repetitions and labeled-sample budgets ranging from 100 to 300. Performance was evaluated on ground-motion records withheld from model development. The results reveal substantial variability and nonmonotonic learning behavior. Uncertainty-based acquisition did not consistently outperform the alternative strategies, and negative mean R 2 values indicated difficulties in generalizing to unseen ground-motion records. Nevertheless, Monte Carlo dropout uncertainty scores exhibited a strong positive correlation with actual prediction errors (Spearman ρ = 0.8697). These findings highlight both the diagnostic value and the limitations of uncertainty-driven sample acquisition for seismic response-history prediction.

Authors

Institutions

Publication Details

Journal
Mathematics and Mechanics of Solids
Published
2026-11-16
DOI
https://doi.org/10.1177/10812865261505838
Primary Topic
Seismic Performance and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Active learning–based efficient seismic response prediction of base-isolated structures using linear time-history analyses

Arcan Yanik
Mathematics and Mechanics of Solids
Seismic Performance and Analysis
article

Active learning–based efficient seismic response prediction of base-isolated structures using linear time-history analyses

Arcan Yanik
article en

Abstract

Deep learning models for seismic response prediction often require extensive datasets generated through repeated time-history analyses. This study investigates uncertainty-driven active learning for training a long short-term memory model to predict complete roof-displacement histories of base-isolated structures. A numerical database comprising 1000 linear time-history simulations was developed using recorded earthquake ground motions and varying isolation parameters. Monte Carlo dropout-based uncertainty acquisition was compared with random and diversity-based sampling across 10 matched repetitions and labeled-sample budgets ranging from 100 to 300. Performance was evaluated on ground-motion records withheld from model development. The results reveal substantial variability and nonmonotonic learning behavior. Uncertainty-based acquisition did not consistently outperform the alternative strategies, and negative mean R 2 values indicated difficulties in generalizing to unseen ground-motion records. Nevertheless, Monte Carlo dropout uncertainty scores exhibited a strong positive correlation with actual prediction errors (Spearman ρ = 0.8697). These findings highlight both the diagnostic value and the limitations of uncertainty-driven sample acquisition for seismic response-history prediction.

Mathematics and Mechanics of Solids
Istanbul Technical University (TR)
Seismic Performance and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon