Predicting the Influence of Soil–Structure Interaction on Seismic Responses of Reinforced Concrete Frame Buildings Using Convolutional Neural Network
Bibliographic record
Abstract
Most regional seismic damage assessment (RSDA) methods are based on the rigid-base assumption to ensure evaluating efficiency, while these practices introduce factual errors due to neglecting the soil–structure interaction (SSI). Predicting the influence of the SSI on seismic responses of regionwide structure portfolios remains a challenging undertaking, as it requires developing numerous high-fidelity, integrated models to capture the dynamic interplay and uncertainties in structures, foundations, and supporting soils. This study develops a one-dimensional convolutional neural network (1D-CNN) model to efficiently predict to what degree considering the SSI would change the inter-story drifts and base shear forces of RC frame buildings. An experimentally validated finite element model is developed to simulate the nonlinear seismic behavior of the building-foundation–soil system. Subsequently, a database comprising input data (i.e., structural and soil parameters, ground motions) and output predictors (i.e., changes in story drift and base shear) is constructed by simulating 1380 pairs of fixed-base versus soil-supported structures under earthquake loading. This large-scale dataset is used to train, test, and identify the optimal hyperparameters for the 1D-CNN model to quantify the demand differences in inter-story drifts and base shears due to the SSI. Results indicate the 1D-CNN model has a superior performance, and the absolute prediction errors of the SSI influence coefficients for the maximum base shear and inter-story drift are within 9.3% and 11.7% for 80% of cases in the testing set. The deep learning model can be conveniently applied to enhance the accuracy of the RSDA of RC buildings by updating their seismic responses where no SSI is considered.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".