PDF
Full
Outline
The response spectrum is a crucial foundation for seismic design. The constitutive models of traditional numerical simulation methods fail to adequately capture the complex site conditions and dynamic processes of soil with high uncertainty, which causes significant discrepancies between calculated and measured response spectra. This paper used 2428 sets of bedrock and surface seismic records from horizontal site stations by KiK-net in Japan. It established a BO-XGBoost-SS model for predicting ground acceleration response spectra, taking soil layer information and bedrock input as primary features through a stratified sampling training strategy guided by site categories. Results demonstrate that the constructed model exhibits good predictive performance, with an R2 evaluation metric of 0.87 for surface acceleration response spectrum, with R2 values above 0.8 for various periods. Applying dynamic time warping (DTW) distance analysis to assess the prediction match of individual response spectrum, the model proposed shows stability across different site categories, overcoming the deficiencies of numerical methods in underestimating high-frequency ground motion and anomalously amplifying long-period response spectrum. Validation with the latest ground motion records as an external dataset further confirms the model’s generalization ability. Through shapley additive explanations (SHAP) analysis, the contributions of features to model predictions are elucidated, revealing key features influencing response spectrum predictions, consistent with existing knowledge. The study’s findings provide training strategies and assessment guidance for the development of site response prediction models, offering new insights into the application of machine learning in seismic zoning and earthquake-resistant design of engineering structures.
PDF
70
35
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
