Abstract
This study proposes a method of estimating the measurement data of nearby seismic stations by training an artificial neural network (ANN) through machine learning to understand the seismic acceleration time history at an arbitrary location where seismic acceleration time history is unknown. The ANN is trained using the observation data of 6 earthquakes at 10 ground seismic stations in Korea and 12 earthquakes at 212 underground seismic stations from the Korea Meteorological Administration. The location of the seismic station is assumed to be arbitrary in the untrained observation data to verify the validity of the trained ANN, and the measured and estimated data are compared. It is confirmed that the estimation accuracy of the ANN trained with the observation data of the underground seismic station is higher than that of the ANN trained with the observation data of the ground seismic station. The accuracy of the seismic acceleration estimation method proposed in this study is improved according to the level of learning data. It can also be applied as seismic acceleration to evaluate seismic damage or behavior of structures or facilities, even in places without seismic acceleration.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abien F, Agarap M (2019) Deep learning using rectified linear units (ReLU). arXiv:1803.08375v2, DOI: https://doi.org/10.48550/arXiv.1803.08375
Abrahamson NA, Somerville PG (1996) Effects of the hanging wall and footwall on ground motions recorded during the Northridge earthquake. Bulletin of the Seismological Society of America 86(1B):S93–S99, DOI: https://doi.org/10.1785/BSSA08601B0S93
Ferebee RC, Clayton J, Alldredge D, Irvine T (2008) An alternative method of specifying shock test Criteria. NASA/TM-2008-215253
Irvine T (2002) An introduction to the shock response spectrum. Vibrationdata, https://endaq.com/pages/introduction-to-shock-vibration-response-spectra
Khosravikia F, Clayton P (2021) Machine learning in ground motion prediction. Computers and Geosciences 148:104700, DOI: https://doi.org/10.1016/j.cageo.2021.104700
Kiani J, Pezeshk S (2017) Sensitivity analysis of the seismic demands of RC moment resisting frames to different aspects of ground motions. Earthquake Engineering & Structural Dynamics 46(15):2739–2755, DOI: https://doi.org/10.1002/eqe.2928
Kingman DP, Ba J (2015) Adam: A method for stochastic optimization. arXiv:1412.6980, DOI: https://doi.org/10.48550/arXiv.1412.6980
Kolasa M, Jóźwicki W, Wojtyna R, Jarzemski P (2007) Optimization of hidden layer in a neural network used to predict bladder-cancer patient-survival. SPA Conference, Poland, DOI: https://doi.org/10.1109/SPA.2007.5903302
Lee KS, Ahn JH, Park JB, Choi HS (2020) Proposal of acceleration time history prediction method based on seismic observation data. Journal of Korea Institute for Structural Maintenance and Inspection 24(2):15–22, DOI: https://doi.org/10.11112/jksmi.2020.24.2.15 (in Korea)
Liu Y, Starzyk JA, Zhu Z (2007) Optimizing number of hidden neurons in neural networks. IASTED International Conference on Artificial Intelligence and Applications, Austria 1(1):6
Mangalathu S, Karthikeyan K, Feng D-C, Jeon J-S (2022) Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems. Engineering Structures 250(1):112883
Mori F, Mendicelli A, Falcone G, Acunzo G, Spacagna RL, Naso G, Moscatelli M (2022) Ground motion prediction maps using seismic-microzonation data and machine learning. Natural Hazards and Earth System Sciences 22:947–966, DOI: https://doi.org/10.5194/nhess-22-947-2022
Park JB, Ahn JH, Choi HS, Kim GS, Kang GC (2018) Application of existing distance attenuation relationships using PGAs recorded during earthquakes. Korean Society of Hazard Mitigation 18(6):149–159, DOI: https://doi.org/10.9798/KOSHAM.2018.18.6.149 (in Korea)
Rampure AB, Mangulkar MN (2016) Comparison between response spectrum and time history method of dynamic analysis of concrete gravity dam. Open Journal of Civil Engineering 6:329–334, DOI: https://doi.org/10.4236/ojce.2016.63027
Rosenblatt F (1958) The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65(6):386–408, DOI: https://doi.org/10.1037/h0042519
Shiuly A, Roy N, Sahu RB (2020) Prediction of peak ground acceleration for Himalayan region using artificial neural network and genetic algorithm. Arabian Journal of Geosciences 13(215), DOI: https://doi.org/10.1007/s12517-020-5211-5
Wagarachchi NM, Karunananda AS (2013) Optimization of multi-layer artificial neural networks using delta values of hidden layers. IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), Singapore, DOI: https://doi.org/10.1109/CCMB.2013.6609169
Zurada JM (1992) Introduction to artificial neural networks systems. West Publishing Company
Acknowledgments
This research was supported by a grant (20011127) of the Regional Customized Disaster-Safety R&D Program funded by the Ministry of Interior and Safety (MOIS, Korea).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, K.S., Ahn, JH., Park, HY. et al. Seismic Acceleration Estimation Method at Arbitrary Position Using Observations and Machine Learning. KSCE J Civ Eng 27, 712–726 (2023). https://doi.org/10.1007/s12205-022-1235-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-022-1235-6