ABSTRACT
Predicting robust earthquake spectra is challenging, especially for data sparse regions such as India. Often, alternatives to the traditional data-driven regression analysis are used to develop empirical models for such regions. Advancing these efforts, the present study aims at exploring an alternative machine learning technique called Transfer learning, wherein a non-parametric deep neural network is trained for response (Sa) and Fourier spectra (FAS) of Himalayas, which uses network parameters that were derived for a large comprehensive database (NGA-West2). While the FAS is derived using magnitude, distance, focal depth, and site class, the Sa is scaled using FAS and significant duration.
Disclosure Statement
No potential conflict of interest was reported by the author(s).
Author Contributions
Professor STG has contributed to the conceptualization and supervision of this work and Ms Basu has contributed to data collection and simulation; whereas concept development, analysis and preparation of the manuscript were performed by the corresponding author Bhargavi Podili.
Data Availability Statement
The models developed in this study are given as electronic supplements. Further, the reader can obtain the required estimates for the Himalayan region, using the models derived in this study through the MATLAB codes published at https://github.com/Blu682/SpectralGMMcodes. A demo code showing the methodology is also provided here, which can be used for developing a DNN with transfer learning for other regions. On the other hand, the datasets generated during and/or analysed during the current study are openly available.
Supplementary Material
Supplemental data for this article can be accessed online at https://doi.org/10.1080/13632469.2024.2353261.