Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
- URL: http://arxiv.org/abs/2412.17333v1
- Date: Mon, 23 Dec 2024 06:56:28 GMT
- Title: Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
- Authors: Jaeheun Jung, Jaehyuk Lee, Chang-Hae Jung, Hanyoung Kim, Bosung Jung, Donghun Lee,
- Abstract summary: We propose a specialized Latent Diffusion Model (LDM) that reliably generates realistic waveforms after learning from real earthquake data.
We construct the time-aligned earthquake dataset using Southern California Earthquake Data Center (SCEDC) API.
Our model surpasses all comparable data-driven methods in various test criteria not only from waveform generation domain but also from seismology.
- Score: 3.1285630695933686
- License:
- Abstract: Earthquakes are rare. Hence there is a fundamental call for reliable methods to generate realistic ground motion data for data-driven approaches in seismology. Recent GAN-based methods fall short of the call, as the methods either require special information such as geological traits or generate subpar waveforms that fail to satisfy seismological constraints such as phase arrival times. We propose a specialized Latent Diffusion Model (LDM) that reliably generates realistic waveforms after learning from real earthquake data with minimal conditions: location and magnitude. We also design a domain-specific training method that exploits the traits of earthquake dataset: multiple observed waveforms time-aligned and paired to each earthquake source that are tagged with seismological metadata comprised of earthquake magnitude, depth of focus, and the locations of epicenter and seismometers. We construct the time-aligned earthquake dataset using Southern California Earthquake Data Center (SCEDC) API, and train our model with the dataset and our proposed training method for performance evaluation. Our model surpasses all comparable data-driven methods in various test criteria not only from waveform generation domain but also from seismology such as phase arrival time, GMPE analysis, and spectrum analysis. Our result opens new future research directions for deep learning applications in seismology.
Related papers
- DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional Applications [59.488352977043974]
This study proposes DispFormer, a transformer-based neural network for inverting the $v_s$ profile from Rayleigh-wave phase and group dispersion curves.
Results indicate that zero-shot DispFormer, even without any labeled data, produces inversion profiles that match well with the ground truth.
arXiv Detail & Related papers (2025-01-08T09:08:24Z) - High Resolution Seismic Waveform Generation using Denoising Diffusion [3.5046784866523932]
This study introduces a novel, efficient, and scalable generative model for high-frequency seismic waveform generation.
A spectrogram representation of seismic waveform data is reduced to a lower-dimensional submanifold via an autoencoder.
A state-of-the-art diffusion model is trained to generate this latent representation, conditioned on key input parameters.
arXiv Detail & Related papers (2024-10-25T07:01:48Z) - SeisLM: a Foundation Model for Seismic Waveforms [9.064547137948743]
We introduce the Seismic Language Model (SeisLM), a model designed to analyze seismic waveforms.
SeisLM is pretrained on a large collection of open-source seismic datasets using a self-supervised contrastive loss.
When fine-tuned, SeisLM excels in seismological tasks like event detection, phase-picking, onset time regression, and foreshock-aftershock classification.
arXiv Detail & Related papers (2024-10-21T08:24:44Z) - Causal Representation Learning in Temporal Data via Single-Parent Decoding [66.34294989334728]
Scientific research often seeks to understand the causal structure underlying high-level variables in a system.
Scientists typically collect low-level measurements, such as geographically distributed temperature readings.
We propose a differentiable method, Causal Discovery with Single-parent Decoding, that simultaneously learns the underlying latents and a causal graph over them.
arXiv Detail & Related papers (2024-10-09T15:57:50Z) - EarthquakeNPP: Benchmark Datasets for Earthquake Forecasting with Neural Point Processes [0.0]
We introduce EarthquakeNPP: a collection of benchmark datasets to facilitate testing of NPPs on earthquake data.
The datasets cover a range of small to large target regions within California, dating from 1971 to 2021.
In a benchmarking experiment, we compare three splits-temporal NPPs against ETAS and find that none outperform ETAS in either spatial or temporal log-likelihood.
arXiv Detail & Related papers (2024-09-27T16:06:17Z) - Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning [56.45067876391473]
Existing EEW approaches treat phase picking, location estimation, and magnitude estimation as separate tasks, lacking a unified framework.
We propose a novel unified seismic neural network called Fast Information Streaming Handler (FisH)
FisH is designed to process real-time streaming seismic data and generate simultaneous results for phase picking, location estimation, and magnitude estimation in an end-to-end fashion.
arXiv Detail & Related papers (2024-08-13T04:33:23Z) - Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling [43.056135090637646]
Conditional Generative Modeling for Ground Motion (CGM-GM)
We propose a novel artificial intelligence (AI) simulator to synthesize high-frequency and spatially continuous earthquake ground motion waveforms.
CGM-GM demonstrates a strong potential for outperforming a state-of-the-art non-ergodic empirical ground motion model.
arXiv Detail & Related papers (2024-07-21T08:23:37Z) - Learning with Noisy Foundation Models [95.50968225050012]
This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.
We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
arXiv Detail & Related papers (2024-03-11T16:22:41Z) - Seismic-phase detection using multiple deep learning models for global
and local representations of waveforms [0.0]
Recent advances in machine learning have enabled the automatic detection of earthquakes from waveform data.
In this study, we proposed and tested a novel phase detection method employing deep learning.
The novelty of the proposed method is its separate explicit learning strategy for global and local representations of waveforms.
arXiv Detail & Related papers (2022-11-04T04:37:04Z) - Semiparametric Bayesian Forecasting of Spatial Earthquake Occurrences [77.68028443709338]
We propose a fully Bayesian formulation of the Epidemic Type Aftershock Sequence (ETAS) model.
The occurrence of the mainshock earthquakes in a geographical region is assumed to follow an inhomogeneous spatial point process.
arXiv Detail & Related papers (2020-02-05T10:11:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.