datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Seismic-AI-DataThis dataset is for AI seismology and can be used for tasks such as phase picking and polarity determination.Some datasets are download in seisbench.
I am developing a unified tool for polarity determination--SeisPolarity, and I hope that like-minded individuals will join me.
SeismicX-Cont
SeismicX-Cont — HDF5 Continuous-Waveform Data Product
Processed continuous-waveform database for reproducible regional monitoring studies
1. Overview
SeismicX-Cont is a processed and structured HDF5-based continuous-waveform
data product for deployment-level earthquake-monitoring studies.
The release preserves continuous waveform context, station-time coverage,
annotation provenance, instrument-response metadata, and validation lineage in a
common file organization.… See the full description on the dataset page: https://huggingface.co/datasets/cangyeone/SeismicX-Cont.SeismicX-Cont-mini
SeismicX-Cont Mini Two-Hour Subset
This folder is the compact, Zenodo-archived two-hour mini release for
SeismicX-Cont. It is designed for quick download, tutorial use, software smoke
tests, and checking that the HDF5, annotation, SQLite, dataloader, picker, and
validation workflow all fit together before using the full 14-day data product.
Zenodo record: https://zenodo.org/records/21331024
DOI: https://doi.org/10.5281/zenodo.21331024
Hugging Face record:… See the full description on the dataset page: https://huggingface.co/datasets/cangyeone/SeismicX-Cont-mini.SeismicTransformerDataadasemseg-seismic-facies-datasets
Processed Seismic Facies Datasets (F3, Parihaka, Penobscot)
Processed, ready-to-train .npy volumes and train/val/test splits for the three public seismic facies datasets used in:
Saha, S. and Whitaker, R. AdaSemSeg: An Adaptive Few-shot Semantic Segmentation of Seismic Facies. IEEE Transactions on Geoscience and Remote Sensing, 2025. arXiv:2501.16760
Code: github.com/Surojit-Utah/AdaSemSeg · Also archived on Zenodo: 10.5281/zenodo.21764042
Important: this is not… See the full description on the dataset page: https://huggingface.co/datasets/Surojit-Utah/adasemseg-seismic-facies-datasets.SeisMIC-Init
SeisMIC-Init modalities and grids.
Modality
Symbol
Domain
Shape (C,H,W)
Sampling / Extent
Depth velocity
V(z,x)
depth
(1,70,70)
dz=dx=10 m;700×700 m
Horizon
H(z,x)
Well log stripes
W(z,x)
RMS velocity
v_rms(t,x)
time (TWT)
(1,1000,70)
dt=1 ms;dx=10 m;TWT=1.0 s
PSTM
M(t,x)
If you… See the full description on the dataset page: https://huggingface.co/datasets/YinghaoXu/SeisMIC-Init.Seismicnasa_space_apps_2024_seismic_detection
Welcome, Space Apps challengers, to “Seismic Detection across the Solar System”.
Today, we challenge YOU to parse through seismic data collected on the Moon and Mars and figure out how to detect moonquakes and marsquakes!
To get you started on the data, we present to you a training set containing the following:
A catalog of quakes identified in the data
Seismic data collected by the Apollo (one day segments) or InSight (one hour segments) missions in miniseed and CSV format.… See the full description on the dataset page: https://huggingface.co/datasets/MH0386/nasa_space_apps_2024_seismic_detection.well-seismic-coreSeismicDataWorldwide
SeismicDataWorldwide
SeismicDataWorldwide is an open-source repository that provides a comprehensive collection of global earthquake data. The data, sourced from the USGS Earthquake Catalog, includes details of earthquakes with a magnitude of 2.5 and above, spanning from 2000 to 2024.
Data Description
The dataset contains the following fields:
time: The timestamp of the earthquake.
latitude, longitude: The geographical coordinates of the earthquake's epicenter.
depth:… See the full description on the dataset page: https://huggingface.co/datasets/nadeeshafdo/SeismicDataWorldwide.seismic-lab-dataseismicfoundationmodel-geobodyThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-geobody.f3-seismic-facies-mood-demoDemo dataset for testing or showing image-text capabilities.seismicfoundationmodel-interpolationThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-interpolation.seismicfoundationmodel-denoiseThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-denoise.seismicfoundationmodel-denoise-fieldThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-denoise-field.seismic-ensemble
Seismic Ensemble — Data & Model Store
This repo holds the data and model artefacts for the code at
irp-jas25, a project on multi-class seismic event discrimination (earthquake / deep earthquake / explosion /
nuclear explosion / volcanic eruption / noise) for CTBT-style monitoring, using a six-member ensemble
(four deep models, two classical) with a stacked meta-learner on top. It accompanies the paper
"Robust and Explainable Multi-Class Seismic Event Discrimination through… See the full description on the dataset page: https://huggingface.co/datasets/Jamie1701/seismic-ensemble.seismicfoundationmodel-faciesThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-facies.seismicflowseismicid-earthquake-forecast-dataset
SeismicID Earthquake Forecast Dataset
Dataset for SeismicID, Indonesian earthquake risk forecasting and visualization.
Live app: https://seismicid.erzanugroho.xyzSource code: https://github.com/erzanugroho/SeismicID
Important notice
This dataset and model outputs are experimental research artifacts. They are not earthquake early warning, official hazard advice, or replacement for BMKG / official authorities.
Files
file
rows
description… See the full description on the dataset page: https://huggingface.co/datasets/erzanugroho/seismicid-earthquake-forecast-dataset.seismicseismic-msmarco-spladeseismicfoundationmodel-inversion-seamThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-inversion-seam.crossdomainfoundationmodeladaption-seismicfaciesThis dataset is part of the work by Guo Zhixiang et al.https://github.com/ProgrammerZXG/Cross-Domain-Foundation-Model-Adaptation?tab=readme-ov-file
The dataset is originally available on Zenodo https://zenodo.org/records/12798750
And licensed under Creative Commons Attribution 4.0 International
Please cite the following article if you use this dataset:
@misc{guo2024crossdomainfoundationmodeladaptation,
title={Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for… See the full description on the dataset page: https://huggingface.co/datasets/porestar/crossdomainfoundationmodeladaption-seismicfacies.seismicfoundationmodel-inversion-syntheticThis dataset is part of the work by Hanlin Sheng et al. https://github.com/shenghanlin/SeismicFoundationModel
Please cite the following article if you use this dataset:
@article{sheng2023seismic,
title={Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
author={Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
journal={arXiv preprint arXiv:2309.02791},
year={2023}
}
Additional information can be found at… See the full description on the dataset page: https://huggingface.co/datasets/porestar/seismicfoundationmodel-inversion-synthetic.global-seismic-risk-catalogSeismic_Dataseismic-tsunami-event-linkage
Seismic-Tsunami Event Linkage
The Seismic-Tsunami Event Linkage is a comprehensive, machine learning-ready dataset. It contains seismic characteristics and tsunami potential indicators for 782 significant earthquakes recorded globally from 2001 to 2022. This dataset has been specifically processed and structured for applications in tsunami risk prediction, earthquake analysis, and seismic hazard assessment. It is an enhanced version derived from the foundational "Earthquake Dataset"… See the full description on the dataset page: https://huggingface.co/datasets/mnemoraorg/seismic-tsunami-event-linkage.synthetic-seismic-vlm
Synthetic Seismic VLM
This dataset contains synthetic seismic multimodal QA rows with raw seismic
images, segmentation masks, evidence-grounded questions, answers, and compact
region metadata.
Rows: 1261
Repository: https://huggingface.co/datasets/thirdExec/synthetic-seismic-vlm
Columns:
images: sequence of all raw images
masks: sequence of all mask images
instruction: task instruction
question: question text
answer: answer text
evidence: JSON string of supporting text evidence… See the full description on the dataset page: https://huggingface.co/datasets/thirdExec/synthetic-seismic-vlm.seismic-msmarco-splade-bin