cigChannel: A massive-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation
收藏NIAID Data Ecosystem2026-05-01 收录
下载链接:
https://zenodo.org/record/10791151
下载链接
链接失效反馈官方服务:
资源简介:
Meandering channel subset of the cigChannel dataset (V1.0)
cigChannel (V1.0) is a dataset created by the Computational Interpretation Group (CIG) for the deep-learning-based paleochannel interpretation in 3D seismic volumes. Guangyu Wang, Xinming Wu and Wen Zhang are the main contributors to the dataset.
This dataset contains 1,200 synthetic 3D seismic volumes with labels of meandering, distributary and submarine channels. Seismic impedance and sedimentary facies (submarine channel only) volumes correspond to the seismic volumes are also included in this dataset. Components of this dataset are listed below:
Name
Sample amount & size
Contents
Features
Meandering channel subset
300, 256x256x256
Seismic volumes (float32)
Binary-class label volumes (uint8)
Seismic impedance volume (float32)
Meandering channels only.
Horizontal, inclined and folded structures.
Noise-free.
Distributary channel subset
300, 256x256x256
Seismic volumes (float32)
Binary-class label volumes (uint8)
Seismic impedance volume (float32)
Distributary channels only.
Horizontal, inclined and folded structures.
Noise-free.
Submarine channel subset
300, 256x256x256
Seismic volumes (float32)
Binary-class label volumes (uint8)
Seismic impedance volumes (float32)
Sedimentary facies volumes (int16)
Submarine channels only.
Horizontal, inclined and folded structures.
Noise-free.
Assorted channel subset
300, 256x256x256
Seismic volumes (float32)
Multi-class label volumes (int16)
Seismic impedance volumes (float32)
Meandering, distributary and submarine channels.
Horizontal, inclined and folded structures.
Noise-free.
More detail of building this dataset is discussed in the paper submitted to the journal of Earth System Science Data:
Wang, G., X. Wu* and W. Zhang, 2024, cigChannel: A massive-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation. Earth System Science Data, submitted.
Due to the size limitation of the uploaded files, we have to publish the dataset in separated versions (uploads). This version includes the meandering channel subset, which contains the following zip files:
Meandering_Channel_Ip_xx-xx.zip: Seismic impedance volumes of sample No.xx to No.xx.
Meandering_Channel_Label_xx-xx.zip: Binary-class label volumes of sample No.xx to No.xx, where the value 0 represents the background (non-channel areas) and 1 represents the meandering channel.
Meandering_Channel_Seismic_xx-xx.zip: Seismic (amplitude) volumes of sample No.xx to No.xx.
Portals to the other subsets:
Assorted channel subset: https://doi.org/10.5281/zenodo.11044512
Distributary channel subset: https://doi.org/10.5281/zenodo.11073030
Submarine channel subset: https://doi.org/10.5281/zenodo.11079950
创建时间:
2024-04-29



