cigChannel: A large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation

Submarine canyon (formerly submarine 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. cigChannel (V1.0) contains 1,600 synthetic 3D seismic volumes with labels of meandering channels, tributary channel networks and submarine canyons. Seismic impedance and sedimentary facies (only for submarine canyons) volumes correspond to the seismic volumes are also included in this dataset. Components of this dataset are listed below: Subset name Sample amount & size Contents Features Meandering channel 400, 256x256x256 Seismic volumes (float32) Binary-class label volumes (uint8) Seismic impedance volume (float32) Meandering channels. Horizontal, inclined, folded and faulted structures. Noise-free. Tributary channel network (formerly distributary channel) 400, 256x256x256 Seismic volumes (float32) Binary-class label volumes (uint8) Seismic impedance volume (float32) Tributary channel networks. Horizontal, inclined, folded and faulted structures. Noise-free. Submarine canyon (formerly submarine channel) 400, 256x256x256 Seismic volumes (float32) Binary-class label volumes (uint8) Seismic impedance volumes (float32) Sedimentary facies volumes (int16) Submarine canyons. Horizontal, inclined, folded and faulted structures. Noise-free. Assorted channel 400, 256x256x256 Seismic volumes (float32) Multi-class label volumes (int16) Seismic impedance volumes (float32) Meandering, tributary channel networks and submarine canyons. Horizontal, inclined, folded and faulted structures. Noise-free. Further details about this dataset are available in our paper published in Earth System Science Data: Wang, G., Wu, X., and Zhang, W.: cigChannel: a large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation, Earth Syst. Sci. Data, 17, 3447–3471, https://doi.org/10.5194/essd-17-3447-2025, 2025. Due to the size limitation of the uploaded files, we have to publish the dataset in separated versions. This version includes the submarine canyon subset, which contains the following zip files: Submarine_Channel_Facies_xx-xx.zip: Sedimentary facies volumes of sample No.xx to No.xx, where the value 0 represents the background (non-channel facies), 2 represents the point bar facies, 3 represents the natural levee facies and 4 represents the oxbow lake facies. Submarine_Channel_Ip_xx-xx.zip: Seismic impedance volumes of sample No.xx to No.xx. Submarine_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 submarine channel. Submarine_Channel_Seismic_xx-xx.zip: Seismic (amplitude) volumes of sample No.xx to No.xx. Samples in this subset feature different geologic structures: Sample No. 0 to No. 49 feature horizontal structure. Sample No. 50 to No. 99 feature inclined structure. Sample No. 100 to No. 299 feature folded structure. Sample No. 300 to No. 399 feature folded and faulted structures (uploaded as an expansion package). Portal to the expansion package: https://doi.org/10.5281/zenodo.15448215 Portals to the other subsets: Assorted channel subset: https://doi.org/10.5281/zenodo.11044512 Tributary channel network subset: https://doi.org/10.5281/zenodo.11073030 Meandering channel subset: https://doi.org/10.5281/zenodo.11078794本数据集为cigChannel数据集（V1.0）的海底峡谷（原海底水道）子集。 cigChannel（V1.0）是由计算解释组（Computational Interpretation Group，CIG）打造的数据集，旨在基于深度学习实现三维地震数据体中的古河道解释。该数据集的主要贡献者为王光宇、吴新明与张文。 cigChannel（V1.0）共包含1600组合成三维地震数据体，对应标注涵盖曲流河道、支流河道网与海底峡谷三类。数据集还附带与地震数据体匹配的地震阻抗数据体，以及仅针对海底峡谷的沉积相数据体。数据集各组成部分如下： ### 曲流河道子集 样本量：400，数据体尺寸：256×256×256 包含数据：浮点型（float32）地震数据体、二分类标签数据体（uint8）、浮点型（float32）地震阻抗数据体 标注内容：曲流河道 数据特征：涵盖水平、倾斜、褶皱与断裂构造，无噪声干扰 ### 支流河道网子集（原分流河道子集） 样本量：400，数据体尺寸：256×256×256 包含数据：浮点型（float32）地震数据体、二分类标签数据体（uint8）、浮点型（float32）地震阻抗数据体 标注内容：支流河道网 数据特征：涵盖水平、倾斜、褶皱与断裂构造，无噪声干扰 ### 海底峡谷子集（原海底水道子集） 样本量：400，数据体尺寸：256×256×256 包含数据：浮点型（float32）地震数据体、二分类标签数据体（uint8）、浮点型（float32）地震阻抗数据体、短整型（int16）沉积相数据体 标注内容：海底峡谷 数据特征：涵盖水平、倾斜、褶皱与断裂构造，无噪声干扰 ### 混合河道子集 样本量：400，数据体尺寸：256×256×256 包含数据：浮点型（float32）地震数据体、多分类标签数据体（int16）、浮点型（float32）地震阻抗数据体 标注内容：涵盖曲流河道、支流河道网与海底峡谷 数据特征：涵盖水平、倾斜、褶皱与断裂构造，无噪声干扰 有关该数据集的更多细节可参阅我们发表于《Earth System Science Data》的论文：Wang, G., Wu, X., and Zhang, W.: cigChannel: a large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation, Earth Syst. Sci. Data, 17, 3447–3471, https://doi.org/10.5194/essd-17-3447-2025, 2025。 受限于上传文件的大小限制，本数据集以分卷形式发布。本次发布的为海底峡谷子集，包含以下压缩包： 1. Submarine_Channel_Facies_xx-xx.zip：样本编号xx至xx的沉积相数据体，其中数值0代表背景（非河道相），2代表点坝相，3代表天然堤相，4代表牛轭湖相。 2. Submarine_Channel_Ip_xx-xx.zip：样本编号xx至xx的地震阻抗数据体。 3. Submarine_Channel_Label_xx-xx.zip：样本编号xx至xx的二分类标签数据体，其中数值0代表背景（非河道区域），1代表海底水道区域。 4. Submarine_Channel_Seismic_xx-xx.zip：样本编号xx至xx的地震（振幅）数据体。 该子集的样本涵盖不同地质构造： - 样本编号0至49：水平构造 - 样本编号50至99：倾斜构造 - 样本编号100至299：褶皱构造 - 样本编号300至399：褶皱与断裂构造（以扩展包形式上传） 扩展包访问入口：https://doi.org/10.5281/zenodo.15448215 其余子集的访问入口： - 混合河道子集：https://doi.org/10.5281/zenodo.11044512 - 支流河道网子集：https://doi.org/10.5281/zenodo.11073030 - 曲流河道子集：https://doi.org/10.5281/zenodo.11078794