Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published June 22, 2022 | Version v1.0.0
Journal article Open

zfbi/DeepISMNet: DeepISMNet: Three-Dimensional Implicit Structural Modeling with Convolutional Neural Network

  • 1. University of Science and Technology of China
  • 2. China Aero Geophysical Survey and Remote Sensing Center for Natural Resources
  • 3. Research Institute of Petroleum Exploration & Development-NorthWest(NWGI), PetroChina

Description

Implicit structural modeling using sparse and unevenly distributed data is essential for various scientific and societal purposes ranging from natural source exploration to geological hazard forecasts. In this study, we propose an efficient deep learning method using a convolution neural network to predict a scalar field from sparse structural data associated with distinct stratigraphic layers and faults. This deep learning architecture is beneficial for the flexible incorporation of empirical geological knowledge when trained with numerous and realistic structural models that are automatically generated from a data simulation workflow. It also presents an impressive characteristic of integrating various types of structural constraints by minimizing a hybrid loss function between the models being compared, opening new opportunities for further improving geological structural modeling. Moreover, the deep neural network, after training, is highly efficient to predict implicit structural models in real-world applications.

As described in Three-Dimensional Implicit Structural Modeling Using Convolutional Neural Network by Zhengfa Bi1, Xinming Wu1, Zhaoliang Li2, Dekuan Change3 and Xueshan Yong31University of Science and Technology of China; 2China Aero Geophysical Survey and Remote Sensing Center for Natural Resources; 3Research Institute of Petroleum Exploration & Development-NorthWest(NWGI), PetroChina.

Files

zfbi/DeepISMNet-v1.0.0.zip

Files (2.9 MB)

Name Size Download all
md5:50e42d23422dc4c250b7da45d2c50732
2.9 MB Preview Download

Additional details

Related works