Datasets
Standard Dataset
Dataset of MCF-NET
- Citation Author(s):
-
ZhesiCui
- Submitted by:
- Zhesi Cui
- Last updated:
- Fri, 09/29/2023 - 22:17
- DOI:
- 10.21227/6req-9621
- Data Format:
- License:
93 Views- Categories:
- Keywords:
Abstract
Dataset in "Multiple-condition fusion network for characterizing complex subsurface structures based on sparse measurements and auxiliary variable". The data set includes two-dimensional experimental case data and three-dimensional experimental case data. All data used in this study are available at Github repository (https://github.com/GS-3DMG/mcf-net-data) and have been published on Zenodo (https://doi.org/10.5281/zenodo.8260600).
Accurately inferring realistic subsurface structures according to different types of geophysical observations and interpretations remains a significant challenge as the morphology controls the subsurface flow and transport behavior. Hard data and soft data are most commonly used in subsurface characterization. Among them, hard data are observations obtained from subsurface measurements. Soft data areremotely sensed geophysical information and interpretations.
The dataset includes a 2-D channelized model with 768×243 pixels and a 3-D deltaic deposit model with 150×200×80 voxels. For the 2-D channelized model, the model contains two facies, namely high- and low-permeability facies. The soft data of the 2-D experiment were obtained by using FloPy and the boundary conditions were simplified as no flow boundary on the North, South, and West sides. Pumping wells were set on the East boundary with a pumping rate q = -1 m3/day to get the hydraulic head data. The hydraulic conductivity values of sand and mud were assigned with 1 m3/day and 0.01 m3/day, respectively. The original channelized model was segmented into small patches with a resolution of 128×128 pixels. For the 3-D deltaic deposit model, the S-wave velocity model was used as soft data. The original deltaic deposit model and the S-wave velocity model were split into small cubes with a resolution of 128×128×72 voxels.
