An official website of the United States government
Abstract Rocks are heterogeneous multiscale porous media: two rock samples with identical bulk properties can vary widely in microstructure. The advent of digital rock technology and modern 3‐D printing provides new opportunities to replicate rocks. However, the inherent trade‐off between imaging resolution and sample size limits the scales over which microstructure and macrostructure can be identified and related to each other. Here, we develop a multiscale digital rock construction strategy by combining X‐ray computed microtomography and focused‐ion beam (FIB)‐scanning electron microscope (SEM) images, and we apply the technique to a tight sandstone. The computed tomography (CT) scanning images characterize macroscale pore structures, while the FIB‐SEM images capture microscale pore textures. The FIB‐SEM images are then coupled to CT images via a template‐matching algorithm and superposition. Bulk properties, including porosity and pore and throat size distribution, can be recovered with this approach. Permeability prediction with a pore network model for the largest connected pore network are 3 orders and 1 order of magnitude greater than the bulk rock measured value using the CT‐only and the SEM‐CT coupled images, respectively.
more »
« less
Core Feature Extraction with Computer Vision
In the oil and gas industry, exploration is largely dependent on the study of the subsurface hundreds or thousands of feet below. Most of the data used for this purpose is collected using borehole logging tools. Although sophisticated, these tools are limited as to how precisely they can measure the subsurface in terms of vertical resolution. There is one method of studying the subsurface that provides unlimited vertical resolution – core samples. Although core samples provide scientists the opportunity to generate a full, continuous data set, lab analysis work is normally done at one-foot intervals, as anything more would be prohibitively expensive. This means at best, a representative data set is generated. However, if the subsurface is not homogeneous, it is difficult to generate a representative data set with lab analysis done at one-foot intervals. This is a void that artificial intelligence can fill. More specifically, a properly trained neural network can analyze high-resolution core images continuously from top to bottom and generate a continuous analysis. It is also important to note that geologic interpretation tied to core analysis can introduce human error and subjectivity. Here too, a properly trained neural network can generate results with extreme levels of accuracy and precision. One core analysis expert believes that core analysis done manually is flawed about 70% of the time. This flawed analysis can result from lack of experience and or a lack of knowledge of the geologic formation. We are not the first to attempt to analyze core samples with vision algorithms. A group of Stanford researchers used micro-computed tomography (micro-CT) and Scanning Electron Microscopy (SEM) images of core samples to characterize the porous media. While promising, SEM and micro-CT imaging is expensive, and more importantly it is not a standard practice in the oil and gas industry to collect these types of images, making these images rare. One other work applied convolutional neural networks to a GIS based regional saturation system, but our work is significantly different. It is well known that training a neural network requires abundant data, thankfully with the method of core analysis we are proposing that will not be a problem. Through industrial partnerships we’ve obtained hundreds to thousands of core images sufficient to train a neural network, as well as core interpretations tied to those images coming from a core analysis expert with over 40 years of experience. We are the first to propose automatic hydrocarbon saturation as well as lithology prediction from core slab images. We propose the use of convolutional neural networks to analyze core samples at a single site. We plan to conduct experiments using a variety of neural networks to determine the best practices, and explore how such a service can be offered to the industry via the software-as-a-service paradigm. In the past, automated analysis through core slab images has not been possible simply because images of the required resolution were not common, but that has changed. If implemented successfully, this proposed method could become the new standard for core evaluation.
more »
« less
- Award ID(s):
- 2122442
- PAR ID:
- 10441012
- Date Published:
- Journal Name:
- 2023 ASEE Annual Conference & Exposition
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
A geologic map is both a visual depiction of the lithologies and structures occurring at the Earth’s surface and a representation of a conceptual model for the geologic history in a region. The work needed to capture such multifaced information in an accurate geologic map is time consuming. Remote sensing can complement traditional primary field observations, geochemistry, chronometry, and subsurface geophysical data in providing useful information to assist with the geologic mapping process. Two novel sources of remote sensing data are particularly relevant for geologic mapping applications: decameter-resolution imaging spectroscopy (spectroscopic imaging) and meter-resolution multispectral shortwave infrared (SWIR) imaging. Decameter spectroscopic imagery can capture important mineral absorptions but is frequently unable to spatially resolve important geologic features. Meter-resolution multispectral SWIR images are better able to resolve fine spatial features but offer reduced spectral information. Such disparate but complementary datasets can be challenging to integrate into the geologic mapping process. Here, we conduct a comparative analysis of spatial and spectral scaling for two such datasets: one Airborne Visible/Infrared Imaging Spectrometer—Classic (AVIRIS-classic) flightline, and one WorldView-3 (WV3) scene, for a geologically complex landscape in Anza-Borrego Desert State Park, California. To do so, we use a two-stage framework that synthesizes recent advances in the spectral mixture residual and joint characterization. The mixture residual uses the wavelength-explicit misfit of a linear spectral mixture model to capture low variance spectral signals. Joint characterization utilizes nonlinear dimensionality reduction (manifold learning) to visualize spectral feature space topology and identify clusters of statistically similar spectra. For this study area, the spectral mixture residual clearly reveals greater spectral dimensionality in AVIRIS than WorldView (99% of variance in 39 versus 5 residual dimensions). Additionally, joint characterization shows more complex spectral feature space topology for AVIRIS than WorldView, revealing information useful to the geologic mapping process in the form of mineralogical variability both within and among mapped geologic units. These results illustrate the potential of recent and planned imaging spectroscopy missions to complement high-resolution multispectral imagery—along with field and lab observations—in planning, collecting, and interpreting the results from geologic field work.more » « less
-
Pore-scale modeling is essential in understanding and predicting flow and transport properties of rocks. Generally, pore-scale modeling is dependent on imaging technologies such as Micro Computed Tomography (micro-CT), which provides visual confirmation into the pore microstructures of rocks at a representative scale. However, this technique is limited in the ability to provide high resolution images showing the pore-throats connecting pore bodies. Pore scale simulations of flow and transport properties of rocks are generally done on a single 3D pore microstructure image. As such, the simulated properties are only representative of the simulated pore-scale rock volume. These are the technological and computational limitations which we address here by using a stochastic pore-scale simulation approach. This approach consists of constructing hundreds of 3D pore microstructures of the same pore size distribution and overall porosity but different pore connectivity. The construction of the 3D pore microstructures incorporates the use of Mercury Injection Capillary Pressure (MICP) data to account for pore throat size distribution, and micro-CT images to account for pore body size distribution. The approach requires a small micro-CT image volume (7–19 mm3) to reveal key pore microstructural features that control flow and transport properties of highly heterogeneous rocks at the core-scale. Four carbonate rock samples were used to test the proposed approach. Permeability calculations from the introduced approach were validated by comparing laboratory measured permeability of rock cores and permeability estimated using five well-known core-scale empirical model equations. The results show that accounting for the stochastic connectivity of pores results in a probabilistic distribution of flow properties which can be used to upscale pore-scale simulated flow properties to the core-scale. The use of the introduced stochastic pore-scale simulation approach is more beneficial when there is a higher degree of heterogeneity in pore size distribution. This is shown to be the case with permeability and hydraulic tortuosity which are key controls of flow and transport processes in rocks.more » « less
-
Abstract A deep convolutional neural network has been developed to denoise atomic-resolution transmission electron microscope image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training the network. The proposed network outperforms state-of-the-art denoising methods on both simulated and experimental test data. Factors contributing to the performance are identified, including (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits both extended and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.more » « less
-
Confocal microscopy is a standard approach for obtaining volumetric images of a sample with high axial and lateral resolution, especially when dealing with scattering samples. Unfortunately, a confocal microscope is quite expensive compared to traditional microscopes. In addition, the point scanning in confocal microscopy leads to slow imaging speed and photobleaching due to the high dose of laser energy. In this paper, we demonstrate how the advances in machine learning can be exploited to teach a traditional wide-field microscope, one that’s available in every lab, into producing 3D volumetric images like a confocal microscope. The key idea is to obtain multiple images with different focus settings using a wide-field microscope and use a 3D generative adversarial network (GAN) based neural network to learn the mapping between the blurry low-contrast image stacks obtained using a wide-field microscope and the sharp, high-contrast image stacks obtained using a confocal microscope. After training the network with widefield-confocal stack pairs, the network can reliably and accurately reconstruct 3D volumetric images that rival confocal images in terms of its lateral resolution, z-sectioning and image contrast. Our experimental results demonstrate generalization ability to handle unseen data, stability in the reconstruction results, high spatial resolution even when imaging thick (∼40 microns) highly-scattering samples. We believe that such learning-based microscopes have the potential to bring confocal imaging quality to every lab that has a wide-field microscope.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
