An Application of Deep Neural Networks for Segmentation of Microtomographic Images of Rock Samples

Coastal landscape classification using convolutional neural network and remote sensing data in Vietnam

The length of global coastline is about 356 thousand kilometers with various dynamic natural and anthropogenic. Although the number of studies on coastal landscape categorization has been increasing, it is still difficult to distinguish precisely them because the used methods commonly are traditional qualitative ones. With the leverage of remote sensing data and GIS tools, it helps categorize and identify a variety of features on land and water based on multi-source data. The aim of study is using different natural - social profile data obtained from ALOS, NOAA, and multi-temporal Landsat satellite images as input data of the convolutional-neural-network (CvNet) models for coastal landscape classification. Studies used 900 cut-line samples which represent coastal landscapes in Vietnam for training and optimizing CvNet models. As a result, nine coastal landscapes were identified including: deltas, alluvial, mature and young sand dunes, cliff, lagoon, tectonic, karst, and transitional landscapes. Three CvNet models using three different optimizer types classified the landscapes of other 1150 cut-lines in Vietnam with the accuracies about 98% and low loss function value. Excepting dalmatian, karst and delta coastal landscapes, five others distribute heterogeneous along the coasts in Vietnam. Therefore, the evaluation of additional natural components is necessary and CvNet model have ability to update new landscape types in variety of tropical nation as a step toward coastal landscape classification at both national and global scales.

Coupled Lattice Boltzmann Modeling Framework for Pore-Scale Fluid Flow and Reactive Transport

In this paper, we propose a modeling framework for pore-scale fluid flow and reactive transport based on a coupled lattice Boltzmann model (LBM). We develop a modeling interface to integrate the LBM modeling code parallel lattice Boltzmann solver and the PHREEQC reaction solver using multiple flow and reaction cell mapping schemes. The major advantage of the proposed workflow is the high modeling flexibility obtained by coupling the geochemical model with the LBM fluid flow model. Consequently, the model is capable of executing one or more complex reactions within desired cells while preserving the high data communication efficiency between the two codes. Meanwhile, the developed mapping mechanism enables the flow, diffusion, and reactions in complex pore-scale geometries. We validate the coupled code in a series of benchmark numerical experiments, including 2D single-phase Poiseuille flow and diffusion, 2D reactive transport with calcite dissolution, as well as surface complexation reactions. The simulation results show good agreement with analytical solutions, experimental data, and multiple other simulation codes. In addition, we design an AI-based optimization workflow and implement it on the surface complexation model to enable increased capacity of the coupled modeling framework. Compared to the manual tuning results proposed in the literature, our workflow demonstrates fast and reliable model optimization results without incorporating pre-existing domain knowledge.

On Acquisition Parameters and Processing Techniques for Interparticle Contact Detection in Granular Packings Using Synchrotron Computed Tomography

X-ray computed tomography (XCT) is regularly employed in geomechanics to non-destructively measure the solid and pore fractions of soil and rock from reconstructed 3D images. With the increasing availability of high-resolution XCT imaging systems, researchers now seek to measure microfabric parameters such as the number and area of interparticle contacts, which can then be used to inform soil behaviour modelling techniques. However, recent research has evidenced that conventional image processing methods consistently overestimate the number and area of interparticle contacts, mainly due to acquisition-driven image artefacts. The present study seeks to address this issue by systematically assessing the role of XCT acquisition parameters in the accurate detection of interparticle contacts. To this end, synchrotron XCT has been applied to a hexagonal close-packed arrangement of glass pellets with and without a prescribed separation between lattice layers. Different values for the number of projections, exposure time, and rotation range have been evaluated. Conventional global grey value thresholding and novel U-Net segmentation methods have been assessed, followed by local refinements at the presumptive contacts, as per recently proposed contact detection routines. The effect of the different acquisition set-ups and segmentation techniques on contact detection performance is presented and discussed, and optimised workflows are proposed.

Super-Resolved Segmentation of X-ray Images of Carbonate Rocks Using Deep Learning

Reliable quantitative analysis of digital rock images requires precise segmentation and identification of the macroporosity, sub-resolution porosity, and solid\mineral phases. This is highly emphasized in heterogeneous rocks with complex pore size distributions such as carbonates. Multi-label segmentation of carbonates using classic segmentation methods such as multi-thresholding is highly sensitive to user bias and often fails in identifying low-contrast sub-resolution porosity. In recent years, deep learning has introduced efficient and automated algorithms that are capable of handling hard tasks with precision comparable to human performance, with application to digital rocks super-resolution and segmentation emerging. Here, we present a framework for using convolutional neural networks (CNNs) to produce super-resolved segmentations of carbonates rock images for the objective of identifying sub-resolution porosity. The volumes used for training and testing are based on two different carbonates rocks imaged in-house at low and high resolutions. We experiment with various implementations of CNNs architectures where super-resolved segmentation is obtained in an end-to-end scheme and using two networks (super-resolution and segmentation) separately. We show the capability of the trained model of producing accurate segmentation by comparing multiple voxel-wise segmentation accuracy metrics, topological features, and measuring effective properties. The results underline the value of integrating deep learning frameworks in digital rock analysis.

A Review of Watershed Implementations for Segmentation of Volumetric Images

Watershed is a widely used image segmentation algorithm. Most researchers understand just an idea of this method: a grayscale image is considered as topographic relief, which is flooded from initial basins. However, frequently they are not aware of the options of the algorithm and the peculiarities of its realizations. There are many watershed implementations in software packages and products. Even if these packages are based on the identical algorithm-watershed, by flooding their outcomes, processing speed, and consumed memory, vary greatly. In particular, the difference among various implementations is noticeable for huge volumetric images; for instance, tomographic 3D images, for which low performance and high memory requirements of watershed might be bottlenecks. In our review, we discuss the peculiarities of algorithms with and without waterline generation, the impact of connectivity type and relief quantization level on the result, approaches for parallelization, as well as other method options. We present detailed benchmarking of seven open-source and three commercial software implementations of marker-controlled watershed for semantic or instance segmentation. We compare those software packages for one synthetic and two natural volumetric images. The aim of the review is to provide information and advice for practitioners to select the appropriate version of watershed for their problem solving. In addition, we forecast future directions of software development for 3D image segmentation by watershed.

Artificial Intelligence as a Tool to Study the 3D Skeletal Architecture in Newly Settled Coral Recruits: Insights into the Effects of Ocean Acidification on Coral Biomineralization

Understanding the formation of the coral skeleton has been a common subject uniting various marine and materials study fields. Two main regions dominate coral skeleton growth: Rapid Accretion Deposits (RADs) and Thickening Deposits (TDs). These have been extensively characterized at the 2D level, but their 3D characteristics are still poorly described. Here, we present an innovative approach to combine synchrotron phase contrast-enhanced microCT (PCE-CT) with artificial intelligence (AI) to explore the 3D architecture of RADs and TDs within the coral skeleton. As a reference study system, we used recruits of the stony coral Stylophora pistillata from the Red Sea, grown under both natural and simulated ocean acidification conditions. We thus studied the recruit’s skeleton under both regular and morphologically-altered acidic conditions. By imaging the corals with PCE-CT, we revealed the interwoven morphologies of RADs and TDs. Deep-learning neural networks were invoked to explore AI segmentation of these regions, to overcome limitations of common segmentation techniques. This analysis yielded highly-detailed 3D information about the RAD’s and TD’s architecture. Our results demonstrate how AI can be used as a powerful tool to obtain 3D data essential for studying coral biomineralization and for exploring the effects of environmental change on coral growth.

Automatic segmentation tool for 3D digital rocks by deep learning

Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results.

Deep Learning Driven Noise Reduction for Reduced Flux Computed Tomography

Deep neural networks have received considerable attention in clinical imaging, particularly with respect to the reduction of radiation risk. Lowering the radiation dose by reducing the photon flux inevitably results in the degradation of the scanned image quality. Thus, researchers have sought to exploit deep convolutional neural networks (DCNNs) to map low-quality, low-dose images to higher-dose, higher-quality images, thereby minimizing the associated radiation hazard. Conversely, computed tomography (CT) measurements of geomaterials are not limited by the radiation dose. In contrast to the human body, however, geomaterials may be comprised of high-density constituents causing increased attenuation of the X-rays. Consequently, higher-dose images are required to obtain an acceptable scan quality. The problem of prolonged acquisition times is particularly severe for micro-CT based scanning technologies. Depending on the sample size and exposure time settings, a single scan may require several hours to complete. This is of particular concern if phenomena with an exponential temperature dependency are to be elucidated. A process may happen too fast to be adequately captured by CT scanning. To address the aforementioned issues, we apply DCNNs to improve the quality of rock CT images and reduce exposure times by more than 60%, simultaneously. We highlight current results based on micro-CT derived datasets and apply transfer learning to improve DCNN results without increasing training time. The approach is applicable to any computed tomography technology. Furthermore, we contrast the performance of the DCNN trained by minimizing different loss functions such as mean squared error and structural similarity index.