Segmentation for Multi-Rock Types on Digital Outcrop Photographs Using Deep Learning Techniques

Abstract

The basic identification and classification of sedimentary rocks into sandstone and mudstone are important in the study of sedimentology and they are executed by a sedimentologist. However, such manual activity involves countless hours of observation and data collection prior to any interpretation. When such activity is conducted in the field as part of an outcrop study, the sedimentologist is likely to be exposed to challenging conditions such as the weather and their accessibility to the outcrops. This study uses high-resolution photographs which are acquired from a sedimentological study to test an alternative basic multi-rock identification through machine learning. While existing studies have effectively applied deep learning techniques to classify the rock types in field rock images, their approaches only handle a single rock-type classification per image. One study applied deep learning techniques to classify multi-rock types in each image; however, the test was performed on artificially overlaid images of different rock types in a test sample and not of naturally occurring rock surfaces of multiple rock types. To the best of our knowledge, no study has applied semantic segmentation to solve the multi-rock classification problem using digital photographs of multiple rock types. This paper presents the application of two state-of-the-art segmentation models, namely U-Net and LinkNet, to identify multiple rock types in digital photographs by segmenting the sandstone, mudstone, and background classes in a self-collected dataset of 102 images from a field in Brunei Darussalam. Four pre-trained networks, including Resnet34, Inceptionv3, VGG16, and Efficientnetb7 were used as a backbone for both models, and the performances of the individual models and their ensembles were compared. We also investigated the impact of image enhancement and different color representations on the performances of these segmentation models. The experiment results of this study show that among the individual models, LinkNet with Efficientnetb7 as a backbone had the best performance with a mean over intersection (MIoU) value of 0.8135 for all of the classes. While the ensemble of U-Net models (with all four backbones) performed slightly better than the LinkNet with Efficientnetb7 did with an MIoU of 0.8201. When different color representations and image enhancements were explored, the best performance (MIoU = 0.8178) was noticed for the L*a*b* color representation with Efficientnetb7 using U-Net segmentation. For the individual classes of interest (sandstone and mudstone), U-Net with Efficientnetb7 was found to be the best model for the segmentation. Thus, this study presents the potential of semantic segmentation in automating the reservoir characterization process whereby we can extract the patches of interest from the rocks for much deeper study and modeling to be conducted.

OutcropHyBNet: Hybrid Backbone Networks with Data Augmentation for Accurate Stratum Semantic Segmentation of Monocular Outcrop Images in Carbon Capture and Storage Applications

“…Zhang et al [21] state that most existing semantic segmentation methods are based on FCNs, which replace the fully connected layer with fully convolutional layers for pixel-level prediction. Malik et al [22] proposed a segmentation method using a model that combines U-Net [23] and LinkNet [24] to classify three classes: background, sandstone, and mudstone. They conducted an evaluation experiment on a self-collected dataset of 102 images from a field in Brunei Darussalam, demonstrating higher accuracy compared to conventional methods.…”

“…Although research utilizing drones in geosciences has gained momentum [26], most studies focus on analyzing topography using 3D models generated from captured photographs. However, there are a limited number of reported studies [22,25] that apply segmentation-based approaches to classify lithostratigraphy in geological outcrops. This paper emphasizes the mounting interest in employing CNNs, ViT, and investigating hybrid backbone architectures for segmentation tasks, while also acknowledging the expanding utilization of drones in geological studies.…”

Estimating millimeter-scale surface roughness of rock outcrops using drone-flyover structure-from-motion (SfM) photogrammetry by applying machine learning model

“…The 3D-DOMs contain visual information such as outcrop color and morphology reconstructed from UAV aerial photography data. Several studies have spotlighted the color of outcrops, including outcrop image segmentation, to better characterize geological reservoirs (Sato et al 2021;Malik et al 2022) and rock fractures (Byun et al 2021). In addition, there is a long tradition of research on morphology as part of geomorphology, a eld of natural geography, and on a larger scale (i.e., meters to kilometers), a study on the possibility that local morphological heterogeneity, including roughness and thickness, of deep sea oors (Kioka and Strasser 2022) and subsurface active faults control (Yamada et al 2013).…”