No abstract

Machine learning has attracted the attention of geoscientists over the years. In particular, image analysis via machine learning has promise for application to exploration and production technologies. Demands have grown for the automation of carbonate lithology identification to shorten the delivery time of work and to enable unspecialized engineers to conduct it. The image analysis of carbonate thin sections is time consuming and requires expert knowledge of carbonate sedimentology. In this study, the authors propose an image analysis technique based on deep neural network for carbonate lithology identification of a thin section, which is an important image analysis process required for oil and gas exploration. In addition, the authors consider that porosity and permeability variations in the same facies are controlled by the grain, cement, pore, and limemud contents. If the contents are accurately measured, the porosity and permeability can be determined more accurately than by using traditional methods such as point counting. The elucidation of the complex relation of porosity and permeability is the objective of automation of carbonate lithology identification. To perform image analysis of the thin section, the authors prepared a data set mainly comprising pictures of the Pleistocene Ryukyu Group, which were composed of reef complex deposits distributed in southern Japan. The data set contains 306 thin section pictures and annotation data labeled by a carbonate sedimentologist. The rock components was divided into four types (grain, cement, pore, and limemud). A convolution neural network (CNN) was utilized to train the model. After training the neural network, each of the four categories was interpreted by the trained model automatically. Resultantly, the accuracy of automatic Dunham classification was 90.6% and the mean average test accuracy of category identification was 83.9%. The interpretation seems highly consistent between human vision and machine vision in both the overview and pixelwise scales. This result indicates that it has sufficient potential to assist geologists and become a basic tool for practical applications. However, the accuracy of category identification is still insufficient. The authors believe that the model requires higher quality supervised data and a greater number of supervised data.

Carbonate sedimentary rocks form the reservoir rocks of many oil and gas fields. The largest oil and gas fields in the world, such as the Ghawar field in Saudi Arabia and the Zakum field in Abu Dhabi, consist of carbonate reservoirs. Therefore, understanding the structure of carbonate sedimentary rocks is important to estimate the reservoir quality and distribution in the oil and gas field. However, carbonate sedimentary rocks have complex sedimentary structures that comprise various kinds of carbonate minerals. In addition, carbonate reservoirs often undergo diagenesis after deposition. Therefore, a detailed carbonate facies analysis requires great expertise. Additionally, traditional thin section analysis approaches such as the point counting method are extremely time intensive. In this context, machine learning, including deep learning, is attracting significant attention. In particular, image analysis using convolutional neural networks (CNNs) has seen dramatic development since the emergence of AlexNet in 2012. CNNs achieve superhuman image recognition capability by utilizing a deep layer structure that consists of a convolutional layer, activation function, etc. In the field of petroleum exploration and production, several studies on image analysis using CNNs have been performed by petroleum exploration and production companies and universities . Nanjo and Tanaka (in press) attempted carbonate lithology identification with pixel-wise segmentation in thin section images; the average accuracy of their category identification for each components [grain, cement, pore, and lime mud areas] was 83.9% and the automatic carbonate lithology identification based on the category identification was over 90%. They showed that machine learning is effective for carbonate lithology identification. However, the model is still not perfect with respect to both of category identification and automatic carbonate lithology identification. Generative Adversarial Networks (GAN) are unique and thought as useful tool to improve the model. GAN has already been studied in various fields (e.g., image generation and analysis). However, few studies have attempted to use GAN for carbonate lithology identification. In this study, the authors attempted to conduct carbonate lithology identification with a GAN and to review the potential of applying GAN for FMI imaging.

No abstract

We investigated the method of estimating porosity/permeability using X-ray CT, a non-destructive method. Using X-ray CT, a method of estimating the porosity/permeability is particularly developed in sandstone. However, for the carbonate rocks, the internal structure is complicated due to biological origin. This is difficult to recognize the pore space, therefore a method of estimating the porosity/permeability using X-ray CT has not been studied. This study is based on Yamanaka et al. 2018, which clarifies rudist development in side slab core using X-ray CT and 3D modeling. The study uses X-ray CT to observe the internal structure from the view of development of rudist of the 200 feet section of the Well A in offshore Abu Dhabi, and compares the porosity/permeability obtained from CCA (Conventional core analysis) of the same well and same interval. Based on the 3D modeling of the X-ray CT, two rudist families (Radiolitidae and Ichthyosarcolites) were identified through their morphological characteristics such as inner diameter and shell thickness. A porosity of slab core around 50 feet is about 18% from CCA (Conventional Core Analysis). This slab core is made up of small rudist populations (length and wide size is 15-10mm), inside core confirmed 3D modeling (surface rendering and volume rendering), and calculated porosity is 0.89% from RCM (Reverse Coupling method). It is understood that this difference is dependent on matrix porosity and further investigation in the future is required in order to measure matrix porosity using thin section and micro X-ray CT. With regards to reservoir properties, the porosity is higher in the lower part than the upper part in the core interval. The size of the Radiolitidae could be dependent on the environment and its vertical variation suggests the change of depositional environment. Larger Radiolitidae, which appeared from 80 to 200 feet below the C-T (Cenomanian-Turonian) boundary, suggests a relatively strong wave influence. From a sedimentological point of view, the coarser matrix grain size supports the interpretation of depositional setting. On the other hand, from 30 to 80 feet below C-T boundary, smaller Radiolitidae is dominated. It was assumed that small Radiolitidae could be due to high physical stress under a restricted environment. This study shows the advantage of X-ray CT image in rudist recognition, based on interpretation of depositional environment and understanding the reservoir property. The result of this study suggests the strong correlation between porosity/permeability and depositional environment (accommodation space) inferred from rudist fossil.