Bo Liu , Qamar Yasin , Mengdi Sun , Atif Ismail , David A. Wood , Xin Tian , Baiquan Yan , Li Fu
{"title":"An improved convolutional architecture for quantitative characterization of pore networks in fine-grained rocks using FIB-SEM","authors":"Bo Liu , Qamar Yasin , Mengdi Sun , Atif Ismail , David A. Wood , Xin Tian , Baiquan Yan , Li Fu","doi":"10.1016/j.coal.2024.104625","DOIUrl":null,"url":null,"abstract":"<div><div>Focused ion beam scanning electron microscope (FIB-SEM) is one of the most advanced imaging techniques for analyzing and understanding complex pore networks in shale and other fine-grained formations. However, FIB-SEM imaging tends to be time-consuming and labor-intensive and can result in biased interpretations associated with pore analysis. Recently, U-Net or its variants for image segmentation have been applied to capture microscopic pores at higher resolutions. The ‘traditional’ encoder-decoder-based approaches tend to detect very fine-scale microscopic pores poorly. This study presents an improved convolutional architecture for automatically analyzing pore structures in shale reservoirs using FIB-SEM. It does so by applying an overcomplete convolutional architecture, KiU-Net, to capture very fine-scale microscopic pores by accurately defining their edges in the input FIB-SEM images. The KiU-Net learns low and high-level features by making the model more sensitive to fine-scale microscopic pores in the input images. The purpose of this study is to demonstrate KiU-Net's capabilities by analyzing different shale formations with varying characteristics. The results indicate that KiU-Net is more accurate and efficient than other methods in predicting nanopores in the Longmaxi, Niutitang, Qingshankou, Qianjiang, and Yanchang Formations (China), Bakken shale (Canada), and coal reservoirs (China). Furthermore, KiU-Net demonstrated the advantage of requiring fewer parameters and achieving super convergence compared to the Attention U-Net technique. KiU-Net addresses the challenges of the Edge-Threshold Automatic Processing (ETAP) methods by capturing very fine-scale microscopic pores with accurate edges. This study further enhances the accuracy and efficiency of pore analysis in shales, thereby offering an improved method for understanding shale reservoir quality with the potential to improve petroleum recovery from such formations.</div></div>","PeriodicalId":13864,"journal":{"name":"International Journal of Coal Geology","volume":"295 ","pages":"Article 104625"},"PeriodicalIF":5.6000,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Coal Geology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0166516224001824","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Focused ion beam scanning electron microscope (FIB-SEM) is one of the most advanced imaging techniques for analyzing and understanding complex pore networks in shale and other fine-grained formations. However, FIB-SEM imaging tends to be time-consuming and labor-intensive and can result in biased interpretations associated with pore analysis. Recently, U-Net or its variants for image segmentation have been applied to capture microscopic pores at higher resolutions. The ‘traditional’ encoder-decoder-based approaches tend to detect very fine-scale microscopic pores poorly. This study presents an improved convolutional architecture for automatically analyzing pore structures in shale reservoirs using FIB-SEM. It does so by applying an overcomplete convolutional architecture, KiU-Net, to capture very fine-scale microscopic pores by accurately defining their edges in the input FIB-SEM images. The KiU-Net learns low and high-level features by making the model more sensitive to fine-scale microscopic pores in the input images. The purpose of this study is to demonstrate KiU-Net's capabilities by analyzing different shale formations with varying characteristics. The results indicate that KiU-Net is more accurate and efficient than other methods in predicting nanopores in the Longmaxi, Niutitang, Qingshankou, Qianjiang, and Yanchang Formations (China), Bakken shale (Canada), and coal reservoirs (China). Furthermore, KiU-Net demonstrated the advantage of requiring fewer parameters and achieving super convergence compared to the Attention U-Net technique. KiU-Net addresses the challenges of the Edge-Threshold Automatic Processing (ETAP) methods by capturing very fine-scale microscopic pores with accurate edges. This study further enhances the accuracy and efficiency of pore analysis in shales, thereby offering an improved method for understanding shale reservoir quality with the potential to improve petroleum recovery from such formations.
期刊介绍:
The International Journal of Coal Geology deals with fundamental and applied aspects of the geology and petrology of coal, oil/gas source rocks and shale gas resources. The journal aims to advance the exploration, exploitation and utilization of these resources, and to stimulate environmental awareness as well as advancement of engineering for effective resource management.