Tight gas sandstone reservoirs vary widely in terms of rock type, depositional environment, mineralogy and petrophysical properties. For this reason, estimating their permeability is a challenge when core is not available because it is a property that cannot be measured directly from wire-line logs. The aim of this work is to create an automatic tool for rock microstructure classification as a first step for future permeability prediction. Permeability can be estimated from porosity measured using wire-line data such as derived from density-neutron tools. However, without additional information this is highly inaccurate because porosity-permeability relationships are controlled by the microstructure of samples and permeability can vary by over five orders of magnitude. Experts can broadly estimate porosity-permeability relationships by analysing the microstructure of rocks using Scanning Electron Microscopy (SEM) or optical microscopy. Such estimates are, however, subjective and require many years of experience. A Machine Learning model for the automation of rock microstructure determination on tight gas sandstones has been built using Convolutional Neural Networks (CNNs) and trained on backscattered images from cuttings. Current results were obtained by training the model on around 24,000 Back Scattering Electron Microscopy (BSEM) images from 25 different rock samples. The obtained model performance for the current dataset are 97% of average of both validation and test categorical accuracy. Also, loss of 0.09 and 0.089 were obtained for validation and test correspondingly. Such high accuracy and low loss indicate an overall great model performance. Other metrics and debugging techniques such Gradient-weighted Class Activation Mapping (Grad-CAM), Receiver Operator Characteristics (ROC) and Area Under the Curve (AUC) were considered for the model performance evaluation obtaining positive results. Nevertheless, this can be improved by obtaining images from new already available samples and make the model generalizes better. Current results indicate that CNNs are a powerful tool and their application over thin section images is an answer for image analysis and classification problems. The use of this classifier removes the subjectivity of estimating porosity-permeability relationships from microstructure and can be used by non-experts. The current results also open the possibility of a data driven permeability prediction based on rock microstructure and porosity from well logs.
{"title":"Convolutional Neural Networks for the Classification of the Microstructure of Tight Sandstone","authors":"Ana Gabriela Reyna Flores, Q. Fisher, P. Lorinczi","doi":"10.2523/IPTC-21208-MS","DOIUrl":"https://doi.org/10.2523/IPTC-21208-MS","url":null,"abstract":"\u0000 Tight gas sandstone reservoirs vary widely in terms of rock type, depositional environment, mineralogy and petrophysical properties. For this reason, estimating their permeability is a challenge when core is not available because it is a property that cannot be measured directly from wire-line logs. The aim of this work is to create an automatic tool for rock microstructure classification as a first step for future permeability prediction.\u0000 Permeability can be estimated from porosity measured using wire-line data such as derived from density-neutron tools. However, without additional information this is highly inaccurate because porosity-permeability relationships are controlled by the microstructure of samples and permeability can vary by over five orders of magnitude. Experts can broadly estimate porosity-permeability relationships by analysing the microstructure of rocks using Scanning Electron Microscopy (SEM) or optical microscopy. Such estimates are, however, subjective and require many years of experience. A Machine Learning model for the automation of rock microstructure determination on tight gas sandstones has been built using Convolutional Neural Networks (CNNs) and trained on backscattered images from cuttings.\u0000 Current results were obtained by training the model on around 24,000 Back Scattering Electron Microscopy (BSEM) images from 25 different rock samples. The obtained model performance for the current dataset are 97% of average of both validation and test categorical accuracy. Also, loss of 0.09 and 0.089 were obtained for validation and test correspondingly. Such high accuracy and low loss indicate an overall great model performance. Other metrics and debugging techniques such Gradient-weighted Class Activation Mapping (Grad-CAM), Receiver Operator Characteristics (ROC) and Area Under the Curve (AUC) were considered for the model performance evaluation obtaining positive results. Nevertheless, this can be improved by obtaining images from new already available samples and make the model generalizes better. Current results indicate that CNNs are a powerful tool and their application over thin section images is an answer for image analysis and classification problems.\u0000 The use of this classifier removes the subjectivity of estimating porosity-permeability relationships from microstructure and can be used by non-experts. The current results also open the possibility of a data driven permeability prediction based on rock microstructure and porosity from well logs.","PeriodicalId":266630,"journal":{"name":"Day 9 Wed, March 31, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115939953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a resourced based economy, Malaysia relies heavily on the energy oil, and gas industry - a critical sector contributing to the economic growth of the Malaysian economy; which makes up in the range of 20% - 25% of the total gross domestic product (GDP) of Malaysia as of 2017. No analysts can properly predict prices of the future, with the highs and lows of crude and natural gas and renewables as the fuel of the future and are perhaps new way of things. This "new normal" in which countries, including Malaysia, must learn to adapt in a more agile manner to the "new way of work" of increased productivity and efficiency (de Graauw, McCreery, & Murphy, 2015). In adapting to the new normal, measures of increased productivity must continue to be pushed forward and implemented. Energy companies and services provider still need to continue with exploration and development (E&P) operations and activities to meet long term strategic objectives and demands of the nation, in line with the aspirations of the national oil company, however, it needs to add more value to every dollar spent as margins have continued to shrink and reduce profit margins of energy producers. This is where Digital Transformation comes into play and the urgency for implementation has gone from novelty solutions to critical business survival. Changing industry trends such as Industrial Revolution 4.0 have made it more prevalent than ever to make better use of capital at a time when productivity is essential. At the same time, the industry needs to continue to explore and develop to meet long-term demands, which continues to grow albeit slower than before.
{"title":"Accelerating Digital Transformation in E&P Business","authors":"A. Karim","doi":"10.2523/IPTC-21847-MS","DOIUrl":"https://doi.org/10.2523/IPTC-21847-MS","url":null,"abstract":"\u0000 As a resourced based economy, Malaysia relies heavily on the energy oil, and gas industry - a critical sector contributing to the economic growth of the Malaysian economy; which makes up in the range of 20% - 25% of the total gross domestic product (GDP) of Malaysia as of 2017. No analysts can properly predict prices of the future, with the highs and lows of crude and natural gas and renewables as the fuel of the future and are perhaps new way of things. This \"new normal\" in which countries, including Malaysia, must learn to adapt in a more agile manner to the \"new way of work\" of increased productivity and efficiency (de Graauw, McCreery, & Murphy, 2015). In adapting to the new normal, measures of increased productivity must continue to be pushed forward and implemented. Energy companies and services provider still need to continue with exploration and development (E&P) operations and activities to meet long term strategic objectives and demands of the nation, in line with the aspirations of the national oil company, however, it needs to add more value to every dollar spent as margins have continued to shrink and reduce profit margins of energy producers. This is where Digital Transformation comes into play and the urgency for implementation has gone from novelty solutions to critical business survival.\u0000 Changing industry trends such as Industrial Revolution 4.0 have made it more prevalent than ever to make better use of capital at a time when productivity is essential. At the same time, the industry needs to continue to explore and develop to meet long-term demands, which continues to grow albeit slower than before.","PeriodicalId":266630,"journal":{"name":"Day 9 Wed, March 31, 2021","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116036807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：