<\/p>\n\n\n
Predicting reservoir properties is one of the key tasks in oil production, which allows one to assess the potential of a field and optimize its development. Traditional methods such as geophysical surveys and core analysis often face difficulties due to the heterogeneity of rock structure. Perm Polytechnic scientists proposed a solution to this problem by using machine learning algorithms to model reservoir porosity.\u00a0<\/p>\n\n\n
Reservoirs are rocks containing voids that can hold and release oil, gas or water. Accurate prediction of their properties, especially porosity, is critical for estimating hydrocarbon reserves. Typically, this is done using geophysical data such as radioactive, electrical and acoustic logging, as well as laboratory core studies. However, in complex geological conditions, these methods often give inaccurate results.\u00a0<\/p>\n\n\n
PNRPU scientists have developed a machine learning algorithm that analyzes data from geophysical research and laboratory core analysis. To train the model, we used information from 238 wells from six fields. The obtained data was integrated into a 3D model of the field, which made it possible to clarify the porosity distribution and recalculate oil reserves.\u00a0<\/p>\n\n\n
\u201cWe carried out comprehensive work on collecting data, training and setting up the algorithm. As a result, the accuracy of porosity prediction increased by 56% compared to traditional methods,\u201d said Sergei Krivoshchekov, associate professor of the Department of Oil and Gas Geology at PNRPU.\u00a0<\/p>\n\n\n
The refined 3D model made it possible to identify additional zones with oil reserves that were not previously taken into account during field development. This made it possible to adjust the production plan and increase the volume of extracted resources.\u00a0<\/p>\n\n\n
\u201cThe developed approach allows for more efficient use of field resources, reducing costs and increasing production volumes,\u201d noted Georgy Shiversky, postgraduate student at the Department of Oil and Gas Geology at PNRPU.\u00a0<\/p>\n\n\n
A study by Perm scientists confirmed the promise of using artificial intelligence in oil production. The new method not only improves forecasting accuracy, but also opens up opportunities for more efficient field development. In the future, such technologies may become industry standard, combining traditional geological knowledge with modern advances in data analysis.<\/p>\n\n\n
Source: naked-science.ru <\/sub><\/p>\n\n\n Photo: 3D model. The resulting porosity cube \/ \u00a9 Sergey Krivoshchekov, Geosystem Engineering magazine<\/sub><\/p>\n\n\n <\/p>\n\n\n <\/p>\n\n\n <\/p>\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" Predicting reservoir properties is one of the key tasks in oil production, which allows one to assess the potential of a field and optimize its development. Traditional methods such as geophysical surveys and core analysis often face difficulties due to the heterogeneity of rock structure. Perm Polytechnic scientists p<\/p>\n","protected":false},"author":9,"featured_media":12448,"comment_status":"open","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_seopress_robots_primary_cat":"","_seopress_titles_title":"Artificial intelligence in oil production: Perm scientists increased forecasting accuracy by 56%","_seopress_titles_desc":"Perm Polytechnic scientists have developed a method for predicting the properties of oil reservoirs using AI. Forecast accuracy increased by 56%, which optimizes field development.","_seopress_robots_index":"","_seopress_analysis_target_kw":"","footnotes":""},"categories":[11],"tags":[320,321],"class_list":["post-60164","news","type-news","status-publish","has-post-thumbnail","category-it","tag-geofizicheskie-metody-razvedki","tag-iskusstvennyj-intellekt-v-geologii"],"acf":[],"pbg_featured_image_src":{"full":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-scaled.webp",1200,891,false],"thumbnail":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-150x150.webp",150,150,true],"medium":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-300x223.webp",300,223,true],"medium_large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-768x570.webp",768,570,true],"large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-1024x760.webp",1024,760,true],"1536x1536":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-1536x1140.webp",1536,1140,true],"2048x2048":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-scaled.webp",1200,891,false],"bricks_large_16x9":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-1200x675.webp",1200,675,true],"bricks_large":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-1200x891.webp",1200,891,true],"bricks_large_square":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-1200x1200.webp",1200,1200,true],"bricks_medium":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-600x445.webp",600,445,true],"bricks_medium_square":["https:\/\/geoconversation.org\/wp-content\/uploads\/2025\/02\/iskusstvennyj-intellekt-v-neftedobyche-600x600.webp",600,600,true]},"pbg_author_info":{"display_name":"Lyubov Cherkasova","author_link":"https:\/\/geoconversation.org\/en\/author\/amourallis\/","author_img":false},"pbg_comment_info":" No Comments","pbg_excerpt":"Predicting reservoir properties is one of the key tasks in oil production, which allows one to assess the potential of a field and optimize its development. Traditional methods such as geophysical surveys and core analysis often face difficulties due to the heterogeneity of rock structure. Perm Polytechnic scientists p","_links":{"self":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news\/60164","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/types\/news"}],"author":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/comments?post=60164"}],"version-history":[{"count":0,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/news\/60164\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/media\/12448"}],"wp:attachment":[{"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/media?parent=60164"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/categories?post=60164"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/geoconversation.org\/en\/wp-json\/wp\/v2\/tags?post=60164"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}