Preliminary work on core automated description by a group of researchers from Skoltech and Digital Petroleum was published in 2018. The need to standardize core description using modern algorithms was born a long time ago. By 2020, CJSC MiMGO sedimentologists have joined the project. This cooperation allowed for developing and adjusting the software product that helps solve practical tasks which are crucial for sedimentological work.
DeepCore Software enables quite an accurate and high-speed classification of core photos by various rock and texture types. Besides, it specifies other features based on the task chosen by a sedimentologist.
To start work, it is necessary to upload core photos which names shall contain information on depth positioning. Then, a few simple steps lead to an automated photo analysis. Core is extracted from boxes and classified.
This classification provides the user with a core description in table and graphical form. Each class determined by the algorithm has a probability estimate of correlation. The application allows for adding classes or create a collection of classes in a new description model. Obtained results can be also exported for further investigation.
CJSC MiMGO specialists with vast experience in core data processing and interpretation perform the assessment and, if necessary, correction of machine learning algorithms on real borehole data.
Please, send your questions about sedimentologists' experience with DeepCore Software to This email address is being protected from spambots. You need JavaScript enabled to view it..
Digital Petroleum - artificial intelligence in the oil and gas industry.
Digital Petroleum is a company developing AI-based IT tools and providing services on the tools incorporation into production operations as well as software maintenance and customization.
Learn more about DeepCore: website SK and here.