One of the priority tasks of the Tyumen Petroleum Research Center (a subsidiary of Rosneft Oil Company) is the development, testing, and introduction of new interpretation methods and technologies that will improve the efficiency of petrophysical support of the Company's projects on reservoir management, exploration, and reserves estimation. Modern petrophysics is steadily progressing towards digitalization, machine intelligence, and big data processing. At the same time, the developed digital assistants, of course, are not yet a replacement for a human interpreter. However, the role of such unmanned algorithms is becoming more and more significant, leading to a gradual replacement of unproductive manual labor in the field of routine preparatory design work. This should result in a dramatic reduction in the time spent on petrophysical projects. At the same time, the role of a human interpreter should increasingly be reduced to the “programming” of such digital assistants and mainly analytical activities, which leads to a qualitative shift in the field of depth and detail of petrophysical solutions. It is also obvious that the analysis of large amounts of data will allow finding new efficient tools for predicting petrophysical and geological properties, as well as a new level of performance estimation. At the same time, these new technological and information standards dictate new requirements for the competence profile of an interpreter engineer, in addition to the traditional baggage of petrophysical knowledge, developed IT competencies and, at least, basic programming will be a natural addition. Thus, digitalization, artificial intelligence and analysis of big data should clearly lead to a new round of development in petrophysics and a qualitative increase in the efficiency of petrophysical support for exploration and development of oil and gas fields.
References
1. Basyrov M.A., Khabarov A.V., Khanafin I.A. et al., Advanced technologies of well logging and data analysis (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2019, no. 11, pp. 13–17.
2. Zichao Yang, Diyi Yang, Dyer C., Xiaodong He et al., Hierarchical attention networks for document classification, San Diego, California: Association for Computational Linguistics, 2016, pp. 1480–1489, URL: https://www.aclweb.org/anthology/N16-1174
