OREANDA-NEWS  Specialists of RN-Krasnoyarsk Oil (a research and design institute, part of the Rosneft research and design unit) have developed a software algorithm based on a neural network that reduces the time of one of the initial stages of seismic data processing by ten times. The software algorithm is available as an independent application for a personal computer (PC). This is stated in the message of Rosneft.

The volume of one project that a specialist works with when interpreting seismic information is 300 square kilometers or about 30,000 seismograms. Processing such a volume of data "manually" can take up to 80 working hours, while the created algorithm allows you to perform similar work for 7 hours without the direct participation of a specialist.

The main parameters for evaluating the effectiveness of the developed solution are not only a significant reduction in labor costs, but also the exclusion of the factor of subjective evaluation of the interpreter, since the work of the program is based on mathematical models, and not on visual perception of information. The created prototype of the program has been successfully tested on real seismic data obtained at two license areas of Rosneft in Eastern Siberia.