The Geomex Technologies company took part in the International Conference and Exhibition of SPE/AAPG/SEG – “Latin America Unconventional Resources Technology Conference” (LA-URTeC 2023), Buenos Aires, Argentina, December 2023. At the conference, for the first time, the information about launching the new company processing cluster is presented. Cluster is based on compact graphics NVIDIA accelerators. It installed in Mexico City. The performance of the new GPU cluster is 1.2 Petaflop. Data storage system is 1.2 Petabytes; the power consumption is no more than 6 kW. On the basis of the cluster, the “RTH Imaging Engine» software and hardware complex was launched for ultra-fast calculation of seismic attributes using the RTH method.
Paper abstract. The paper discusses exploration and development issues using artificial intelligence methods based on new seismic attributes of the RTH (Reverse Time Holography) method and well drilling data. RTH attributes are based on two-stage seismic data processing: on decomposition the initial common shot gathers in common image gathers, using the time-reversal algorithms and on synthesis a seismic attributes. It is shown that a detailed analysis of the joint behavior of two vectors: the velocity vector in forward wave and the velocity vector in time-reversed backward scattering wave provides detailed information about the medium. The main differences between RTH attributes and traditional ones obtained during migration are their voxel nature and hyperattributivity. It turned out that this is a key advantage of the new approach to solving problems of geological prediction using artificial intelligence methods. The paper presents the results of using the new method for processing and interpreting 3D seismic data, as well as geological prediction based on RTH attributes for a number of oil and gas fields.
Gennady Erokhin; Mariia Erokhina; Kirill Safran and Alexandre Iakovlev
Paper presented at the SPE/AAPG/SEG Latin America Unconventional Resources Technology Conference, Buenos Aires, Argentina, December 2023.
Paper Number: URTEC-2023-3968978-MS
https://doi.org/10.15530/urtec-2023-3968978
Published: December 04 2023
The Geomex Technologies Company took part in the Caspian Technical Conference, 21 – 23 November 2023, Baku, Azerbaijan. A report entitled “Exploration and Development with the Reverse Time Holography Technology” was presented at the conference.
Paper abstract. The article analyzes methods for constructing seismic attributes, which are based on two-stage data processing: on decomposition the initial common shot gathers in common image gathers, using the time-reversal algorithm and on synthesis a seismic attributes. It is shown that a detailed analysis of the joint behavior of two vectors: the velocity vectors in forward wave and the velocity vectors in time-reversed backward scattering wave provides detailed information about the medium. This is the essence of a new approach called RTH, which allows the acquisition of various seismic attributes at high spatial resolution. The new approach provides the solutions of prediction problems in oil and gas exploration, as well as problems in development using the drilling data and AI algorithms, at a new qualitative level.
Erokhin, M. Erokhina, K. Safran
Publisher: Society of Petroleum Engineers (SPE)
Paper presented at the SPE Caspian Technical Conference and Exhibition, November 21–23, 2023
Paper Number: SPE-217596-MS
https://doi.org/10.2118/217596-MS
RTH Imaging Engine
Geomex Technologies offers the RTH Imaging Engine (RTH IE) – the hard & software
solution for specialized processing of 2D/3D seismic data and imaging by Reverse Time
Holography (RTH) method. The method is a further development of the depth-based
Reverse Time Migration (RTM) method, taking into account the vector nature of seismic
information. The main difference between these methods is the way they decompose
common shot gathers dataset into common image gathers (CIG) dataset. In RTM CIG
dataset have a parameter dimension of 2, whereas in RTH they have a parameter
dimension of 8. This circumstance significantly expands the class of scattering models
used in RTH and ensures the hyperattributivity of the RTH method. The latter fact, along
with the voxel nature of the depth-based RTH method, ideally matches with well-log data
and provides high technology and accuracy in predicting geological and petrophysical
parameters of the media based on machine learning.
The new RTH method is based on more general seismic scattering models than those
used in traditional reflection-based seismic exploration during the past 70 years. The
RTH method marks the emergence of a new seismic paradigm – “Time-dependent
scattering seismic”. This paradigm changes not only a data processing stage, but also a
data acquisition stage and an interpretation stage. In particular, the RTH stochastic
acquisition system makes it possible to use irregular observation systems and
significantly reduces the number of sources used.
The input data for RTH processing are standard seismograms of the common shot point
or 2D/3D CDP data of average fold – no higher than 80. The RTH method is an
alternative to depth migration methods, as well as AVO and FWI. The RTH method was
developed in 2017 and successfully tested at 21 hydrocarbon fields. RTH software is
patented. The essence of the RTH method has been published in 20 articles and has been
presented at international conferences, including EAGE, SEG and SPE.
At the heart of RTH IE’s efficiency lies its innovative mathematical algorithms and
software, harnessing the immense power of high-performance parallel computing on
graphics accelerators (GPUs) boasting a staggering performance of 1 Petaflops and data
storage capabilities are exceeding 1 Petabyte.
Operating on the robust Linux platform, the RTH IE boasts a power consumption of
approximately 6 kW and fits neatly into a 12U in rack system and with the weight not
more100 kg. The RTH IE software has its own developed graphical interface for setting processing
parameters, launching programs and viewing calculation results.
20 Nodes, 1.2 Petaflops.
Data Storage, 1.2 Petabytes.
RTH IE graphical interface
Node, 2 GPU
Geomex Technologies Company took part in 84th EAGE Annual Conference & Exhibition, which took place in Vienna 5-8 June, Austria ( https://eageannual.org/eage-
Geomex Technologies Company acted as a silver sponsor of The International Meeting for Applied Geoscience & Energy IMAGE’23 , 28 Aug–1 Sept 2023 Houston, Texas (https://www.imageevent.org/).
