Pre Stack Solutions-Geohas signed the contract with the Research Council of Norway
We are happy to share that today, Pre Stack Solutions-Geo AS has signed the contract with the Research Council of Norway to conduct a two years research study of Pre-stack implementation of the AI-based seismic inversion algorithm with artificial constraints.
The project aims to develop an AI-based pre-stack seismic inversion algorithm with a radically new solution approach. Combining metaheuristic procedures and designed artificial constraints reveals the unexampled possibility of estimating non-linked rock properties from the seismic data.
We expect this new algorithm to benefit the estimation accuracy of rock properties and substantially reduce the man-hand influence and processing costs.
No algorithms and methods are available in conventional physics to estimate non-linked properties of the Velocity and Density of the rocks from seismic data. Oil and gas exploration mainly uses these properties as a basis for further lithology and fluids prediction. Presently, all existing approaches to seismic inversions are based on the following fundamental assumptions: the linearization of the Zoeppritz equation, the estimation of impedances or elastic parameters, and the extraction through regressions of linked Velocity and Density. Even though "the regressions" have gotten more sophisticated (using statistical or ML methods) - they are still regression approaches.
We aim to overcome regression problems and obtain an accurate estimation of the Velocity and Density that removes the gap between pure seismic structural interpolation and quantitative interpretation (QI). Using only a conventional physical approach leaves QI as supplementary with less trustable methods due to fundamental assumptions/limitations.
What are the expected benefits?
The application of the proposed technique for high-resolution shallower seismic will significantly improve geohazard studies for seabed installations and windmills. It greatly reduces the required time and resources to achieve a high-resolution velocity field with full frequency band. FWI is, in comparison, less efficient and can only generate results with limited frequency band. In the field of seabed mining (SBM), the technology will directly allow the mapping of rock properties with information on the spreading of geo bodies or the accumulation of specific minerals.
We thank the Research Council of Norway and Lime Petroleum AS for supporting the project!
If you are interested in being a part of the project to get software or cloud access, do not hesitate to contact barbara@pss-geo.com
Comments