AI-supported inversion of marine CSEM measurements

Kontrollert-kilde-elektromagnetiske data (Controlled source electromagnetic, forkortet CSEM) brukes til å avbilde resistivitetsegenskapene i undergrunnen. Teknologien har utviklet seg betydelig de siste 20 årene, med flere anvendelser innen petroleumsindustrien, innen kartlegging av dyphavsmineraler, kartlegging av grunnvannsreservoarer og innen geoteknikk. Den største hindringen for mer omfattende anvendelse av CSEM er flertydigheten av resultatene. Målingene må modelleres for å representere geologiske legemer i 3D. Flere modeller kan tilfredstille de samme målingene, og brukeren sitter igjen med store usikkerheter.Vi foreslår å kombinere CSEM-teknologien med nylige framskritt innen teknologien rundt kunstig intelligens. Vi ser et stort forbedringspotensiale i invertering og modellering av CSEM-data ved bruk av AI-metoder i en ny arbeidsflyt.

Better and more cost-effective identification, delineation and monitoring of geological units and natural resources will benefit the society at large. In this project we are focusing on marine CSEM data, with the potential to identify oil and gas resources and monitor CO2 storage sites. CSEM can improve the ability to cost-efficiently discover marine minerals of commercial quantities, which may be part of the mineral supply. CSEM is already in use for mapping of the shallow offshore section, and onshore mapping of mineral deposits, sediments, and freshwater aquifers, activities representing a substantial potential for value creation. If successful, results of the project can be applied to other inverse geophysical problems. Since the code will be released under an open source license, researches and developers will obtain the possibility to contribute to the further development of a probabilistic approach and we expect an increase of R&D activities in this area.

CSEM data is proven to be very valuable in hydrocarbon exploration due to the sensitivity of electromagnetic energy to net reservoir volume (porosity) and hydrocarbon saturation that is derived from the resistivity distribution. CSEM, however, does not measure resistivity directly. To obtain resistivity, an inverse problem must be solved. Under inverse problem we understand the situation where electromagnetic response to given sources is measured, while resistivity distribution is unknown and must be estimated. However, this problem is ill-posed from the mathematical standpoint. CSEM inversion is a non-linear problem, that is, small changes in the measurements can lead to large changes in the estimated model parameters; moreover, non-linearity of the problem is even more pronounced by the presence of noise. In addition, the solution of the problem is non-unique since observations can fit more than one model. Complexity and instability of the traditional inversion process prevents CSEM from being used to its full capacity. In recent years researchers started to explore possibilities to apply deep learning methods to the geophysical inversion. The results demonstrate capabilities of the deep learning to cope with such a challenging problem, however, examples presented are more of an illustrative nature. In this project we will further investigate applicability of ML methodologies to processing and inversion of CSEM data. Our rationale behind the choice of this methodology is connected to the opportunity to reduce significantly processing and inversion time. Our goal in this project is to develop a methodology for efficient probabilistic inversion of CSEM data. Both PINNs and cGANs use already probabilistic principles, and building on top of these methods will allow for the development of the probabilistic inversion methodology that is much faster than the traditional one.