Much of the globe still relies on fossil fuels to supply its energy needs. However, while energy consumption increases, the amount of fuels available and found already drastically decreases. Therefore, the oil and gas industry have to search for new resources and it becomes more and more challenging.
For this reason, Petrogal Brasil (under Galp) and IBM Research-Brazil undertook a three-year project under the Brazilian National Petroleum Agency (ANP) R&D incentive regulatory framework. They developed a tool that advises geoscientists in the interpretation of seismic images and identification and evaluation of the exploration prospects. The tool uses AI to facilitate creation of enhanced geological models, risk assessment of new prospects, and optimization of new oil wells.
It follows a typical AI pattern: by gathering more information it becomes more precise and effective. In this case, the information is generated from previous seismic interpretations or from interactions with users. In order to help geoscientists with sifting through large 3-D seismic data sets, AI-based visual comprehension is used. Additionally, it quickly identifies geological structures that could bear oil and gas.
The tool gathers data from seismic images, academic papers, notes, and reports. Then, it automatically analyzes the provided information, gives the user advices or suggestions on how to interpret subsurface images, and aids in risk assessments.
The tool can also boost the development of young professionals’ skills since the information can be accessed easily and instantly. It can also perform a transversal and comparable risk analysis, avoiding individual bias and making the information comparable across the board (from one project to another, one geography to another, one decade to another).
AI is the technology that will push science forward. It is able to resolve problems of higher complexity quicker and more precisely than a group of the best world’s researchers.
Currently, the tool is being tested, and additional features are being developed. If this tool proves itself to be successful and useful, the technical and scientific competencies of both IBM and Galp will grow.