When geologists of Abu Dhabi National Oil Company (ADNOC) identified an opportunity to improve the way the company applies geomodelling for assessing hydrocarbon reservoirs, it's leaders turned to IBM and SAP for support.
With a daily production of about 3 million barrels of oil and 10 billion cubic feet of raw gas, Abu Dhabi National Oil Company is one of the globe’s leaders in the oil & gas energy and petrochemical sectors.
After identifying potential fields for exploration, ADNOC flies in geologists to explore the area, with their input crucial to next steps – including the feasibility and business case for exploration, and pinning down the best locations for drilling.
In their work, geologists used a labour-intensive process for classifying the characteristics of rock samples. Having seen best practices in industry, geologists put forward the initiative to apply the power of technology in order to classify rock samples more accurately. This is turn improve and could speed up the entire drilling strategy process, and free up their time for more value-adding activities.
Geologic modelling of hydrocarbon reservoirs
Together with IBM and SAP, ADNOC brought the proposed digital innovation to life. Using technology that has its origins in the world of flowers (where AI-engines identify flowers among thousands of different species), ADNOC deployed a solution that identifies classes of carbonate rock.
The solution works as follows. First, geologists feed high-resolution rock images into a database. The solution then matches the images with a database to classify the rock. Using IBM Watson – IBM’s artificial intelligence engine – ADNOC’s geologists can then more effectively digitally construct reservoirs – and simulate all kinds of decision-making factors.
Engineers construct reservoir simulation models to test reservoir behaviour, including storage space (porosity), the ability to flow (permeability) and the amount of oil (potential recovery). The models allow engineers to consider different development characteristics, including well spacing, the type of well, the number of wells and pressure maintenance schemes.
Using the new artificial intelligence-driven solution, image classification is much faster and more automated (bringing down the time to analyse all of the samples taken from a single reservoir from months to minutes), and in addition, more effective simulations can be designed and tested.
“The new way of working not only increases the delivery speed and consistency of reservoir rock samples, it also de-risks [multibillion dollar] reservoir development decisions,” said Hani Abdulla Nehaid, Teamleader Geology and Geoscience at ADNOC.
The tech-driven solution further helps ADNOC institutionalise one of the key challenges it faces over time: the transfer of knowledge to the next generation. “The solution helps us preserve expertise that geologists have spent decades developing, and with transferring that knowledge to younger generations.”
Meanwhile, for IBM and SAP, the tandem with ADNOC was a first-of-a-kind application of artificial intelligence in the rock classification scene.
“When we started out, there was a very important question – can artificial intelligence really be applied to such a technical domain as geology,” reflected Yahya Mahmoud, Industry Leader for Industrial Products, Chemicals and Petroleum at IBM. “But having now seen the outcome and its impact, it is an eye opening experience for us and the industry.”
Talal Malas, Cognitive and Analytics Practice Leader at IBM, added: “This initiative with ADNOC is one of the most exciting use cases in the chemicals and petroleum industry – cognitive geology, which emulates geologists and petrophysicists in classifying rock samples with high accuracy at an enormous scale. It’s the perfect example of how AI boosts productivity and frees up highly skilled experts for higher value activities.”
In the coming period, ADNOC, IBM and SAP will expand their solution with other areas that can provide predictive insights, such as seismic data. Hesham Shebl, Technical Center Geologist at ADNOC, said that the team will also seek to explore more advanced technology such as machine learning to help geologists create more complete and accurate geological models.
“The more data points we can use, the better and more efficient our models, our development plans and our ultimate hydrocarbon recovery will be. This is fundamental to the success of our industry,” he concluded.
Sourced from Consultancy.me