Alterna – kognitus

AI-Assisted O&G Exploration: The Challenges and Opportunities in Unlocking Higher Value from Subsurface Data

admin — Mon, 29 Nov 2021 10:58:53 +0000

ACGGP | 4th Oil & Gas Summit

The crisis triggered by the coronavirus pandemic and society’s growing concern with climate change brought enormous uncertainty regarding the future of global demand for oil and gas and about the level of exploratory activity necessary to meet it. As a result, current industry trends point to a prioritization of short-cycle development opportunities over greenfield projects and infrastructure-led exploration over frontier plays. To keep up with this shift in focus, exploration teams must analyze increasing volumes of legacy data from mature areas with increasingly shrunken resources and timelines. Opportunely, such dramatic changes occur at the moment when a digital revolution is underway. This work discusses what Artificial Intelligence (AI) means for subsurface analysis, as well as the challenges and opportunities it poses for O&G exploration teams. Some of the challenges are related to the unique characteristics of the subsurface domain, such as data sparsity and uncertainty, strong spatial dependence, and complicated physics background. Other challenges are associated with the business and operational context of the O&G industry, such as data silos, shortage of Data Science skills, and availability of domain-specific AI platforms. We will present case studies demonstrating how applying the latest AI and cloud computing technologies can automate and accelerate the analysis of large-volume datasets, provide new insights from legacy data and support faster and better decisions.

Examples include automatic correlation of multiple well logs at scale, prediction of reservoir rock properties in 3D grids, automatic seismic interpretation and geobodies detection, and AI-assisted geologic risk assessment for O&G exploration.

Investigation of migration dynamics in Sergipe-Alagoas Basin (Brazil): insights from a global sensitivity analysis powered by machine learning

admin — Wed, 29 Sep 2021 09:53:45 +0000

The Geological Society – Workshop Basin and Petroleum Systems Modelling: Best Practices, Challenges and New Techniques

In the last decade, a series of light oil and gas discoveries renewed interest among oil industry players in the deep and ultra-deep-waters of the Sergipe-Alagoas (SEAL) Basin (Rodriguez et al., 2017). Some oil seeps are observed in the basin and could be used to guide the exploration. Although oil seeps are considered a strong indicator of the presence of a working petroleum system, they often cannot be unequivocally associated with a particular petroleum accumulation, notably in offshore areas.

In this study, we used a combination of 3D Petroleum System Modeling with a Machine Learning-powered global sensitivity analysis to investigate the occurrence and geologic controls of oil seeps in the deep offshore SEAL basin. The integration of SAR images and oceanographic modeling (Mano et al. 2014), and piston core data provide the basis for locating the oil seeps in the seafloor.

The global sensitivity analysis was performed using a modern Machine Learning approach to account for geological uncertainties and rank the main geological features responsible for the observations (Ducros & Nader, 2020; Ducros & Gonçalves, 2020). The analysis accounted for several input parameters, such as the organic richness of source rocks, effectiveness of seals, and nature of the overburden sequence.

The results indicate that hydrocarbon charge is not a limiting factor in the area. The quality of the Campanian-Maastrichtian seals appears to control the volume of accumulated hydrocarbons in the known fields. Seeps occurrences generally occur associated with prominent structural highs and seem strongly influenced by the sealing capacity of the overburden.

Only one observed seep can be unequivocally related to a known petroleum accumulation. The origin of all the other seeps can be explained without the existence of an underlying hydrocarbon occurrence. Therefore, although seeps in the study area cannot be used as direct indicators of petroleum accumulations, they are solid evidence of a working source rock and can be employed to constrain better the sealing effectiveness of the overburden.

The results further indicate that a more detailed risk analysis integrating the geometrical uncertainties related to time to depth conversion and the distribution of the reservoir bodies, for instance, would improve constraining the sealing capacity of the Campanian-Maastrichtian layer. Risk analyses show that a better understanding of the seal properties would help to reduce the uncertainty on the prediction of trapped hydrocarbons properties (GOR and API).

This study demonstrates how a robust sensitivity and risk analysis powered by machine learning can bring valuable insights into petroleum system risk assessments more efficiently than classical scenario testing approaches.

Digital subsurface transformation: challenges and perspectives towards an AI-assisted G&G workflow

admin — Wed, 09 Dec 2020 10:50:00 +0000

IBP - Rio Oil & Gas Expo and Conference 2020

The O&G industry is being disrupted at multiple levels by changes in the global energy landscape, business and operating models, and geopolitical order. Such a confluence of elements occurs at the moment when a technological revolution is also underway. This work focuses on discussing what Artificial Intelligence (AI) means for the subsurface data analysis and G&G disciplines. Despite all the enthusiasm around the topic and the proliferation of AI pilot projects, an effective insertion of these technologies in the mainstream of G&G workflow still poses significant challenges. Some of them are related to the unique characteristics of subsurface data, such as marked data sparsity, a high degree of uncertainty, strong spatial dependence, and complicated physics background. Other challenges are more related to the business and operational context of the O&G industry, such as domain silos in data infrastructure, difficulties to assemble teams with the required mix of skills, obstacles to deploy ML and DL solutions in a timely and reliable way and availability of domain-specific AI platforms. This work will demonstrate some examples of how a cloud-native AI platform for G&G can be employed to automate the analysis of large-volume datasets at scale and to solve existing subsurface problems such as prediction of missing well log curves, seismic inversion, reservoir properties prediction, seismic interpretation and seismic data compression.

AI and Petroleum System Risk Assessment

admin — Sun, 01 Mar 2020 09:11:27 +0000

GeoExpro Magazine | Mar 1, 2020

At this turning point for the oil and gas industry, with escalating competitiveness and a need to optimise productivity, petroleum companies must pick their new exploration projects carefully, making sure the returns have the potential to be as high as possible, while keeping the costs and risks low. Numerical methods such as petroleum system modelling (PSM) or forward stratigraphic modelling have proved that they can play a key role in the assessment and mitigation of exploration risks in both mature and frontier areas.

However, in order to keep up with the evolution of geological knowledge through a prospect’s life cycle, these powerful simulation methods can be very labour-intensive, which hampers the regular updating of the models with the most recent data and information.

Taking these issues into consideration, a new solution that takes advantage of the investments made in numerical modeling has been developed by Kognitus, a technology company that specializes in the use of analytics and AI to help O&G companies gain insights from subsurface data.

The system is based both on knowledge gleaned from experts, which enhances and guides the determination of the uncertainties, and on machine learning (ML) techniques, which provide maps of risks at exploration scale and in timeframes compatible with operational studies. Essentially, the solution takes the explorationist’s petroleum systems model as an input from which to infer geologically meaningful uncertainties. This solution is a first step in making basin modeling useful throughout the full life cycle of E&P assets by continuously updating the geological model as new data is acquired.