A new formula for oil and gas exploration

To position exploration as a key organic growth driver, oil and gas companies need to do two things: 1) improve the accuracy of their exploration analyses, and 2) significantly reduce the time it takes to produce the first barrel of oil. Digital technologies and advanced analytics can help companies achieve both imperatives.

Faster and better

Using today’s best practices, exploration accuracy tops out at just 50 or 60 percent. The cycle time of the asset (time to first oil) can take five to ten years. A huge portion of that time is spent evaluating the asset during the exploration phase and conducting geological and engineering analyses to mitigate risks associated with the asset’s production. Advanced analytics can help streamline and accelerate decision-making and allow companies to focus on overall asset economics in ways never before possible. That can boost exploration accuracy to 90 percent. At the same time, speeding up technical evaluations with digital and advanced analytics solutions can reduce cycle times to just one-tenth of what they have historically been.

This “90-10” model transforms three critical aspects of exploration:

• Evaluation consistency. Today, exploration relies largely on the judgment of experts, resulting in inconsistent decision quality and outcomes. Moreover, legacy workflows and data management systems make it difficult for those experts to use the relevant knowledge accumulated by the organization. New technologies change the game. AI-driven automation of certain tasks such as seismic horizon picking or log interpretation brings consistency to decision-making. Machine learning, which can be applied to recognize patterns in various subsurface models, improves the accuracy of interpretation and the efficacy of recommendations. This improved accuracy is key to winning in resource plays such as light tight oil, where identifying “sweet spots” makes or breaks the economic viability of assets.
• Value chain visibility. Traditional exploration approaches prioritize subsurface evaluation. Little consideration is given to other value chain issues such as development costs. With better data management systems integrated with technical workflows, explorers have access to information across the lifecycle of assets—from production behavior and pressure data to well tests. By applying analytics to this data, they can better understand the uncertainties that have the greatest potential economic impact.
• Speed to first oil. Today, geoscientists spend inordinate amounts of time searching for and organizing data, rather than generating insights. This issue can be addressed with digital platforms that not only make internal and external knowledge accessible to explorers, but make it possible for them to rapidly sift through large volumes of “raw” data (e.g. seismic surveys, logs) and “interpreted” data (e.g. seismic interpretation, log analysis, reports). The step change in evaluation velocity enabled by searchable, “Google-like” interfaces and AI-driven interpretation and modeling will increase the efficacy of the exploration function by an order of magnitude. As a result, explorers will identify significant volumes of near-field opportunities that are low-cost and lower-risk.

Reaping the rewards

A successful transition to the 90-10 model will require superior capabilities in several areas: data acquisition, storage, transmission, visualization and especially advanced analytics. New skills and new ways of working will also be key. Exploration teams must move away from performing analyses and towards validating recommendations generated by algorithms. As data starts flowing across functional silos, companies must re-imagine their exploration and production value chains. Changes in the way data is used will necessitate a redesign of how exploration works with other domains. Geoscientists and petroleum engineers must work alongside non-traditional functions such as data scientists.

The 90-10 model also calls for a new leadership mindset. Leaders must embrace this change, building a shared vision across their organization, reinforcing the need to heavily leverage new technologies and analytics platforms and skillsets, and guiding their teams as they adopt new ways of exploring the best resources rapidly from an abundant pool.

Implementing the new model will not be easy. But the ability to translate evaluation velocity and accuracy into profitability and growth will more than compensate for the effort required.