Gas forecast (km3/d)
Problem
An operator has the complex task to plan and manage an active drilling program with 5 rigs and a portfolio of hundreds of different exploration and development projects.
The projects all vary in front-end maturity, duration, value, location and hydrocarbon type.
Oil delivers most economic value per barrel, but meeting the existing gas contract is important for the company's reputation.
Use Game AI approach to create optimized sequences for different value drivers, and test robustness against uncertainties.
Process
We translated the company's rig sequence management into a game, and taught an AI agent to play this game.
Through self-play, the AI learns to master the game mechanics and to develop sequences that outperform human planning capability.
Using our AI as a planning assistant, we can now develop rig sequences much more efficiently than before.
Different business drivers are translated into alternative sequences for better decisions. Robustness against key uncertainties can be verified. And managing change becomes much easier.
Dashboard
Use the settings below to reflect the gas contract as an important driver, or not. And to perform robustness checks on project schedules and exploration outcome. Evaluate how these settings lead to different optimized rig sequences and use this insight to make the "right" decision.
GAS CONTRACT
SCHEDULE
EXPLORATION SUCCESS
Gas forecast (km3/d)
Oil forecast (m3/d)
Capex forecast (mln USD)
10 yr CAPEX spend(mln USD)
13.180
10 yr EXPEX spend(mln USD)
1.900
10 yr NPV(mln USD)
5272
Timeline