AI-optimisation of oil and gas field portfolio development under CO₂ and capital constraints
Upstream investments involve portfolio decisions subject to strict constraints: Capital, emissions, risk profiles, development sequencing and strategic objectives all interact simultaneously.
In practice, fields are often evaluated individually and then prioritised. The constraints – CAPEX limits, emissions budgets or strategic minimum shares – are only taken into account at a later stage.
This rarely leads to the best combination, but rather to a sequential selection that disregards combinatorial trade-offs.
Domain
Energy / Upstream Investment
Objective
Maximisation of the net present value (NPV) of the selected field portfolio whilst adhering to a fixed CAPEX budget and a CO₂ emissions budget – supplemented by strategic requirements (e.g. offshore/onshore mix).
Assessment Inputs
Portfolio modelling is based on project-related input data, typically:
- CAPEX per field (USD)
- Lifecycle CO₂ emissions (tonnes)
- Expected NPV (discounted cash flows)
- Strategic tags (e.g. offshore/onshore, region, risk/maturity level, partner structure)
Decision model and selection mechanism
Each field is modelled as a binary selection decision:
- Decision variable xᵢ ∈ {0,1} for each field (0 = do not develop, 1 = develop)
- Optimisation objective: max Σ NPVᵢ · xᵢ
The crucial point is the selection logic: It is not a case of ‘ranking each field individually’ and then adjusting them manually, but rather the ranking is derived from optimising the best combination subject to constraints. This reveals combinatorial trade-offs that are typically lost in individual assessments.
Constraints
The portfolio is calculated subject to explicit restrictions, e.g.:
- CAPEX budget: Σ CAPEXᵢ · xᵢ ≤ 2 billion USD
- Emissions budget: Σ CO₂ᵢ · xᵢ ≤ 5 million tonnes
- Strategic minimum requirement (offshore example): Σ i∈offshore xᵢ ≥ 2
This combination of financial, regulatory and strategic constraints makes the decision non-linear, rather than combinatorial. This is precisely why portfolio logic is crucial.
Technology approach
A hybrid decision-making architecture is employed:
- StratePlan Hybrid-Techs for combinatorial portfolio optimisation under constraints
- MCDA (Multi-Criteria Decision Analysis) for the strategic weighting and classification of qualitative factors (e.g. strategic tags, risk/maturity level, location logic)
Outcome logic
The outcome is not merely a list of ‘top projects’, but a consistent portfolio decision:
- Maximises NPV within restrictive CAPEX and CO₂ limits
- Meets strategic minimum targets (e.g. offshore mix)
- Makes trade-offs transparent (value contribution vs. emissions vs. capital commitment)
Conclusion
Optimising an oil and gas field portfolio under CO₂ and capital constraints is not a ranking problem, but a combinatorial selection problem.
Only when valuation, constraints and group selection are brought together in a formal model, can the best combination of fields be systematically determined – thereby measurably improving the quality of decision-making.
Common Patterns Across Cases
Assessment
Qualitative and quantitative factors are converted into comparable scores – using scales, valuation models or structured expert assessment. The aim is to establish a consistent, decision-ready evaluation basis.
Ranking
Elements are prioritised. However, ranking is rarely the final decision. In complex environments, prioritisation is frequently embedded directly into a combinatorial optimisation process in order to systematically account for interactions and constraints.
Group Selection
The final selection goes beyond a simple ‘Top-k’ approach. StratePlan solves structured selection problems such as knapsack, portfolio or scheduling models and calculates the optimal combination under real-world constraints.
Constraints
Constraints reflect real-world scarcity: capital, time, resources, risk appetite, regulatory requirements, strategic mandates or sustainability requirements. They are an integral part of the decision-making logic.
Technologies
Hybrid use of MCDA methods (e.g. AHP, TOPSIS) for structured evaluation combined with StratePlan for constraint-aware group or portfolio selection.
These cases demonstrate how StratePlan evolves decision-making processes from pure ranking to intelligent, constraint-aware portfolio construction. Evaluation data is translated into actionable, optimised group decisions – aligned with financial, strategic and sustainability-related objectives.
The underlying core logic – structured evaluation → quantitative prioritisation → constrained group selection – scales across different sectors and is adapted in each case to domain-specific success metrics and constraints.
