Oil Seeker is a research project exploring how stochastic analysis and 3D probability modelling can identify hydrocarbon signatures with minimal well data. Currently in active modelling phase.
The Problem
Hydrocarbon exploration remains one of the most capital intensive and uncertain processes in the energy industry. Traditional methods require extensive well data and often miss reserves in tight or unconventional formations.
Machine learning approaches attempt to solve this but require thousands of wells for training, produce black box results that are difficult to validate, and struggle with the rare event detection that exploration demands.
We believe there is a better way: using physics and stochastic analysis to detect hydrocarbon signatures from first principles, with minimal data requirements and fully explainable results.
Our Approach
Oil Seeker applies the same foundational approach we use across all our projects: physics-based modelling and mathematical analysis to find what conventional methods miss.
Designed to work with as few as 5 to 10 wells, compared to 1000+ required by machine learning approaches
Uses physics-based probability distributions to capture subsurface heterogeneity and identify anomalies
Builds complete probability maps from sparse well data using physics-based interpolation
Every detection comes with physical reasoning, not a black box confidence score
Where We Are
Oil Seeker is in active modelling phase. Here is what we have achieved so far and what comes next.
Potential Applications
If our modelling validates at scale, Oil Seeker could impact several stages of hydrocarbon exploration.
Reduce dry well risk before committing capital to new exploration areas
Identify sweet spots and undrained zones in producing fields
Find bypassed reserves in fields previously considered depleted
Detect hydrocarbons in tight and low permeability zones
Whether you're exploring risk analytics for your organisation or interested in our research, we're always open to a conversation.
