Technological breakthrough - improving predictive power
Solution Seeker, a Norwegian tech start-up, has had a breakthrough in the technical development of its artificial intelligence for real time oil & gas production optimization.
- Author
- Solution Seeker
- Publish date
- · 2 min read
After several years of research on machine learning algorithms running on oil & gas production data, Solution Seeker has developed a hierarchical neural network model that significantly improves the predictive power for real time production optimization. The model leverages the power of neural network learning algorithms combined with domain knowledge in the form of first principle physics and production system logic.
The neural network takes further advantage of Solution Seeker’s proprietary algorithms for data analysis, which automatically extract and prepare suitable training data from the production data history. New training data is generated in real time as the system is operated, and the neural network model learns to adapt to the changing operational conditions with minimal human intervention.
The new learning algorithms will first be deployed at ENGIE E&P’s Gjøa field and Wintershall’s Vega field early next year.
The full stack AI deploys a three-step Solution Seeker proprietary technology pipeline, from data analytics to machine learning to optimization. The data analytics algorithms perform automatic pattern recognition, classification, statistical analysis and compression of thousands of live data streams. The learning algorithm then identifies field behavior and relations, and enables estimation of parameters, correlations and quantification of uncertainty before automatically generating predictive models while continuously learning from new production data. Finally, Solution Seeker’s proprietary optimization algorithm provides a framework for scalable optimization on the predictive, stochastic models.
The AI makes use of the very best available technologies, such as Google’s TensorFlow for machine learning, and is powered by cloud computing technologies to achieve reliability and performance.
