New advances in data-driven models and deep learning offer unprecedented insight into data and their correlations. Yet, observations and correlations alone can only inform based on what is in the data and not the causal effects in the systems producing the data.
About the RaPiD project
The RaPiD project (Reciprocal Physics and Data-driven models) aims to provide more specific, accurate and timely decision support in operation of safety-critical systems, by combining physics-based modelling with data-driven machine learning and probabilistic uncertainty assessment. The rationale that we need to combine our causal knowledge with all relevant data runs throughout all the research within this project and its case applications.
For example, weather scenario simulations for offshore drilling don’t capture scenarios that have not yet been experienced; by better use of the combination of observed experience and physics-based models, potential down time can be reduced significantly, reducing unproductive rig time by millions of USD per year. Watch a video presenting research of this case application at the end of the article.
We will develop and document the methodologies and technologies needed to consistently combine physics-based and data-driven models to alleviate the deficiencies of both by capturing their complementary advantages.
Invitation to contribute
Potential case applications are vast and diverse, from road bridge maintenance to design and validation of offshore wind turbines. We therefore invite the industry to challenge the RaPiD project with interesting case contributions.
Please contact Simen Eldevik or Frank Børre Pedersen.
RaPiD will contribute with a consistent decision process that take full advantage of both data-driven experience and physics-based logical reasoning. If you apply data-driven or physics-based models, we would like to talk to you about how these can be combined to reduce uncertainty.