Our processing is automated, removing human interpretation as much as possible. Futhermore, we have developed advanced machine learning techniques, which enable us to extract information relevant to micro annulus detection and include that in the final evaluation.
The optimal solution is found by combining knowledge of the underlying physics with machine learning. Several different processing techniques have been developed, some target physical parameters and others use advanced machine learning. Additionally, we have developed many post-processing techniques.
Using these we can calculate the total length of the sealing barrier; the top of cement; distinguish different types of bonding; divide the well into different sections based on the characteristics and provide information about the micro annulus thickness.
From this, Equanostic can provide an answer as to whether the cementing job during drilling and complementation meets requirements. This will result in risk reduction and cost savings for drilling and completion, greatly benefiting the oil & gas industry and the carbon capture storage chain.
The analysis is done using data from qualified well logging technology. This type of logging is already performed across large parts of Norway and Europe, allowing our techniques to be applied quickly to existing data.