Well schematics techlog
In addition, we proposed the QC method for the verification of the spectral enhanced results. The comparison results showed that the ML model trained using SSI yielded better results. To investigate the performance of the developed method, we compared the spectral enhanced results from ML model trained by training data set generated using well log with those using SSI. To reflect the characteristics of the reflectivity series of the target seismic data in the training dataset without well logs, the results of sparse spike inversion (SSI) of the seismic data were adopted. In this study, to solve this problem, we suggested a ML-based spectral enhancement method where the characteristics of the reflectivity series of the target seismic data were extracted from seismic traces themselves. However, with well log data, the reflectivity series only at the well location can be computed and it may be quite different from the reflectivity series in the area far from the well. The characteristic of reflectivity series, one of the important features of target data, was extracted from well log data in previous studies. The Techlog Production Logging module enables you to perform a complete production logging workflow, from raw acquisition data to interpreted zonal flow rates to yield information about the type and movement of fluids within and near the wellbore. For generating ML model with high performance, the features of target seismic data must be reflected in the training data when the training dataset is numerically generated.
To enhance the vertical resolution of the seismic data, we present a method which broadens the spectrum of the seismic data by using machine learning (ML) technique. Vertical resolution enhancement of seismic data is a very useful tool for the interpretation of subsurface structures.