Seismic data are recorded and commonly interpreted in vertical two-way time; well logs, measured in depth, must be tied to seismic using a time-depth curve. However, well ties contain a large amount of uncertainty due to errors in the generation of synthetic seismograms and manual matching of synthetic seismograms to seismic traces. Using dynamic time warping, a fast algorithm that optimally al...

Well log correlation is an important step in geophysical interpretation, but as the number of wells increases, so does the complexity of the correlation process. We propose a new method for automatic and simultaneous well log correlation that provides a globally optimal alignment of all logs, and in addition, is relatively insensitive to large measurement errors common in well logs. First, for ...

The representation learning problem in the oil & gas industry aims to construct a model that provides based on logging data for well interval. Previous attempts are mainly supervised and focus similarity task, which estimates closeness between intervals. We desire build informative representations without using (labelled) data. One of possible approaches is self-supervised (SSL). In contrast pa...

Intelligent reservoir characterization using seismic attributes and hydraulic flow units has a vital role in the description of oil and gas traps. The predicted model allows an accurate understanding of the reservoir quality, especially at the un-cored well location. This study was conducted in two major steps. In the first step, the survey compared different intelligent techniques to discover ...