Prediction of geophysical properties of rocks on rare well data and attributes of seismic waves by machine learning methods on the example of the Achimov formation
This work addresses a domain-specific challenge in oil field exploration in Western Siberia, but it is incremental as it applies existing machine learning methods to a new dataset.
The study tackled the problem of predicting sand body development in the Achimov formation using well log data and seismic attributes, achieving acceptable prediction quality as confirmed by cross-validation and new well data.
Purpose of this research is to forecast the development of sand bodies in productive sediments based on well log data and seismic attributes. The object of the study is the productive intervals of Achimov sedimentary complex in the part of oil field located in Western Siberia. The research shows a technological stack of machine learning algorithms, methods for enriching the source data with synthetic ones and algorithms for creating new features. The result was the model of regression relationship between the values of natural radioactivity of rocks and seismic wave field attributes with an acceptable prediction quality. Acceptable quality of the forecast is confirmed both by model cross validation, and by the data obtained following the results of new well.