Utilizing Machine Learning to Evaluate the Connection between Poisson's Ratio and the Petrophysical Properties of Reservoir Rocks

Al-Obaidi SH, Khalaf FH and Viktor S

Published on: 2025-04-19

Abstract

The Poisson's ratio is a crucial cornerstone, illuminating our understanding of geomechanically behaviour in wells during the dynamic drilling process and the inspiring recovery journey. This research rigorously employs machine learning methods to analyse the significant impact of geophysical parameters on the Poisson ratio in hydrocarbon reservoirs found in oil fields. The analysis utilized data from multiple oil and gas fields, highlighting the crucial relationships between the Poisson ratio, the natural radioactivity of rocks, and the velocity of the longitudinal wave. Understanding these dependencies is essential for optimizing extraction processes and improving resource management. The PIK-UIDK/PL unit was crucial in conducting triaxial tests on samples in reservoir conditions. The insights gained from these tests have led to essential dependencies that underscore their significance.

Numerous geophysical well surveys are utilized to establish robust equations that define the relationship between the Poisson ratio and geophysical parameters. This is achieved through effective linear regression and advanced machine-learning methods. Based on these dependencies, the Poisson ratio can be assessed more accurately for various rocks and fields. In addition to improving efficiency in hydrocarbon production and optimizing oil industry operations, the findings can be used to improve forecasts and modelling for oil field development processes.