Machine Learning: A Useful Tool in Geomechanical Studies, a Case Study from an Offshore Gas Field

Abstract

<jats:p>For a safe drilling operation with the of minimum borehole instability challenges, building a mechanical earth model (MEM) has proven to be extremely valuable. However, the natural complexity of reservoirs along with the lack of reliable information leads to a poor prediction of geomechanical parameters. Shear wave velocity has many applications, such as in petrophysical and geophysical as well as geomechanical studies. However, occasionally, wells lack shear wave velocity (especially in old wells), and estimating this parameter using other well logs is the optimum solution. Generally, available empirical relationships are being used, while they can only describe similar formations and their validation needs calibration. In this study, machine learning approaches for shear sonic log prediction were used. The results were then compared with each other and the empirical Greenberg–Castagna method. Results showed that the artificial neural network has the highest accuracy of the predictions over the single and multiple linear regression models. This improvement is more highlighted in hydrocarbon-bearing intervals, which is considered as a limitation of the empirical or any linear method. In the next step, rock elastic properties and in-situ stresses were calculated. Afterwards, in-situ stresses were predicted and coupled with a failure criterion to yield safe mud weight windows for wells in the field. Predicted drilling events matched quite well with the observed drilling reports.</jats:p>

Back-calculation of soil parameters from displacement-controlled cavity expansion under geostatic stress by FEM and machine learning

“…Some of the studies that use field and lab data include the work of Sulewska [39], which discusses six different applications of NN to predict displacements (settlement, consolidation) and the limit load (bearing capacity) in different applications. Khatibi et al [13] estimated the shear wave velocity in incomplete data sets achieving good agreement between predicted and measured downhole pressures, which helped assessing wellbore stability. Zhang et al [49] used data from a tunneling project in Changsha city (China) to predict surface settlement.…”

An advanced computational intelligent framework to predict shear sonic velocity with application to mechanical rock classification

“…Compressional (V p ) and shear (V s ) sonic wave velocities, routinely obtained from seismic surveys and wireline logging, play a first-order role in reservoir evaluation under in-situ conditions. Sonic velocity measurements provide significant insights into formation pore pressure 1 , rock physical properties, including porosity, pore geometry, pore fluid, and mineralogical content 2 – 4 , as well as rock stiffness, strength, and brittleness of target strata 5 , with a wide range of applications from reservoir management and development 6 to a variety of geomechanical, geotechnical and geophysical studies 7 , 8 . Therefore, in-situ measurements of compressional and shear velocities, frequently using full-waveform recordings, for example, Schlumberger Dipole Sonic Imaging tool (DSI), should be incorporated into the standard practice for reservoir evaluation.…”

Hybrid and Automated Machine Learning Approaches for Oil Fields Development: the Case Study of Volve Field, North Sea

“…Nowadays, machine learning is widely known as an effective and useful instrument in geophysical modeling [5]. However, it is impossible to deny that many geophysical problems can be solved using interpretable physics-based models.…”