A dataset of 2307 points from two wells (Well-1 and Well-2) was used to build the different ML models. The logging data includes gamma-ray (GR) log, formation bulk density (RHOB) log, compressional (DTC), and shear (DTS) wave transit-time log. This study aims to apply different machine learning (ML) techniques, specifically, random forest (RF), functional network (FN), and adaptive neuro-fuzzy inference system (ANFIS), to predict the σ h and σ H using well-log data. However, these methods are complex, expensive, or need unavailable tectonic stress data. The σ h and σ H can be estimated either from borehole injection tests or theoretical finite elements methods. The σ h and σ H are difficult to determine, whereas the overburden stress can be determined directly from the density logs. In-situ stresses consist of overburden stress (σ v), minimum (σ h), and maximum (σ H) horizontal stresses. Determination of in-situ stresses is essential for subsurface planning and modeling, such as horizontal well planning and hydraulic fracture design.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |