Estimation of Shear Wave Velocity for Shallow Depth Using Artificial Neural Network Technique: A Case Study in Rumaila oil field

In Rumaila oilfield, the lost circulation problem is a challenging issue. The geological and geomechanical properties of subsurface formations have role in causing loss. One natural features related to mud loss against these an unconformity surface. Inferring surface needs be understood how mechanical rocks are distributed across entire reservoir. result identifying areas for solving most problems. Using well logs, model can constructed identify unconformity. Shear wave velocity crucial factor determining properties. They not frequently recorded during logging time cost-saving purposes. save cost. To overcome this challenge, ANNs was developed estimate missing Vs data Hasa Aruma groups oil field interested wells from south north domes (extending top Dammam bottom Hartha). performance new tested through calibration. outcomes showed that measured depth (MD), bulk density (RHOB), compressional (Vp) key parameters creating ANN utilizing. This study has proven basic systematic equations accurately anticipate shear (Vs) conventional logs. correlation coefficient (R2) root mean square error were 0.956) and0.118, respectively.The optimum number hidden neurons 3 neurons). presented closely resemble when dataset other used check accuracy predictive model. presents effective, simple, cost-effective technique, which absence rock tests DTs.