Vitrinite maturity and programmed pyrolysis are conventional methods to evaluate organic matter (OM) regarding its thermal maturity. Moreover, vitrinite reflectance analysis can be difficult if prepared samples have no primary vitrinite or dispersed widely. Raman spectroscopy is a nondestructive method that has been used in the last decade for maturity evaluation of organic matter by detecting structural transformations, however, it might suffer from fluorescence background in low mature samples. In this study, four samples of different maturities from both shale formations of Bakken (the upper and lower members) Formation were collected and analyzed with Rock-Eval (RE) and Raman spectroscopy. In the next step, portions of the same samples were then used for the isolation of kerogen and analyzed by Raman spectroscopy. Results showed that Raman spectroscopy, by detecting structural information of OM, could reflect thermal maturity parameters that were derived from programmed pyrolysis. Moreover, isolating kerogen will reduce the background noise (fluorescence) in the samples dramatically and yield a better spectrum. The study showed that thermal properties of OM could be precisely reflected in Raman signals.

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.