... properties and predicting stress profiles along the wellbores are key to improve production and stimulation design. We acquire over 3,000 feet of continuous cores from five wells in New Mexico, Delaware Basin. We combine a variety of high-resolution, whole core-based characterization techniques that include...

... ABSTRACT: Being able to predict the dimensions of excavation damage zones (EDZs) is crucial for the design of permeability-sensitive structures. This study focuses on predicting excavation-induced damage depth using a machine learning method called multi-layer perceptron (MLP). The inputs...

... ABSTRACT: Accurate prediction of dynamic pressures is essential for wellbore integrity analysis in deep water wells and wells with narrow operational windows. During the start-up of circulation, a higher circulating pressure is needed due to the gelation effect of drilling fluid. A coupled...

... ABSTRACT: Data-driven fracturing production prediction relies on geological engineering parameters to forecast production indicators. These parameters are traditionally derived from manual summarization and statistical analysis of well logging curves, potentially leading to inaccuracies due...

... subdiscipline mechanical earth model calibration statistical concept ray breakout classification prediction probability machine learning mem brier score accuracy scenario statistics wikipedia regime drilling probabilistic forecasting ARMA 24 439 Improve Mechanical Earth Model Calibration...

... ABSTRACT: The Thrust-Penetration Gradient (TPG) is an essential tool in analyzing and predicting the performance of Tunnel Boring Machines (TBMs). It evaluates TBM efficiency, reflecting geomechanical dynamics during tunneling. The TPG effectively captures the complex relationship between...

... ABSTRACT: A Graph Neural Network (GNN) approach is introduced for predicting the effective properties of rocks. The Mapper algorithm was employed to convert rock microstructures into graph datasets, effectively capturing the topological features of geomaterials. Two separate GNNs were trained...

... ABSTRACT: The growing need for better reservoir characterization methods in unconventional hydrocarbon extraction, geothermal energy production, and carbon sequestration has led to a demand for more accurate and reliable petrophysical data prediction techniques. However, data standardization...

... ABSTRACT: Predicting near-wellbore hydraulic fracture (HF) orientation is crucial for designing stimulation treatments. This work proposes a physics-based approach to determine the orientation of HF initiation considering formation breakdown pressure (FBP) and key geomechanical parameters...

..., the temporary plugging ball is subjected to stronger drag force in the horizontal direction, and the steering tendency is slightly slower than that of small displacement. Based on SVM and RF two machine learning models to predict the blocking results, analyze and predict different temporary plugging ball...

... ABSTRACT: This paper presents a comprehensive analysis of the correlation between static and dynamic mechanical properties of sedimentary rocks from Australian basins. By leveraging both empirical and machine learning techniques, we provide valuable insights into the predictive capabilities...

... necessitates consideration of lateral confinement in predicting penetration rate. Yet, most of the proposed methods for estimating penetration rate are of phenomenological nature, with only a few based on theoretical analysis for which it is not straightforward to extend to confinement conditions...

... ABSTRACT: We discuss a 3D case study for pressure and stress prediction in the Mad Dog field, deepwater GoM. We employ a novel approach that couples seismic velocities with geomechanical models and the full stress tensor (including lateral and deviatoric stresses; FES workflow). We show...

... ABSTRACT: Lost circulation events occur frequently during the drilling process. Due to their sudden and difficult to predict nature, they are often difficult to control in the field, resulting in low success rates and increased costs. Therefore, accurate formulation of lost circulation...

.... The prediction of formation pore pressure is a core factor of drilling design optimization and risk prevention. In order to improve the prediction accuracy on the basis of existing pre-drilling formation pore pressure prediction methods, the logging data and actual drilling data of the drilled wells were...

... ABSTRACT: Predicting the appropriate mud density in drilling operations is crucial in the construction of oil and gas wells, in order to mitigate the drilling problems and improve the drilling efficiency. This paper investigates ten failure criteria in directional wells drilled through...

... ABSTRACT: Accurate prediction of ROP is the premise and key to increase drilling speed. Artificial intelligence provides technical means for accurate ROP prediction. In this paper, the influence of borehole trajectory and drilling parameters on ROP is considered, and the prediction model...

... ABSTRACT: Surface ground deformations due to mining are dynamic in nature and depend, among others, on the rate of mining. There are many formulations that can calculate and predict ground deformation due to mining. The majority of these models can accurately predict final deformations, i.e...

... mining takes place (geology, stress conditions, mining procedures, etc.), any applicable model must be flexible, adaptable, and dynamic to provide a range of predictions with acceptable accuracy. This paper discusses the results and model validation of using multivariate regression analysis to analyze...

... ABSTRACT: Knowing accurate values of rock engineering parameters in hard rock condition is the key in estimating and adjusting TBM performance. Therefore, this paper has tried to predict the rock engineering factors using some indicators related to machine performance, mechanical specification...