... ABSTRACT A pre-drill prediction method of 3D geomechanical parameters based on seismic data is proposed. Firstly, the wave impedance parameters are predicted in the target area by the logging-constrained method, which mainly uses post-stack seismic data and logged data from drilled wells...

... ABSTRACT Accurate and real-time prediction of formation pore pressure is critical to ensure drilling safety. However, the performance of the most traditional formation pore pressure calculation methods are not satisfied in field applications due to their limited accuracy and time-effectiveness...

... both parallel and perpendicular to the bedding plane, are used to obtain the grain-scale, micromechanical statistics. Model predictions are compared with microseismic wave velocities measured in the field and good agreement is found. INTRODUCTION The growing momentum in the energy transition...

... is deemed necessary through prediction models. The study aims to develop reliable machine learning models for predicting S-wave velocity in shale formation using conveniently available wireline logs. Six robust machine learning techniques such as decision tree (DT), artificial neural networks (ANN), K...

... ABSTRACT Managing ground prone to rockburst is challenging, especially in seismically active underground mines. Over the past few decades, numerous studies have been conducted on predicting rockburst damage potential. However, in most cases, only fair model performance was achieved due...

... ABSTRACT Formation pore pressure plays a critical role in petroleum drilling and is an indispensable basic parameter for casing program design and mud weight optimization in petroleum drilling. Formation pore pressure can be predicted using seismic, logging and mud log data. However, due...

... analyses have poor timeliness and low accuracy so that it cannot meet the requirements of field application. This study provides a data-driven prediction method for stuck pipe probability. First, the dataset is established combining drilling records and logging data from 108 wells, and 15 input features...

... - proppant filling index (PFI). Data from shale gas fracturing wells are collected to train the algorithm for the prediction of PFIs. The variations in PFI curves are then used to reveal the dynamic matching between proppant injection and fracture propagation, based on which the development of underground...

... ABSTRACT Data-driven models are used extensively for predicting rate of penetration (ROP). However, what data-driven algorithm is best suited to ROP prediction is currently undecided. In this paper, the data-driven model based on back propagation neural network (BP-ANN) and random forest (RF...

... ABSTRACT In situ stress prediction is critical for applications associated with unconventional resource development including drilling, hydraulic fracturing, enhanced oil recovery and induced seismicity. A range of model-driven approaches have been developed to predict variation...

... evolution, especially for the low porosity range is not known in its entireness and the calibration of numerical models is not finished yet. The KOMPASS projects were initiated with the aim to reduce these knowledge gaps and improve predictions of crushed salt behavior. This paper gives an insight...

... fracturing materials geological subdiscipline fracture geometry diagnostic data machine learning rnn model proxy model prediction dataset ARMA 23-315 A Machine Learning based proxy model for the rapid prediction of hydraulic fractures Varun Gupta, Alexandros Solomou, Padmanabh Limaye, Gauthier...

... ABSTRACT The geomechanical response concerning porosity, permeability, and water saturation, will directly affect the prediction of oil production as well as the economic benefits of oil fields. In this paper, different models are established for the three stages of the SAGD (Steam Assisted...

... ABSTRACT Sand production prediction is essential from the early stages of field development planning for well completion design and later for production management. Unconsolidated and weakly consolidated sandstones are prone to fail at low flowing bottom hole pressures during hydrocarbon...

... progress and increasing the cost of the drilling operation. Conventional wellbore stability prediction relies on some deterministic physical models, involving some empirical coefficients which are difficult to determine and often dependent on field experience. In addition, some complex factors...

... ABSTRACT Knowledge of the in-situ state of stress is fundamental to all subsurface geomechanics/rock engineering endeavors and predicting layer-to-layer variation of horizontal principal stress magnitudes is imperative for a wide range of energy-related applications. In addition, the ability...

... ABSTRACT The uncertainty of rockmass conditions will be an important factor causing TBM construction risks and inefficient tunnelling. Currently, prediction of rockmass classification based on TBM operation data and machine learning models has been proved feasible by many researchers. However...

... ABSTRACT Ensemble learning is a recent development in machine learning. Random forest regression (RFR) is one such widely utilized ensemble learning algorithm. However, the current literature lacks studies that primarily focus on the effects of hyperparameter tuning in RFR when predicting...

... ABSTRACT Deep learning can better simulate highly nonlinear engineering problems through training adjustment, and has good practicability for predicting invisible data. BP Neural Network (BPNN) is a widely used deep learning algorithm, and strengthens the accuracy of developing training models...

... ABSTRACT The current research presents a machine learning application toward predicting the equivalent circulating density (ECD) in real-time while drilling operations. Maintaining high accuracy in estimating equivalent circulating density (ECD) is crucial due to the potential well control...