... Abstract This study demonstrates that machine learning models trained on manually performed petrophysical analyses (n = 1542) can generate predictions with accuracy that is sufficient to make business decisions. We evaluated multiple machine learning algorithms to establish a benchmark...

... approaches, such as Chevron's ALICE machine learning workflow for recovery forecasts. We demonstrate FRITZ with a Permian Basin example that this stress shadow proxy is amongst the top predictors of well productivity when included in subsurface machine learning. Introduction In 2020, fossil fuels...

... characterization and facilitates the completion parameter optimization thereby improving reservoir development in unconventional oil reservoirs. energy economics artificial intelligence drillstem testing unconventional resource economics data mining shale gas machine learning upstream oil & gas...

... is used for testing, and (b) Cross well prediction, a group of wells from the same region is divided into training and testing. The logs used in this work were collected from seven Permian Basin wells gamma-ray, bulk density, resistivity, etc. Finally, we employed four various machine learning (ML...

... not be so straightforward and additional information about the pumping system may be needed to estimate the BHP. The goal of this work is to build a Machine Learning data-driven model that can predict the BHP for multi-fractured horizontal wells of the Vaca Muerta Formation in Argentina. Input variables...

... (Reichstein et al., 2019; Willard et al., 2020) have widely discussed applications of data- driven methods (i.e., machine learning and deep learning) to the problem of earth system science. In recent years, increased eld development and data collection activities have motivated the adoption of data-driven...

... Abstract Recently, machine and deep learning algorithms have been proposed as alternatives to statistical methods for production time series forecasting of unconventional reservoirs. Although most efforts provide timeseries forecasts using machine learning (ML) algorithms for unconventional...

... and unique optimized landing point, having a set of pertinent low-cost data before fracking to estimate the geological variations along the laterals and evaluating systematically the well production performance via a PLT proxy opens the possibility of initiating a machine learning process to guide completion...

... uses Hough Transform along with other optical attributes associated with sand-like particles within a machine learning framework to detect proppant. Finally, select samples were further tested using high resolution scanning electron microscopes with compositional analysis to validate the imaging...

... Abstract Objectives/Scope This study will demonstrate an automated machine learning approach for fault detection in a 3D seismic volume. The result combines Deep Learning Convolution Neural Networks (CNN) with a conventional data pre-processing step and an image processing-based post...

... maturity measurements as predictive tools for modeling produced fluid phase in this formation. geochemical characterization machine learning drilling operation complex reservoir area 2 upstream oil & gas geochemistry urtec artificial intelligence structural geology marl 1 1 reservoir...

... Abstract Outlier detection is a critical component of every Log Quality Control workflow and a Machine Learning implementation that is unsupervised and automated must robustly address several challenges. The outlier analysis methodology developed should not only correctly identify truly...

... understanding of the hydrodynamics involved in proppant transport in wellbores and enables us to make quick and informed decisions during the stage design process. completion installation and operations fracturing fluid fracturing materials proppant machine learning hydraulic fracturing upstream...

... Abstract A machine learning approach is considered to develop a Seq2Seq LSTM-based learning framework for oil production forecasting in the Eagle Ford shale employing encoder-decoder architecture to generate future declining production rates. The study's novelty is a methodology...

... the potential to improve shale reservoir characterization and time-lapse monitoring of shale hydrocarbon production. reservoir characterization shale gas machine learning artificial intelligence upstream oil & gas anisotropy parameter well logging structural geology variation stiffness...

... due to human bias. For unconventional resource plays with tens of thousands of wells, constructing geological models and algorithms can be a daunting task. Machine learning is an emerging technology that has been increasingly adopted in the energy industry. It can provide automated and accurate well...

... and their ranges are defined. Then, initial sample size of M is generated using the Latin Hypercube (LH) sampling method. Next, these uncertainties along with other model inputs are simulated using the ZFRAC, and the simulated pumping pressure responses are obtained. The machine learning proxy model called XGBoost...

... optimization. machine learning hydraulic fracturing artificial intelligence modeling & simulation shale gas complex reservoir new workflow modeling result workflow optimization algorithm reservoir simulation variance-covariance matrix high precision mgd posterior histogram history...

... and stimulation testing, and reservoir development. This paper develops a workflow for modeling the spatial distribution of natural fractures in a shale reservoir, using machine learning and geostatistical methods. This study focuses on the Hydraulic Fracturing Test Site 1 (HFTS1), located in the Midland Basin...

... to the probability of chance. To address these challenges, this paper offers a low-cost and scalable machine learning workflow, capable of predicting SWD interference with public and affordable private data. In this study, a logistic regression model was trained with cross-validation on 136 historic Ovintiv wells...