... is required to estimate methane flux from the measurements made by the drone. We trained a convolutional neural network (CNN) using Large Eddy Simulations (LES) dataset of methane plumes that mimic the real dataset of the next-generation Airborne Visible/Infrared Imaging Spectrometer (AVIRIS-NG) where wind...

... information geological subdiscipline neural network reservoir geomechanics young united states government artificial intelligence machine learning geology textural intensity 0 machine learning facilitate prediction grayscale intensity segmentation elastic moduli pixel texture dataset complex...

... upstream oil & gas neural network artificial intelligence architecture geological subdiscipline geology mineral machine learning classification mancos shale information detection utilizing deep learning approach conference dataset calcite accuracy university characteristic mineral...

... prediction seg unconventional resource technology conference uncertainty quantification upstream oil & gas neural network urtec data mining algorithm interpretation estimator URTeC: 3865670 Data Driven Oil Production Prediction and Uncertainty Quantification for Unconventional Asset...

...-in) by integrating the BP neural network with the AttBiLSTM network model. Moreover, the "phase" events (i.e., the pump ball, temporary plugging fracturing, sand plugging, and pre-frac acid treatment) are automatically identified by improved U-net++ network model. Then, a real-time prediction model for flowing...

.... upstream oil & gas asia government sedimentary rock geology neural network clastic rock deep learning mudrock artificial intelligence production control geologist united states government complex reservoir shale gas production monitoring rock type reservoir surveillance mudstone...

... of formation and fluid data. Besides, frequent manual operations are always ignored in the production history because of their cumbersome processing. To overcome this limitation, a supervised deep neural network (DNN) model is established in this paper to forecast hydrocarbon production that considers...

... Abstract Application of a Convolutional neural network (CNN) is presented for an unconventional reservoir to simultaneously predict elastic, mineral volumes, geomechanical and reservoir properties from seismic and well data. In the Barnett Shale, success requires identifying brittle...

... value when used to assist the interpretation process of fiber-optics field data, which in turn is complex and holds a full potential not explored yet. geology complex reservoir upstream oil & gas neural network geologist fracture united states government hydraulic fracturing...

.... The developed data were used to train different Artificial Neural Network (ANN) algorithms. ANN algorithms showed high capabilities to develop a surrogate model of the high-fidelity model. The ANN models provided robust predictions on the monthly production level for oil recovery factors. The robustness...

... tree-based algorithms (random forest and gradient boosting), feed-forward neural networks, and recurrent neural networks (simple RNN, LSTM, and GRU), were implemented and trained using historic data of a number of lateral wells that liquid loaded. The best performing model was selected to predict...

... to maximum the EUR (i.e., cumulative production within a certain period) or the NPV from a fractured well. upstream oil & gas geologist clastic rock sedimentary rock geology drilling operation optimization problem fracture mudstone neural network optimum ufd dimensionless pi ufd...

... for prediction accuracy. After several rounds of model refinement we then selected a deep-learning neural network architecture as the model that offered the best combination of predictive accuracy, prediction speed, training efficiency, and model portability. The accuracy of the selected machine learning model...

... learning and deep neural network to estimate and predict the geomechanical properties of the Permian Basin. The log-derived prediction algorithm includes (a) Single-Well prediction, 75% of log data of a single well is used as a specimen for training the Bi-LSTM, and the rest 25% of data of the same well...

... extrapolation ability and require sufficient training data, where training an under-determined neural network predictive model with limited data can result in overfitting and poor prediction performance. Unlike statistical models, physics-based models impose causal relations that can provide reliable...

... Multilayer Perceptrons (MLP), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Convolutional Neural Network (CNN), Long-term Recurrent Convolutional Network (LRCN), and Gated Recurrent Unit (GRU) with two statistical methods (Exponential Smoothing, and Seasonal Autoregressive Integrated Moving...

... 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...

... that integrates innovative and revolutionary machine learning techniques, which embed recurrent neural networks and Seq2Seq architectures commonly used for language processing in translation tasks for estimating in this paper future oil rates. The method uses a type of recurrent neural network known as LSTM...

.... Additionally, this study serves as a guide to help improve the DL applications in production forecasting. production forecasting artificial intelligence modeling & simulation neural network upstream oil & gas rnn application algorithm long term dependency deep learning proceedings...

... to develop a predictive machine learning model (comprising a multiple linear regression model and a simple neural network). This model has been successfully implemented in field developments to optimize child well placement and has produced improvements in performance predictions and net present value (NPV...