1-20 of 255
Keywords: accuracy
Close
Follow your search
Access your saved searches in your account

Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206129-MS
... well category presented non-integral well confusion matrix exhibition integrity well integrity well integrity anomaly ml model accuracy prediction feature description evaluation metric Introduction When oil and gas assets mature, well-integrity assurance becomes more necessary...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206178-MS
... temperature simulators are in use to predict, with better accuracy, cementing bottomhole temperatures. The manuscript investigates the strange differences in predictions between the simulators for a range of high temperature applications. The results of the work efforts should help end users understand...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-205903-MS
... predict the production performance of multi-fractured horizontal CBM wells in a fast manner. Compared with Simple Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), the proposed GRU-MLP had the highest accuracy and stability especially for gas production in late...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206281-MS
... application transmitter flow rate mpfm component mpfm reservoir surveillance accuracy real-time sensor operation petroleum engineer health monitoring strategy algorithm industrial revolution 4 software yateem introduction Measuring the flow rate is critical in determining the quantity...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206276-MS
... model selection, Random Forest (RF) shows the best accuracy with the given dataset, and Differential Evolution (DE) was used for optimization. Using recursive feature elimination (RFE), the final master dataset was reduced to 50 parameters to feed into the machine learning model. After hyperparameter...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206298-MS
... are not K-orthogonal. To improve the simulation accuracy, we developed a novel method where the faults are modeled by polyhedral cells, and mimetic finite difference (MFD) methods are used to solve flow equations. We use a cut-cell approach to build the mesh for faulted reservoirs. A regular orthogonal grid...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-205988-MS
... be classified into two classes (high scaling or low scaling) with good accuracy. Though existing physical and chemical methods can be used to analyze scale deposition, the methods are often applied after considerable production decrease has already occurred. By using deep learning algorithms, our study came up...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206021-MS
..., while providing a new level of risk avoidance and safety factor. well planning pressure data pressure transducer drilling fluid management & disposal upstream oil & gas absolute pressure array sensor petroleum engineer drilling fluids and materials accuracy wdp network fluid...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206047-MS
... in low GLR, decreasing the accuracy in gas wells. In order to predict the pressure gradient in horizontal gas wells, an experimental investigation of gas-water flow has been conducted. The experimental test matrix was designed to cover all the flow patterns. The experiment was conducted in a 5-m long...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, September 21–23, 2021
Paper Number: SPE-206364-MS
... relative error of the curve parameter inversion is less than 10%. In addition, the accuracy of parameter prediction can be improved by increasing the weight of some important parameters in deep learning model training, such as permeability and fracture half-length. Finally, the automatic interpretation...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201295-MS
... the pipeline ( Amin, 2015 ; Hansen et al., 2019 ). These tools are very cheap, but the lack of specific measurements of the mixture properties limits their measurement accuracy. Another approach is by using a Multiphase Flow Meter (MPFM): an in-line meter able to estimate the three individual flows...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201282-MS
... architecture model 600 model 2200 artificial intelligence upstream oil & gas pixel training dataset machine learning neural network segmentation model 17600 sem image accuracy ec value connectivity permeability ground truth image segmentation ground truth segmentation dataset...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201763-MS
... acceleration). In order to reproduce the response from the well as precise as possible, it is crucial that these inputs are sent into the model with high accuracy. Hence, all real input parameters that affect the drilling process must be known with the accuracy needed for the ADC system to calculate...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-204267-STU
... that this neural-network approximation provides great compression of the traveltime tables (10 2 −10 5 times) with reasonable accuracy of predicting traveltimes on a fine imaging grid. Overall, the use of artificial neural networks results in a speed-up of the Kirchhoff migration operator in two applications...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-204272-STU
... model. The accuracy of the predicted results matched with the computed values from watershed segmentation. The average error between CNN predictions and the ground truth (watershed segmentation) for porosity and Average pore radius was 0.4% and 1%, which is negligible. This study aimed to test how...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201433-MS
..., and operation shear rate. The developed model covers HVFRs dosage ranging from 0.25 to 2.0 gpt (gallons per thousand gallons). This model can be used to assist in obtaining proppant settling velocity as a function of shear rate. The developed model shows the high accuracy of prediction HVFR viscosity profile...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201430-MS
... in the reservoir simulator to predict the stress field from numerically solved pressure field at time step level. Hence the geomechanical simulation is replaced by the DNN proxy. Our results show that the accuracy of the U-Net network is above 97%, in the metric of mean square error. Moreover, the U-Net network...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201379-MS
.... optimization problem artificial intelligence machine learning upstream oil & gas simulation accuracy well control optimization optimization ml algorithm neural network ml technique iteration simulation run iterative discrete latin hypercube equation coefficient optimization algorithm...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201453-MS
... of this procedure as it can learn sequential data which a traditional neural network (ANN) cannot. The accuracy of the c-RNN was superior when compared to that of the ANN, simple baselines and empirical correlations. This procedure is a cost effective and fast alternative to running DTS logs and with further...
Proceedings Papers

Paper presented at the SPE Annual Technical Conference and Exhibition, October 26–29, 2020
Paper Number: SPE-201512-MS
... will be generated to display the amplitude of road noise with respect to total signal amplitude. The answer product helps to identify whether an elevated signal level is due to road noise or other guided-wave noises. The accuracy of beamformed 2D flow map will also be improved, especially when the frequency...

Product(s) added to cart

Close Modal