1-20 of 698
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 SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3914280
...), medium vehicles (SUVs and cars), and small vehicles (motorcycles and electric bicycles). We compare the performance of Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) for identifying vehicles of different sizes. The accuracy of all three neural...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3905696
... corresponding to the characteristic reflector. This eliminates the need for tedious manual picking and ultimately improves the automatic extraction accuracy. To efficiently determine and update the reflector positions, an efficient kinematic imaging method based on the Eikonal equation is developed. In each...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907037
... the desired characteristics and outperforms UNet with a 2× higher throughput for the presented DL-driven Seismic Inversion example. Additionally, our proposed architecture is 7× leaner in terms of the number of parameters. Despite its limited capacity, it can match the accuracy of UNet for the task at hand...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907527
... commonly used approach to augment the labels. However, it is crucial to ascertain the rationale behind such interpolation and determine the optimal interpolation method to enhance inversion accuracy. Through model testing, we confirm that Deep Learning (DL) networks have the ability to tolerate labels...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907951
... exploration geophysicist accuracy evaluation permeability intelligent evaluation international Intelligent Evaluation and Prediction of Reservoir Based on Machine Learning Method Wenjun Zhao1*, Tangyan Liu2 1 State Key Lab of Marine Geology, Tongji University, Shanghai 200092, China; 2 School...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3908382
... DDR. The models were optimized through variable selection and cross-validation before being compared to each other. For each ML algorithm the inclusion of the DDR data increased the accuracy of the prediction. The initial average of 72% for all models changed to a final average accuracy of 84...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3916060
..., different bands of seismic data affect each other, and the network tends to capture the features of the low and middle-frequency components while high-frequency components may have signal leakage. It can lead to inadequate accuracy for seismic data interpolation. To weaken the signal leakage and improve...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3916706
... To improve the accuracy of carbonate reservoir modeling, mainly well data such as core, thin section and well logging data had been adopted in conventional methods. Although the reservoir types classification is very detailed, but it is usually difficult to integrate with seismic data to make 3D...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3916936
...) based surrogate models for real-time high-resolution modeling of subsurface CO 2 storage. We demonstrate that significant computational acceleration can be achieved with FNO-based surrogate models without sacrificing the prediction accuracy of CO 2 -rich phase saturation (a.k.a. CO 2 saturation...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3917392
... As we all know, accuracy of depth prediction determines the quality of oilfield development effectiveness to a large extent, especially for thin sand within offshore reservoir, where development wells are mainly horizontal and extremely sensitive to depth. However, traditional methods predict...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3909144
... wavefield in viscoacoustic anisotropic media, as it can provide clear and stable wavefield. However, the previous pure-viscoacoustic anisotropic wave equations have low accuracy because the approximations are adopted in the derivation of the wave equation. In this paper, starting from the exact complex...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3909883
... method, the new method could eliminates the influence of the dip angle of the strata and has higher prediction accuracy. The fusion attribute of residual diffraction wave and improved ant tracking can reduce the interference of noise and the result is more accurate and effective in fracture prediction...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3910343
... Laplace operators, which impose difficulties in numerical solution. Recently, Fourier neural operators (FNO) have demonstrated notable efficacy in the resolution of partial differential equations (PDEs). To enhance the predictive accuracy further, we present a novel approach that leverages the U-net...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3910425
... learning (DL) methods for reconstructing missing traces in observed seismic data. While many DL-based reconstruction methods employ convolutional neural networks (CNNs) as their core components in supervised or unsupervised settings, the accuracy of CNN-based DL reconstruction methods can still be enhanced...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3912930
.... However, the scarcity of field work area well-log data poses challenges in providing low-frequency elastic parameters and suitable training samples, consequently impacting the accuracy and resolution of inverted elastic parameter. To tackle these challenges, we employ neural network technology and propose...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3910135
... Principles from gravity-subsidence surveys have been integrated in OBN operations to accurately measure relative node depths using a technology called DepthWatch. In our deep-water fields, the accuracy obtained is <5 cm, much better than that from OBN-reported depths or acoustic bathymetry...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 28–September 1, 2022
Paper Number: SEG-2022-3746075
... The landing process of horizontal wells requires high accuracy of depth prediction. In the region with severe lateral velocity variation, the accuracy of the traditional method of predicting depth by using the time-depth relationship of exploration wells cannot meet the demand at all...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 28–September 1, 2022
Paper Number: SEG-2022-3745795
... format detection with machine learning can be used to identify errors in floating-point number format conversions of a seismic dataset. A machine learning model was built using a deep artificial neural network to classify the floating-point numbers. The model has a training accuracy of 96 percent...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 28–September 1, 2022
Paper Number: SEG-2022-3746166
... ying xiongling exploration geophysicist reservoir characterization geometry applied geoscience imaging high-efficiency auxiliary operation hinterland qaidam basin mountain accuracy convergence accuracy energy 10 society High-density 3D acquisition technology and Its Application in dual...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 28–September 1, 2022
Paper Number: SEG-2022-3746172
... energy 10 fillippone formula algorithm application accuracy mudstone gypsum mudstone Application of formation pressure prediction technique based on high-density threedimensional seismic constraints in complex structural zones Yu Baoli, Liu Keyu, China University of Petroleum (East China); Li...

Product(s) added to cart

Close Modal