Nam Pham

Nam Pham

Auto-generated profile, based on publicly available information

Nam Pham

The University of Texas at Austin 1 , Austin, Texas, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2019 in Geophysics
Verified
Journal Article
Closed access
XWXinming Wu
Xinming Wu
ZGZhicheng Geng
Zhicheng Geng
YSYunzhi Shi
Yunzhi Shi
NPNam Pham
Nam Pham
SFSergey Fomel
Sergey Fomel
GCGuillaume Caumon
Guillaume Caumon
Seismic structural interpretation involves highlighting and extracting faults and horizons that are apparent as geometric features in a seismic image. Although seismic image processing methods have been proposed to automate fault and horizon interpretation, each of which today still requires significant human effort. We improve automatic structural interpretation in seismic images by using convolutional neural networks (CNNs) that recently have shown excellent performances in detecting and extracting useful image features and objects. The main limitation of applying CNNs in seismic interpretation is the preparation of many training data sets and especially the corresponding geologic labels. Manually labeling geologic features in a seismic image is highly time-consuming and subjective, which often results in incompletely or inaccurately labeled training images. To solve this problem, we have developed a workflow to automatically build diverse structure models with realistic folding and faulting features. In this workflow, with some assumptions about typical folding and faulting patterns, we simulate structural features in a 3D model by using a set of parameters. By randomly choosing the parameters from some predefined ranges, we are able to automatically generate numerous structure models with realistic and diverse structural features. Based on these structure models with known structural information, we further automatically create numerous synthetic seismic images and the corresponding ground truth of structural labels to train CNNs for structural interpretation in field seismic images. Accurate results of structural interpretation in multiple field seismic images indicate that our workflow simulates realistic and generalized structure models from which the CNNs effectively learn to recognize real structures in field images.

1 August 2019 in Interpretation
Verified
Journal Article
Closed access
NPNam Pham
Nam Pham
SFSergey Fomel
Sergey Fomel
Dallas B DunlapDallas B Dunlap
Dallas B Dunlap
We have developed a method based on an encoder-decoder convolutional neural network for automatic channel detection in 3D seismic volumes. We use two architectures borrowed from computer vision: SegNet for image segmentation together with Bayesian SegNet for uncertainty measurement. We train the network on 3D synthetic volumes and then apply it to field data. We test the proposed approach on a 3D field data set from the Browse Basin, offshore Australia, and a 3D Parihaka seismic data in New Zealand. Applying the weights estimated from training on 3D synthetic volumes to a 3D field data set accurately identifies channel geobodies without the need for any human interpretation on seismic attributes. Our proposed method also produces uncertainty volumes to quantify the trustworthiness of the detection model.

17 March 2020 in Geophysics
Verified
Journal Article
Closed access
NPNam Pham
Nam Pham
XWXinming Wu
Xinming Wu
ENEhsan Zabihi Naeini
Ehsan Zabihi Naeini
Reservoir characterization involves integration of different types of data to understand the subsurface rock properties. To incorporate multiple well log types into reservoir studies, estimating missing logs is an essential step. We have developed a method to estimate missing well logs by using a bidirectional convolutional long short-term memory (bidirectional ConvLSTM) cascaded with fully connected neural networks. We train the model on 177 wells from mature areas of the UK continental shelf (UKCS). We test the trained model on one blind well from UKCS, three wells from the Volve field in the Norwegian continental shelf, one well from the Penobscot field in the Scotian shelf offshore Canada, and one well from the Teapot Dome data set in Wyoming. The method takes into account the depth trend and the local shape of logs by using ConvLSTM architecture. The method is examined on sonic log prediction and can produce an accurate prediction of sonic logs from gamma-ray, density, and neutron porosity logs. The advantages of our method are that it is not applied on an interval by interval basis like rock-physics-based methods and it also outputs the uncertainties facilitated by dropout layers and Monte Carlo sampling at inference time.

31 March 2020 in Geophysics
Verified
Journal Article
Open access
HKHarpreet Kaur
Harpreet Kaur
NPNam Pham
Nam Pham
SFSergey Fomel
Sergey Fomel
We have estimated migrated images with meaningful amplitudes matching least-squares migrated images by approximating the inverse Hessian using generative adversarial networks (GANs) in a conditional setting. We use the CycleGAN framework and extend it to the conditional CycleGAN such that the mapping from the migrated image to the true reflectivity is subjected to a velocity attribute condition. This algorithm is applied after migration and is computationally efficient. It produces results comparable to iterative inversion but at a significantly reduced cost. In numerical experiments with synthetic and field data sets, the adopted method improves image resolution, attenuates noise, reduces migration artifacts, and enhances reflection amplitudes. We train the network with three different data sets and test on three other data sets, which are not a part of training. Tests on validation data sets verify the effectiveness of the approach. In addition, the field-data example also highlights the effect of the bandwidth of the training data and the quality of the velocity model on the quality of the deep neural network output.

4 October 2021 in Geophysics
Verified
Journal Article
Open access
NPNam Pham
Nam Pham
WLWeichang Li
Weichang Li
We have developed a method to combine unsupervised and supervised deep-learning approaches for seismic ground roll attenuation. The method consists of three components that have physical meaning and motivation. The first component is a convolutional neural network (CNN) to separate a seismic record into ground roll and signal, while minimizing the residual between the sum of the generated signal and ground roll from two subnetworks and the input seismic record. The second component creates a maximum separation of signal and ground roll in the f-k domain, by training a supervised classifier. The third component is a CNN mapping signal to ground roll, which overcomes the problem of finding appropriate masks in traditional methods. Each component in our method is closely related to and motivated by the wave characteristics of the ground roll. Test results on field seismic records demonstrate the effectiveness of combining these components in preventing signal leakage and removing ground roll from seismic data.

21 October 2022 in Interpretation
Verified
Journal Article
Open access
HKHarpreet Kaur
Harpreet Kaur
NPNam Pham
Nam Pham
SFSergey Fomel
Sergey Fomel
ZGZhicheng Geng
Zhicheng Geng
LDLuke Decker
Luke Decker
SGShuang Gao
Shuang Gao
We have proposed a deep neural network-based framework for seismic facies classification. We implement two different neural networks based on the architectures of DeepLabv3+ and generative adversarial network for segmentation and compare the mapping results from seismic reflection data to lithologic facies. DeepLabv3+ predictions have sharper boundaries between the predicted facies whereas generative adversarial network output has a better continuity of predicted facies. We incorporate uncertainty analysis into the workflow using a Bayesian framework. The proposed approach consisting of joint analysis of predicted facies from multiple networks along with uncertainty in prediction accelerates the interpretation process by reducing the need for human intervention and also lessens individual biases that an interpreter may bring. We determine the effectiveness of the proposed algorithm by testing on field data examples, and we find that the proposed workflow classifies facies accurately. This may potentially enable the development of depositional environment maps in areas of low well density.