OpenFWI 2.0: Benchmark Datasets for Elastic Full-waveform Inversion

Shihang Feng, Hanchen Wang, Chengyuan Deng, Yinan Feng, Min Zhu, Peng Jin, Yinpeng Chen, Youzuo Lin

International Meeting for Applied Geoscience and Energy (IMAGE)

... into the inversion significantly expands the model space and introduces increased degrees of freedom, resulting in even more pronounced nonlinearity (Operto et...

Automatic detection of DAS-recorded microseismic fracture reflections

Youfang Liu, Ivan Lim, Chen Ning, Kurt Nihei

International Meeting for Applied Geoscience and Energy (IMAGE)

...). In addition to direct arrivals, reflections from hydraulic fractures can also be imaged from the time domain to the space domain and help...

Abstract: Neural Networks Facilitate Precise at - Bit Formation Detection Suitable for Deployment in Automated Drilling Systems; #91204 (2023)

Lucas Katzmann, Stefan Wessling, Matthew Forshaw, Joern Koeneke

Search and Discovery.com

... with rapid transitions between low and high unconfined compressive (UCS) stress formations create both invisible-lost-time and non-productive-time. Both...

Machine-learning Facilitates Prediction of Geomechanical Properties Directly From SEM Images in Unconventional Plays

Heehwan Yang, Deepak Devegowda, Mark Curtis, Chandra Rai

Unconventional Resources Technology Conference (URTEC)

...., 1995. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10), p.1995. Li, X., Liu, Z...

Seismic imaging uncertainty using deep learning predicted Greens functions

Han Liu, Anar Yusifov, Muhong Zhou, Linda Hodgson

International Meeting for Applied Geoscience and Energy (IMAGE)

... ( 𝑃 𝑥𝑥 + 𝑃 𝑧𝑧 ) + 𝑆( 𝑥, 𝑧, 𝑡), where 𝑃 𝑡𝑡 is the second order time derivative of pressure field, 𝑣 is velocity model...

Estimating CO2 saturation maps from seismic data using deep convolutional neural networks

Zi Xian Leong, Tieyuan Zhu, Alexander Y. Sun

International Meeting for Applied Geoscience and Energy (IMAGE)

... the connection between seismic shot gathers and CO2 leakage mass. Li et al. (2021) used a fully convolutional neural network to predict time-lapse velocity...

Data selection for velocity model estimation using a circular shot OBN survey

Felipe T. Costa, Sergio L. E. F. da Silva, Ammir A. Karsou, Felipe Capuzzo, Roger M. Moreira, Jorge Lopez, Marco Cetale

International Meeting for Applied Geoscience and Energy (IMAGE)

... the spatial and the time coordinates, p is the pressure field, vp is the acoustic velocity model, and s represent the shot index. We apply...

Deep Learning for Quantitative Hydraulic Fracture Profiling from Fiber Optic Measurements

Weichang Li, Han Lu, Yuchen Jin, Frode Hveding

Unconventional Resources Technology Conference (URTEC)

... to the synced pump data independently; and II) a convolutional LSTM (long short-term memory) sequence learning model maps time segments...

Multiscenario-based deep learning workflow for high-resolution seismic inversion on Brazil presalt 4D

Yang Xue, Dan Clarke, Kanglin Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

... model and 1D convolutional modeling. The training datasets are generated from scenario-based modeling with each group trained separately with a DL...

Increasing The Resolution of Seismic Imaging With Spectral Blueing, Spectral Decomposition RGB And HSV Blending to Delineate The Fluvial Facies on Fluvio Deltaic Environment

Aji Darma Maulana, Nine Safira, Ongki Ari Prayoga, Egie Wijaksono, Alit Ascaria

Indonesian Petroleum Association

... or more dominance than the red and green spectrum. The Spectral Blueing algorithm is performed in the time domain. Therefore, before performing Spectral...

Seismic Data Compression by Variational Autoencoder With Hyperprior

Shirui Wang, Wenyi Hu, Aria Abubakar, Xuqing Wu, Jiefu Chen

International Meeting for Applied Geoscience and Energy (IMAGE)

..., end-to-end approach. Our experimental analyses demonstrate the efficacy of the introduced compression model on both pre-migration and post-migration...

Abstract: Fault Detection Based on 3D Seismic Images using an Integration of GCN and U-Net; #91215 (2026)

G. Lu, J. Drummond Alves, J. Su, J. Zhao

Search and Discovery.com

... probabilities. However, due to the convolutional kernels' limited receptive field, the features extracted only represent the faults' local appearance...

Time-lapse attenuation variations during CO2 injection using DAS VSP data from the CaMI Field Research Station, Alberta, Canada

Yichuan Wang, Donald C. Lawton

International Meeting for Applied Geoscience and Energy (IMAGE)

... convolutional model for seismic reflection signal is A(t, f ) = S ( f ) R (t, f ) F (t, f ) G (t ) , (1) where A(t, f) is the time-frequency variant...

Magnetotelluric inversion using supervised learning trained with random smooth geoelectric models

Lian Liu, Bo Yang, Yixian Xu, Dikun Yang

International Meeting for Applied Geoscience and Energy (IMAGE)

... frequencies and observation stations, noise, and the model equivalence regarding its resolution (Backus & Gilbert 1967; Parker 1983). Geophysicists...

A two-stage deep learning workflow for automated seismic inversion

Haibin Di, Wenyi Hu, Aria Abubakar

International Meeting for Applied Geoscience and Energy (IMAGE)

... of four major steps, (i) large-scale structural model construction, (ii) initial property model estimation via a multi-task convolutional neural...

Survey merging using CycleGAN and patchy seismic images

Chaoshun Hu, Fan Jiang, Konstantin Osypov, Julianna Toms

International Meeting for Applied Geoscience and Energy (IMAGE)

... Resnet convolutional neural network. Discriminator is using the VGG16 pretrained model. Loss function is based on the SRGAN perceptional content loss...

Abstract: Fast and Accurate Impedance Inversion by Well-Log Calibration; #90171 (2013)

Igor B. Morozov and Jinfeng Ma

Search and Discovery.com

...) the convolutional equation; 2) time-depth constraints from the seismic data, 3) background low-frequency model from the logs or seismic/geological interpretation...

Implementation of Seismic Data Quality Characterisation Using Supervised Deep Learning

Joshua Thorp, Krista Davies, Julien Bluteau, Peter Hoiles

Australian Petroleum Production & Exploration Association (APPEA) Journal

... the analysis. Traditionally, the quality of seismic data has been characterised through the domain expertise of geoscientists and through traditional analytical...

High-resolution prestack seismic inversion of reservoir parameters using an arch network

Ting Chen, Yaojun Wang, Yuan Yuan, Gang Yu, Guangmin Hu

International Meeting for Applied Geoscience and Energy (IMAGE)

...) construct a convolutional neural network (CNN) that is trained to perform mapping of relevant seismic data cubes to respective velocity logs. Meanwhile...

Abstract: Object Detection in SEM Images Using Convolutional Neural Networks: Application on Pyrite Framboid Size-Distribution in Fine-Grained Sediments;

Artur Davletshin, Lucy Tingwei Ko, Kitty Milliken, Priyanka Periwal, Wen Song

Search and Discovery.com

... and time-consuming tasks with machines. Results from manually traced and automation were compared. Deep learning techniques such as convolutional...

ABSTRACT: Selected Topics in Seismic Dispersion

Christopher L. Liner

Houston Geological Society Bulletin

..., reflection and transmission coefficients, head waves, etc. The convolutional reflection models we use to model thick and thin bed thin response...

Abstract: Modeling of Seismic Signatures of Carbonate Rock Types, by B. Jan and Y. Sun, #90188 (2014)

Search and Discovery.com

Abstract: Fault Detection in 2D Seismic Data with Convolutional Neural Networks and Transformers; #91215 (2026)

G. T. Custodio, T. Y. Aoyagi, H. Saar, A. Heleno, C. T. Gamba, C. L. da Silva, C. M. da Silva, D. B. Virissimo, E. M. Sales, F. S. Silles, L. G. Netto, N. F. Guerra, O. C. Gandolfo, R. A. Rubo

Search and Discovery.com

... (convolutional neural network) and the recent Seismic Foundation Model (SFM) based on Transformers. We compare their performance on four training setups...

Machine-Learning Driven Prediction of Geological Marker Signatures

Shashin Sharan, Kaustubh Shrivastava, Per Irgens, Tatjana Scherschel

Unconventional Resources Technology Conference (URTEC)

... formations. The scope includes the integration of feature engineering, time series analysis, and ML to process available well and mud log data...

A robust approach for shear log predictions using deep learning on big data sets from a carbonate reservoir for integrated reservoir characterization projects

Aun Al Ghaithi

International Meeting for Applied Geoscience and Energy (IMAGE)

... reservoir. The trained model was then used to predict shear logs in wells drilled previously without acquired shear log data. Deep learning provided added...