Manipulating the loss calculation to enhance the training process of physics-informed neural networks to solve the 1D wave equation
H Nosrati, M Emami Niri - Engineering with Computers, 2024 - Springer
The application of physics-informed neural networks (PINNs) to address problems involving
partial differential equations (PDEs) is increasing. However, PINNs still need lots of …
partial differential equations (PDEs) is increasing. However, PINNs still need lots of …
Bayesian neural network and Bayesian physics-informed neural network via variational inference for seismic petrophysical inversion
Deep-learning methods are being successfully applied to seismic inversion and reservoir
characterization problems; however, the uncertainty quantification process has not been …
characterization problems; however, the uncertainty quantification process has not been …
Probabilistic physics-informed neural network for seismic petrophysical inversion
The main challenge in the inversion of seismic data to predict the petrophysical properties of
hydrocarbon-saturated rocks is that the physical relations that link the data to the model …
hydrocarbon-saturated rocks is that the physical relations that link the data to the model …
Enhancing seismic porosity estimation through 3D sequence-to-sequence deep learning with data augmentation, spatial constraints, and geologic constraints
Estimating porosity from seismic data is critical for studying underground rock properties,
assessing energy reserves, and subsequent reservoir exploration and development. For …
assessing energy reserves, and subsequent reservoir exploration and development. For …
Prestack Seismic Inversion Driven by Priori Information Neural Network and Statistical Characteristic
T Chen, B Zou, Y Wang, H Cai, X Li… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Seismic inversion accuracy significantly affects the quality of reservoir modeling. Given the
limited samples of well logging, prior information such as geological data and stratigraphic …
limited samples of well logging, prior information such as geological data and stratigraphic …
Deep carbonate reservoir characterization using multiseismic attributes: A comparison of unsupervised machine-learning approaches
Seismic reservoir characterization is of great interest for sweet spot identification, reservoir
quality assessment, and geologic model building. The sparsity of the labeled samples often …
quality assessment, and geologic model building. The sparsity of the labeled samples often …
Seismic impedance estimation from poststack seismic data using quantum computing
D Vashisth, R Lessard - … Meeting for Applied Geoscience & Energy, 2024 - library.seg.org
Quantum computing is increasingly recognized as a transformative technology in
geophysics, offering the potential to significantly enhance computational power and …
geophysics, offering the potential to significantly enhance computational power and …
Bayesian Physics-Informed Neural Networks for Seismic Petrophysical Inversion
P Li - 2024 - search.proquest.com
The main challenge for seismic petrophysical inversion is that the physical relations that link
the data to the model properties are often non-linear and the solutions of the inverse …
the data to the model properties are often non-linear and the solutions of the inverse …
Inversion of DC Resistivity Data using Physics-Informed Neural Networks
DC resistivity surveys are widely employed for near-surface characterization. By inverting
the apparent resistivity data obtained in these surveys, the true subsurface resistivity model …
the apparent resistivity data obtained in these surveys, the true subsurface resistivity model …