Porosity prediction from prestack seismic data via deep learning: incorporating a low-frequency porosity model
Porosity prediction from seismic data is of considerable importance in reservoir quality
assessment, geological model building, and flow unit delineation. Deep learning …
assessment, geological model building, and flow unit delineation. Deep learning …
[PDF][PDF] 基于数据与模型联合驱动的波阻抗反演方法
桑文镜， 袁三一， 丁智强， 于越， 刘浩杰， 韩智颖 - 地球物理学报, 2024 - dsjyj.com.cn
摘要井插值初始模型为基于模型的反演提供的低频信息往往不够准确, 导致该模型驱动方法容易
出现较大的波阻抗预测误差且建模效率较低. 为缓解这些问题, 本文利用数据驱动的深度学习反 …
出现较大的波阻抗预测误差且建模效率较低. 为缓解这些问题, 本文利用数据驱动的深度学习反 …
InverMulT-STP: Closed-loop Transformer Seismic AVA Inversion with Synthetic Data Style Transfer Pretraining
Prestack seismic data amplitude variation with angle (AVA) inversion is critical in identifying
oil and gas reservoirs. Recently, deep learning (DL) has gained significant popularity in AVA …
oil and gas reservoirs. Recently, deep learning (DL) has gained significant popularity in AVA …
Inversion with stratigraphy-guided deep learning
Property estimation in seismic exploration traditionally relies on seismic inversion, which is
an ill-posed problem. However, recent advances in deep learning (DL), specifically …
an ill-posed problem. However, recent advances in deep learning (DL), specifically …
Deghosting in Depth Image Domain Using a PSF-trained U-net
In the marine seismic acquisition, hydrophones are distributed along streamers that are
towed under the sea surface, recording both the upgoing primary reflections and the …
towed under the sea surface, recording both the upgoing primary reflections and the …
Data-model jointly driven acoustic impedance inversion
WJ SANG, SY YUAN, ZQ DING, Y Yu, HJ LIU… - Chinese Journal of …, 2024 - en.dzkx.org
The low-frequency components provided by the well-interpolated prior model for the model-
based inversion is usually inaccurate, which usually results in large errors of predicted …
based inversion is usually inaccurate, which usually results in large errors of predicted …
Physics-driven cycle network for seismic impedance inversion using conditional generative adversarial networks
Despite the extensive application of artificial neural networks in seismic inversion, their
effectiveness is often hampered by the limited availability of labeled data. To address this …
effectiveness is often hampered by the limited availability of labeled data. To address this …
Seismic absolute acoustic impedance inversion using domain adversarial based transfer learning
Absolute acoustic impedance (AI) inversion is crucial to recover the elastic attributes such as
porosity, saturation, to name a few. However, to obtain absolute AI, incorporation of low …
porosity, saturation, to name a few. However, to obtain absolute AI, incorporation of low …