返回
Joint physics-based and data-driven time-lapse seismic inversion: Mitigating data scarcity
DOI:10.1190/GEO2022-0050.1.png)
摘要
En 中文
In carbon capture and sequestration, developing rapid and effective imaging techniques is crucial for real-time monitoring of the spatial and temporal dynamics of CO2 propagation during and after injection. With continuing improvements in computational power and data storage, data-driven techniques based on machine learning (ML) have been effectively applied to seismic inverse problems. In particular, ML helps alleviate the ill-posedness and high computational cost of full-waveform inversion massive high-quality training data sets to ensure prediction accuracy, which hinders their application to time-lapse monitoring of CO2 sequestration. We develop an efficient hybrid time-lapse workflow that combines physics-based FWI and data -driven ML inversion. The scarcity of the available training data is addressed by developing a new data-generation technique with physics constraints. The method is validated using a synthetic CO2-sequestration model based on the Kimberlina storage reservoir in California. Our approach is shown to synthesize a large volume of high-quality, physically realistic training data, which is critically important in accurately characterizing the CO2 movement in the reservoir. The developed hybrid method-ology can also simultaneously predict the variations in velocity and saturation and achieve high spatial resolution in the presence of realistic noise in the data.
Keyword:
WAVE-FORM INVERSION
CO2 INJECTION
期刊
IF:
3.2
论文数:
8.4K
被引数:
3.3W
机构
引用论文
Physics-Consistent Data-Driven Waveform Inversion With Adaptive Data Augmentation具有自适应数据增强的物理一致数据驱动波形反演
Elastic full-waveform inversion application using multicomponent measurements of seismic data collection
GEOPHYSICS
IF3.2
Measurement of emission current and temperature profile of emissive probe materials using CO2 LASER使用CO2激光器测量发射探针材料的发射电流和温度分布

