Hanlin Sheng

2023

1. 

   Seismic Foundation Model (SFM): a new generation deep learning model in geophysics

   Hanlin Sheng, Xinming Wu, Xu Si, and 3 more authors

   arXiv preprint arXiv:2309.02791, 2023

   Abs Bib PDF

   While computer science has seen remarkable advancements in foundation models, which remain underexplored in geoscience. Addressing this gap, we introduce a workflow to develop geophysical foundation models, including data preparation, model pre-training, and adaption to downstream tasks. From 192 globally collected 3-D seismic volumes, we create a carefully curated dataset of 2,286,422 2-D seismic images. Fully using these unlabeled images, we employ the self-supervised learning to pre-train a Transformer-based Seismic Foundation Model (SFM) for producing all-purpose seismic features that work across various tasks and surveys. Through experiments on seismic facies classification, geobody identification, interpolation, denoising, and inversion, our pre-trained model demonstrates versatility, generalization, scalability, and superior performance over baseline models. Conclusively, we provide a foundation model and vast dataset to advance AI in geophysics, addressing challenges (poor generalization, lacking labels, and repetitive training for task-specified models) of applying AI in geophysics and paving the way for future innovations in geoscience.

   @article{sheng2023seismic,
     title = {Seismic Foundation Model (SFM): a new generation deep learning model in geophysics},
     author = {Sheng, Hanlin and Wu, Xinming and Si, Xu and Li, Jintao and Zhang, Sibio and Duan, Xudong},
     journal = {arXiv preprint arXiv:2309.02791},
     year = {2023},
     dimensions = {true},
   }

2. 

   Deep learning for characterizing CO2 migration in time-lapse seismic images

   Hanlin Sheng, Xinming Wu, Xiaoming Sun, and 1 more author

   Fuel, 2023

   Abs Bib PDF

   We propose a deep-learning-based method to efficiently and accurately characterize CO_2 plumes in time-lapse seismic data. We first introduce a workflow to build 3-D realistic impedance models containing CO_2 plumes with various shapes, sizes, and locations. From the impedance models, we then simulate synthetic seismic datasets and automatically obtain the corresponding CO_2 label volumes. We extract real noise from field seismic datasets and add the noise to the synthetic ones to make them more realistic. We further construct a diverse and realistic training dataset with the combination of synthetic data containing CO_2 plumes and real data without CO_2 plumes that are randomly cropped from field seismic data before CO_2 injection. We finally utilize the training datasets without any human labeling to train a 3-D deep U-shape convolutional neural network for detecting CO_2 plumes in the Sleipner time-lapse seismic images. The results indicate that our prediction is consistent with the manual interpretation and could distinguish reflections of CO_2 plumes from the ones of pre-existing fluids, thin layers, and noise. To more accurately characterize the CO_2 plume migration, we use dynamic image warping to compute relative shifts that register the time-lapse seismic volumes before and after CO_2 injection and then apply the same shifts to the predicted CO_2 plumes. By doing this, we are able to reduce the inconsistencies that may be introduced by acquisition, processing, push-down effect (velocity decrease by injected CO_2), and pull-up effect (wavelet distortion), which is helpful to more accurately characterize the CO_2 plume migration.

   @article{sheng2023deep,
     title = {Deep learning for characterizing CO2 migration in time-lapse seismic images},
     author = {Sheng, Hanlin and Wu, Xinming and Sun, Xiaoming and Wu, Long},
     journal = {Fuel},
     volume = {336},
     pages = {126806},
     year = {2023},
     publisher = {Elsevier},
     dimensions = {true},
   }

2022

1. 

   Wavelet estimation and nonstretching NMO correction

   Hanlin Sheng, Xinming Wu, and Bo Zhang

   Geophysics, 2022

   Abs Bib PDF

   Normal moveout  (NMO) correction is an important step applied to common-midpoint (CMP) gathers for subsequent stacking. However, conventional NMO correction methods often suffer from the problem of NMO stretching, which non-linearly increases with offsets and decreases with zero-offset traveltime. The NMO stretching can be quantified by frequency distortion, so stretching is confined mainly to large offsets and shallow times. To solve this problem, we propose a wavelet-based method with the following four steps. First, we estimate a wavelet from the CMP gather by utilizing the NMO stretching appearing in the conventional NMO correction. Second, we deconvolve the original CMP gather based on the estimated wavelet. This step of removing the wavelet from the CMP gather is helpful for the next steps of NMO velocity scan and NMO correction. Third, we apply an improved NMO correction to the deconvolved CMP gather and obtain flattened reflectivities. We finally convolve the flattened and deconvolved gather with the estimated wavelet back to obtain an NMO-corrected gather without stretching artifacts. In our method, by using a deconvolved CMP gather, we are able to calculate a high-resolution semblance velocity spectrum that benefits from the NMO velocity picking. In addition, applying the NMO correction to the deconvolved CMP gather, instead of the original gather, is helpful to reduce the NMO stretching related to the wavelet distortion. Tests on synthetic and field data show that our new NMO correction method can estimate an accurate seismic wavelet and obtain an NMO-corrected gather without NMO stretching. Reducing the NMO stretching can significantly improve the resolution of shallow layers at far offsets and preserve the spectral bandwidth.

   @article{sheng2022wavelet,
     title = {Wavelet estimation and nonstretching NMO correction},
     author = {Sheng, Hanlin and Wu, Xinming and Zhang, Bo},
     journal = {Geophysics},
     volume = {87},
     number = {3},
     pages = {V193--V203},
     year = {2022},
     publisher = {Society of Exploration Geophysicists},
     dimensions = {true},
   }