AUTHOR=Tawfik Miral S. , Adishesha Amogh Subbakrishna , Hsi Yuhan , Purswani Prakash , Johns Russell T. , Shokouhi Parisa , Huang Xiaolei , Karpyn Zuleima T. 

TITLE=Comparative Study of Traditional and Deep-Learning Denoising Approaches for Image-Based Petrophysical Characterization of Porous Media

JOURNAL=Frontiers in Water

VOLUME=Volume 3 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/water/articles/10.3389/frwa.2021.800369

DOI=10.3389/frwa.2021.800369

ISSN=2624-9375

ABSTRACT=Digital rock physics has seen significant advances owing to improvements in micro-computed tomography (MCT) imaging techniques and computing power. These advances allow for characterization of multiphase transport in porous media. Despite such advancements, image processing and particularly denoising remains less explored. As such, selection of proper denoising method is a challenging optimization exercise of balancing the tradeoffs between minimizing noise and preserving original features. Despite its importance, there are no comparative studies in the geoscience domain that assess the performance of different denoising approaches, and their effect on image-based rock and fluid property estimates. Further, the application of machine learning and deep learning-based (DL) denoising models remains under-explored. In this research, we evaluate the performance of six denoising filters and compare them to five supervised and unsupervised  DL-based denoising models. We also propose semi-supervised DL denoising models which only require a fraction of clean reference images. Using these models, we investigate the optimal number of high-exposure reference images that balances data acquisition cost and accurate petrophysical characterization. The performance of each denoising approach is evaluated using two sets of metrics: (1) standard denoising evaluation metrics, such as peak signal-to-noise ratio (PSNR), and (2) image-based petrophysical properties such as porosity, saturation, phase connectivity, and specific surface area. Petrophysical estimates show that most traditional filters perform well when estimating bulk properties but show large errors for pore-scale properties like phase connectivity. Meanwhile, N2C, a supervised DL model shows the best performance, and N2V, an unsupervised model, shows the worst performance. N2N75, which is a newly proposed semi-supervised model where 75% of the clean reference data is used for training, shows promising outcomes. Lastly, N2C is found to be the most, while CCGAN is found to be the least computationally efficient among the DL-based models considered. Overall, this investigation shows that application of sophisticated supervised and semi-supervised DL-based denoising models can significantly reduce petrophysical characterization errors introduced during the denoising step. Furthermore, with the advancement of semi-supervised DL-based models, requirement of clean reference or ground truth images for training can be reduced and deployment of fast X-ray scanning can be made possible.