| Titre | Applications of end-to-end deep learning models in processing digital rock data |
| |
| Auteur | Bizhani, M ;
Ardakani, O H; Little, E |
| Source | Geoconvention 2021, abstracts; 2021 p. 1-2  Accès
ouvert |
| Liens | Online - En ligne
|
| Année | 2021 |
| Séries alt. | Ressources naturelles Canada, Contribution externe 20210160 |
| Éditeur | GeoConvention Partnership |
| Réunion | GeoConvention 2021; Septembre 13-15, 2021 |
| Document | site Web |
| Lang. | anglais |
| Media | en ligne; numérique |
| Formats | pdf |
| Sujets | modèles; ressources pétrolières; exploration pétrolière; hydrocarbures; roches reservoirs; porosité; microscopie électronique à balayage; Méthodologie; Traitement des données; Intelligence artificielle;
combustibles fossiles; sédimentologie; Sciences et technologie; Nature et environnement |
| Illustrations | organigrammes; photomicrographies |
| Programme | Les géosciences pour les nouvelles sources d'énergie La coordination du programme |
| Diffusé | 2021 09 01 |
| Résumé | (Sommaire disponible en anglais seulement)
Augmented Intelligence (AI) and Deep Learning (DL) techniques and the production of digital rock data have become powerful tools for studying and
characterizing reservoir rocks properties - such as pore structure - at unprecedented resolutions. The rise of powerful imaging methods (e.g. micro-CT scanner) has enabled acquiring a substantial amount of image data of different rock properties
under varying conditions. The caveats of digital rock data analysis techniques are the resolution and processing of these types of data. Image enhancement and segmentation are often time-consuming and subjective to the methods used. Deep learning as
an emerging new means of image processing offers a great potential for automating image analysis tasks that can significantly speed up characterization. The research presented here demonstrates the use of deep-learning models for seamless processing
of scanning electron microscopy (SEM) or micro-CT images of rock samples. Image denoising, resolution enhancement, semantic segmentation, and prediction of several properties such as porosity are shown to be successfully performed by these models.
The automation of these tasks greatly reduces the time spent on each step. Additionally, as more data become available better models can be trained to push the boundaries of data characterization past physical limitations of currently available
imaging devices.
We show through the use of several connected convolutional neural networks (CNN) that images acquired using SEM or micro-CT data can be directly characterized right out of the instrument using trained CNNs. In our work, a network
first denoises the image, a second network takes the output of the denoiser and enhances the resolution by a factor of 4. The third network segments the super-resolved images. A final network is also attached to quickly obtain information about the
pore size and porosity of the samples. The use of these models greatly reduces processing time. Additionally, it offers flexibility in terms of obtaining large lower resolution images and boosting their resolution through deep-learning models.
The
novelty of this work is in the use of several state-of-the-art CNN models simultaneously to pre-process and produce quick results using raw microscopic rock images. We believe the industry, as well as the researcher, can benefit substantially by
adopting these new tools in their analysis that can save time and enhance the workflow. |
| Sommaire | (Résumé en langage clair et simple, non publié)
L'imagerie microscopique est une méthode puissante pour étudier des échantillons de roche. Cependant, les images acquises à l'aide de techniques
à haute résolution ont nécessité plusieurs étapes de pré-et post-traitement pour l'analyse quantitative. Le développement de modèles robustes d'apprentissage en profondeur ainsi que l'accès à la puissance de calcul ont transformé de nombreuses
industries dans leur quête d'efficacité et de rapidité. Le même principe est appliqué dans ce travail pour automatiser le traitement des images microscopiques d'échantillons de roches à des fins de caractérisation rapide et précise. Les avantages de
l'adoption de techniques de pointe d'intelligence augmentée (IA) et d'apprentissage en profondeur (DL) pour de telles tâches sont la rapidité, la précision et la cohérence des résultats. En outre, il est possible d'améliorer davantage les images
au-delà des limites physiques des appareils d'imagerie grâce à des méthodes d'apprentissage en profondeur. |
| GEOSCAN ID | 328589 |
|
|