Rock thin sections identification based on improved squeeze-and-Excitation Networks model

Rock thin section recognition provides geological information, which is crucial in petroleum geology, exploration, and mining research as a kind of fundamental work. Although many machine learning methods solve this research, there are still problems of data hierarchy and model pertinence. We use th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & geosciences Ročník 152; s. 104780
Hlavní autoři: Ma, He, Han, Guoqing, Peng, Long, Zhu, Liying, Shu, Jin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.07.2021
Témata:
Algorithm improvement
data collection
Deep learning
geology
Hierarchical classification
Image classification
petroleum
Rock thin sections
SENet
Deep learning
SENet
Hierarchical classification
Algorithm improvement
Rock thin sections
Image classification
ISSN:0098-3004, 1873-7803
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Rock thin section recognition provides geological information, which is crucial in petroleum geology, exploration, and mining research as a kind of fundamental work. Although many machine learning methods solve this research, there are still problems of data hierarchy and model pertinence. We use the hierarchical classification method to divide the dataset into sedimentary, metamorphic, and igneous rock as first-level, and to subdivide a total of 105 s-level further from the three categories. We propose the MaSE-ResNeXt model based on the fundamental work in the SeNet that can enhance the feature connection between different channels. The MaSE-ResNeXt adopted hierarchical filter groups, bottleneck stacking, and other strategies to enhance the representational capability of the model which advances the solving ability in rock recognition. Six data enhancement methods and other techniques are used to improve the robustness and effectiveness. The accuracy in the test set was 90.89% and 81.97% for the first and second level, respectively, with the inference duration is only 0.0357s. This study also designs a degeneration experiment and model comparison to demonstrate the model's effectiveness. Future research can employ this model as the fundamental base of transfer learning in geology to save time in the training of study. [Display omitted] •Image recognition of rock slices.•Multitype and multilevel classification.•Improved Squeeze-and-Excitation Networks.•Fundamentals of transfer learning in the field of geology.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0098-3004
1873-7803
DOI:10.1016/j.cageo.2021.104780