Automatic description of rock thin sections: A web application
The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2025-06-01
|
| Series: | Artificial Intelligence in Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666544125000140 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839651226338197504 |
|---|---|
| author | Stalyn Paucar Christian Mejia-Escobar Victor Collaguazo |
| author_facet | Stalyn Paucar Christian Mejia-Escobar Victor Collaguazo |
| author_sort | Stalyn Paucar |
| collection | DOAJ |
| description | The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into verbal responses using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use. |
| format | Article |
| id | doaj-art-8d0ab92f7c4f48a3b93c67d50ec116a0 |
| institution | Matheson Library |
| issn | 2666-5441 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Geosciences |
| spelling | doaj-art-8d0ab92f7c4f48a3b93c67d50ec116a02025-06-26T09:53:36ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412025-06-0161100118Automatic description of rock thin sections: A web applicationStalyn Paucar0Christian Mejia-Escobar1Victor Collaguazo2Faculty of Geology, Mining, Petroleum, and Environmental Engineering (FIGEMPA), Central University of Ecuador, Quito, EcuadorCorresponding author.; Faculty of Geology, Mining, Petroleum, and Environmental Engineering (FIGEMPA), Central University of Ecuador, Quito, EcuadorFaculty of Geology, Mining, Petroleum, and Environmental Engineering (FIGEMPA), Central University of Ecuador, Quito, EcuadorThe identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into verbal responses using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use.http://www.sciencedirect.com/science/article/pii/S2666544125000140RocksThin sectionsArtificial intelligenceDeep learningTransformer |
| spellingShingle | Stalyn Paucar Christian Mejia-Escobar Victor Collaguazo Automatic description of rock thin sections: A web application Artificial Intelligence in Geosciences Rocks Thin sections Artificial intelligence Deep learning Transformer |
| title | Automatic description of rock thin sections: A web application |
| title_full | Automatic description of rock thin sections: A web application |
| title_fullStr | Automatic description of rock thin sections: A web application |
| title_full_unstemmed | Automatic description of rock thin sections: A web application |
| title_short | Automatic description of rock thin sections: A web application |
| title_sort | automatic description of rock thin sections a web application |
| topic | Rocks Thin sections Artificial intelligence Deep learning Transformer |
| url | http://www.sciencedirect.com/science/article/pii/S2666544125000140 |
| work_keys_str_mv | AT stalynpaucar automaticdescriptionofrockthinsectionsawebapplication AT christianmejiaescobar automaticdescriptionofrockthinsectionsawebapplication AT victorcollaguazo automaticdescriptionofrockthinsectionsawebapplication |