Master Thesis Online
Master thesis : Rock lithology recognition
Mazur, Thomas 
Promoteur(s) :
Geurts, Pierre
Date de soutenance : 5-sep-2022/6-sep-2022 • URL permanente : http://hdl.handle.net/2268.2/15902
Master_thesis_Report.pdfDétails
| Titre : | Master thesis : Rock lithology recognition |
| Auteur : | Mazur, Thomas
|
| Date de soutenance : | 5-sep-2022/6-sep-2022 |
| Promoteur(s) : | Geurts, Pierre
|
| Membre(s) du jury : | Van Droogenbroeck, Marc
Marée, Raphaël
Germay, Christophe |
| Langue : | Anglais |
| Discipline(s) : | Ingénierie, informatique & technologie > Sciences informatiques |
| Institution(s) : | Université de Liège, Liège, Belgique |
| Diplôme : | Master : ingénieur civil en science des données, à finalité spécialisée |
| Faculté : | Mémoires de la Faculté des Sciences appliquées |
Résumé
[en] In oil and gas, The most important properties that are studied are the porosity and the permeability. Those are necessary properties of the soil to make holding fossil fuel possible. The size of the particles that may contain the oil and gas is essential indicator of those two properties. The challenges for a century has been to develop methods to measure the particles as cheaply and accurately as possible. EPSLOG is a society that develops equipment for oil and gas and mining industries. As such, they also develop software to process the data. \\
In this work we will explore the optical granulometry method, which measures the grain size based on pictures of the surface of the rocks. More specifically, we will use computer vision technique and deep learning. For this, will compare different backbones in order to extract valuable information from the pictures.
Fichier(s)
Document(s)
Annexe(s)
Citer ce mémoire
L'Université de Liège ne garantit pas la qualité scientifique de ces travaux d'étudiants ni l'exactitude de l'ensemble des informations qu'ils contiennent.