Comparison of model initialization methods in machine learning for thin-section rock image classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68145535%3A_____%2F25%3A00640285" target="_blank" >RIV/68145535:_____/25:00640285 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s10596-025-10385-3" target="_blank" >https://doi.org/10.1007/s10596-025-10385-3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10596-025-10385-3" target="_blank" >10.1007/s10596-025-10385-3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of model initialization methods in machine learning for thin-section rock image classification

Popis výsledku v původním jazyce

Microscopic rock image analysis aids geotechnical and geological studies, often with computational methods. The growing availability of image data has led to the widespread adoption of automation in image analysis. However, the lack of large, publicly available datasets has hindered the development of dedicated machine learning models for geological applications. This study explores the use of transfer learning techniques to overcome this limitation by leveraging pre-trained machine learning models for rock type classification based on thin-section images. The research compares models trained from scratch with those utilizing pre-trained architectures to assess whether models trained on non-geological data can effectively support rock classification. The experiments were conducted using a dataset comprising 11901 microscopic images representing 40 rock types. The study evaluates different model initialization methods to assess their performance in geological applications. The results indicate that transfer learning enhances classification accuracy compared to models trained from scratch, demonstrating the potential in geoscientific research. This work provides insights into the practical application of machine learning in rock classification and serves as a reference and survey for specialists in geotechnics and geology seeking to integrate artificial intelligence into their research.

Název v anglickém jazyce

Comparison of model initialization methods in machine learning for thin-section rock image classification

Popis výsledku anglicky

Microscopic rock image analysis aids geotechnical and geological studies, often with computational methods. The growing availability of image data has led to the widespread adoption of automation in image analysis. However, the lack of large, publicly available datasets has hindered the development of dedicated machine learning models for geological applications. This study explores the use of transfer learning techniques to overcome this limitation by leveraging pre-trained machine learning models for rock type classification based on thin-section images. The research compares models trained from scratch with those utilizing pre-trained architectures to assess whether models trained on non-geological data can effectively support rock classification. The experiments were conducted using a dataset comprising 11901 microscopic images representing 40 rock types. The study evaluates different model initialization methods to assess their performance in geological applications. The results indicate that transfer learning enhances classification accuracy compared to models trained from scratch, demonstrating the potential in geoscientific research. This work provides insights into the practical application of machine learning in rock classification and serves as a reference and survey for specialists in geotechnics and geology seeking to integrate artificial intelligence into their research.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computational Geosciences

ISSN

1420-0597

e-ISSN

1573-1499

Svazek periodika

29

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

24

Strana od-do

44

Kód UT WoS článku

001590919100001

EID výsledku v databázi Scopus

2-s2.0-105018694366