Salvato in:
Dettagli Bibliografici
Autori principali: Ang, Iye Szin, Findl, Martin Johannes, Hauzinger, Elisabeth, Sedlazeck, Klaus Philipp, Savolainen, Jyrki, Bakker, Ronald, Galler, Robert, Rueckert, Elmar
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.13937
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908596602667008
author Ang, Iye Szin
Findl, Martin Johannes
Hauzinger, Elisabeth
Sedlazeck, Klaus Philipp
Savolainen, Jyrki
Bakker, Ronald
Galler, Robert
Rueckert, Elmar
author_facet Ang, Iye Szin
Findl, Martin Johannes
Hauzinger, Elisabeth
Sedlazeck, Klaus Philipp
Savolainen, Jyrki
Bakker, Ronald
Galler, Robert
Rueckert, Elmar
contents Automated rock classification from mineral composition presents a significant challenge in geological applications, with critical implications for material recycling, resource management, and industrial processing. While existing methods using One dimensional Convolutional Neural Network (1D-CNN) excel at mineral identification through Raman spectroscopy, the crucial step of determining rock types from mineral assemblages remains unsolved, particularly because the same minerals can form different rock types depending on their proportions and formation conditions. This study presents a novel knowledge-enhanced deep learning approach that integrates geological domain expertise with spectral analysis. The performance of five machine learning methods were evaluated out of which the 1D-CNN and its uncertainty-aware variant demonstrated excellent mineral classification performance (98.37+-0.006% and 97.75+-0.010% respectively). The integrated system's evaluation on rock samples revealed variable performance across lithologies, with optimal results for limestone classification but reduced accuracy for rocks sharing similar mineral assemblages. These findings not only show critical challenges in automated geological classification systems but also provide a methodological framework for advancing material characterization and sorting technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rock Classification through Knowledge-Enhanced Deep Learning: A Hybrid Mineral-Based Approach
Ang, Iye Szin
Findl, Martin Johannes
Hauzinger, Elisabeth
Sedlazeck, Klaus Philipp
Savolainen, Jyrki
Bakker, Ronald
Galler, Robert
Rueckert, Elmar
Computational Engineering, Finance, and Science
Automated rock classification from mineral composition presents a significant challenge in geological applications, with critical implications for material recycling, resource management, and industrial processing. While existing methods using One dimensional Convolutional Neural Network (1D-CNN) excel at mineral identification through Raman spectroscopy, the crucial step of determining rock types from mineral assemblages remains unsolved, particularly because the same minerals can form different rock types depending on their proportions and formation conditions. This study presents a novel knowledge-enhanced deep learning approach that integrates geological domain expertise with spectral analysis. The performance of five machine learning methods were evaluated out of which the 1D-CNN and its uncertainty-aware variant demonstrated excellent mineral classification performance (98.37+-0.006% and 97.75+-0.010% respectively). The integrated system's evaluation on rock samples revealed variable performance across lithologies, with optimal results for limestone classification but reduced accuracy for rocks sharing similar mineral assemblages. These findings not only show critical challenges in automated geological classification systems but also provide a methodological framework for advancing material characterization and sorting technologies.
title Rock Classification through Knowledge-Enhanced Deep Learning: A Hybrid Mineral-Based Approach
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2510.13937