Advanced mineralogical classification and concentration estimation in mining with MATLAB-powered hyper-spectral imaging and machine learning

被引：1

作者：

Okada, Natsuo ^{[1
]}

Sinaice, Brian Bino ^{[2
]}

Kim, Jaewon ^{[3
]}

Nozaki, Hiromasa ^{[1
]}

Takizawa, Kaito ^{[1
]}

Owada, Narihiro ^{[4
]}

Ohtomo, Yoko ^{[1
]}

Kawamura, Youhei ^{[1
]}

机构：

[1] Hokkaido Univ, Grad Sch Engn, Div Sustainable Resources Engn, Sapporo, Hokkaido 0600813, Japan

[2] Akita Univ, Ctr Reg Revitalizat Res & Educ, Akita, Japan

[3] MMC RYOTEC, Sales Div, Rock Tools Grp, Tokyo, Japan

[4] Akita Univ, Grad Sch Int Resource Sci, Dept Earth Resource Engn & Environm Sci, Akita, Japan

来源：

INTERNATIONAL JOURNAL OF MINING RECLAMATION AND ENVIRONMENT | 2024年 / 38卷 / 10期

基金：

日本学术振兴会;

关键词：

Hyperspectral imaging; MATLAB; spectroscopy; mineral processing;

D O I：

10.1080/17480930.2024.2360743

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

The study presents a new technique that combines hyperspectral imaging and machine learning to identify minerals. Overcoming the challenges of processing hyperspectral data, the solution offers a user-friendly hyperspectral analysis tool tailored for constructing datasets and enhancing mineral identification and concentration estimation. The tool integrates hyperspectral data processing with segmentation, simplifying complex operations and making mineral identification accessible to non-experts. The tool's capabilities extend to handling multi-spectral data efficiently, potentially leading to energy-efficient analysis when combined with dimensionality reduction techniques. Presented as a novel approach, it improves geological surveys in mining areas, enabling industrial applications and mineral research.

引用

页码：851 / 871

页数：21