A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery

Hyperspectral lithological mapping is a critical task in geological surveys and mineral resource exploration. However, the distribution of geological units is typically imbalanced and heterogeneous, with practical tasks requiring high-efficiency mapping over large regions. Traditional methods, such...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuanchao Wang, Li He, Zhengwei He, Jiang Chen, Fang Luo
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225003966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387777648492544
author Yuanchao Wang
Li He
Zhengwei He
Jiang Chen
Fang Luo
author_facet Yuanchao Wang
Li He
Zhengwei He
Jiang Chen
Fang Luo
author_sort Yuanchao Wang
collection DOAJ
description Hyperspectral lithological mapping is a critical task in geological surveys and mineral resource exploration. However, the distribution of geological units is typically imbalanced and heterogeneous, with practical tasks requiring high-efficiency mapping over large regions. Traditional methods, such as patch-based and regular window approaches, struggle to effectively address these challenges. In this study, we propose a novel fast sample-based window lithological mapping (FSWLM) framework that integrates three key innovations: (1) a sample-based window strategy to reduce computational redundancy and improve efficiency, (2) an TFM (Threshold and Frequency Modulation)-based sampling strategy to address class imbalance during training, and (3) an encoder-decoder network characterized by feature-spectrum fusion (FSF) pattern. FSWLM offers an integrated solution tailored to the geological demands of lithological mapping, optimizing both efficiency and accuracy. Experimental validation on the Dajiling dataset, a geologically complex region in Tibet, demonstrates that FSWLM outperforms state-of-the-art methods in classification accuracy, minor class recognition, and spatial coherence. These results underscore the effectiveness of the task-oriented framework in addressing the unique challenges of hyperspectral lithological mapping, with promising implications for large-scale geological surveys and mineral resource exploration.
format Article
id doaj-art-2f0e5f3f6bc4434c87d9f914b0790a46
institution Kabale University
issn 1569-8432
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-2f0e5f3f6bc4434c87d9f914b0790a462025-08-20T03:44:24ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-09-0114310474910.1016/j.jag.2025.104749A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imageryYuanchao Wang0Li He1Zhengwei He2Jiang Chen3Fang Luo4State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, PR China; College of Geography and Planning, Chengdu University of Technology, Chengdu 610059 Sichuan, PR China; Research Center of Applied Geology of China Geological Survey, Chengdu 610036 Sichuan, PR ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, PR China; College of Geography and Planning, Chengdu University of Technology, Chengdu 610059 Sichuan, PR China; Corresponding author at: State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, No.1 Erxianqiao East Third Road, Chengdu 610059, PR China.State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, PR China; College of Geography and Planning, Chengdu University of Technology, Chengdu 610059 Sichuan, PR ChinaResearch Center of Applied Geology of China Geological Survey, Chengdu 610036 Sichuan, PR ChinaCollege of Geography and Planning, Chengdu University of Technology, Chengdu 610059 Sichuan, PR ChinaHyperspectral lithological mapping is a critical task in geological surveys and mineral resource exploration. However, the distribution of geological units is typically imbalanced and heterogeneous, with practical tasks requiring high-efficiency mapping over large regions. Traditional methods, such as patch-based and regular window approaches, struggle to effectively address these challenges. In this study, we propose a novel fast sample-based window lithological mapping (FSWLM) framework that integrates three key innovations: (1) a sample-based window strategy to reduce computational redundancy and improve efficiency, (2) an TFM (Threshold and Frequency Modulation)-based sampling strategy to address class imbalance during training, and (3) an encoder-decoder network characterized by feature-spectrum fusion (FSF) pattern. FSWLM offers an integrated solution tailored to the geological demands of lithological mapping, optimizing both efficiency and accuracy. Experimental validation on the Dajiling dataset, a geologically complex region in Tibet, demonstrates that FSWLM outperforms state-of-the-art methods in classification accuracy, minor class recognition, and spatial coherence. These results underscore the effectiveness of the task-oriented framework in addressing the unique challenges of hyperspectral lithological mapping, with promising implications for large-scale geological surveys and mineral resource exploration.http://www.sciencedirect.com/science/article/pii/S1569843225003966Lithological mappingSampled-based windowFrequency modulationEncoder-decoder networkHyperspectral image
spellingShingle Yuanchao Wang
Li He
Zhengwei He
Jiang Chen
Fang Luo
A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
International Journal of Applied Earth Observations and Geoinformation
Lithological mapping
Sampled-based window
Frequency modulation
Encoder-decoder network
Hyperspectral image
title A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
title_full A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
title_fullStr A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
title_full_unstemmed A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
title_short A task-oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
title_sort task oriented framework for efficient lithological mapping of imbalanced categories using hyperspectral imagery
topic Lithological mapping
Sampled-based window
Frequency modulation
Encoder-decoder network
Hyperspectral image
url http://www.sciencedirect.com/science/article/pii/S1569843225003966
work_keys_str_mv AT yuanchaowang ataskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT lihe ataskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT zhengweihe ataskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT jiangchen ataskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT fangluo ataskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT yuanchaowang taskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT lihe taskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT zhengweihe taskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT jiangchen taskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery
AT fangluo taskorientedframeworkforefficientlithologicalmappingofimbalancedcategoriesusinghyperspectralimagery