Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine

Machine learning, as an increasingly prominent method in recent years, has introduced new methodologies and perspectives for extracting geological alteration information. To enhance the accuracy of remote-sensing-alteration mineral information, this study focuses on the extraction of alteration info...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuhan Yang, Shufang Tian
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/19/3646
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850284333586186240
author Shuhan Yang
Shufang Tian
author_facet Shuhan Yang
Shufang Tian
author_sort Shuhan Yang
collection DOAJ
description Machine learning, as an increasingly prominent method in recent years, has introduced new methodologies and perspectives for extracting geological alteration information. To enhance the accuracy of remote-sensing-alteration mineral information, this study focuses on the extraction of alteration information from hyperspectral remote sensing data using the Kernel-Based Extreme Learning Machine (KELM) optimized with the Sparrow Search Algorithm (SSA). The ideal parameters of the Kernel Extreme Learning Machine model were successfully acquired by utilizing the sparrow optimization method for continuous search and iteration, avoiding the blindness and arbitrariness associated with parameter selection by humans. Spectral Angle Mapper (SAM) technology was used to extract sample data from hyperspectral imagery, which were then used to train the machine learning model for alteration information extraction. The experimental results show that, when compared to the Random Forest and the Support Vector Machine algorithms, the Kernel-Based Extreme Learning Machine algorithm achieved the highest accuracy and the best effect in the extraction results. It closely matches the known mineral points and geochemical anomalies in the area, confirming that the method has a clear advantage in the extraction of hyperspectral alteration information.
format Article
id doaj-art-f4c49f5049c0483eb6f1a8e3d6b55c1c
institution OA Journals
issn 2072-4292
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-f4c49f5049c0483eb6f1a8e3d6b55c1c2025-08-20T01:47:36ZengMDPI AGRemote Sensing2072-42922024-09-011619364610.3390/rs16193646Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning MachineShuhan Yang0Shufang Tian1School of Earth Sciences and Resources, China University of Geosciences, Beijing 100083, ChinaSchool of Earth Sciences and Resources, China University of Geosciences, Beijing 100083, ChinaMachine learning, as an increasingly prominent method in recent years, has introduced new methodologies and perspectives for extracting geological alteration information. To enhance the accuracy of remote-sensing-alteration mineral information, this study focuses on the extraction of alteration information from hyperspectral remote sensing data using the Kernel-Based Extreme Learning Machine (KELM) optimized with the Sparrow Search Algorithm (SSA). The ideal parameters of the Kernel Extreme Learning Machine model were successfully acquired by utilizing the sparrow optimization method for continuous search and iteration, avoiding the blindness and arbitrariness associated with parameter selection by humans. Spectral Angle Mapper (SAM) technology was used to extract sample data from hyperspectral imagery, which were then used to train the machine learning model for alteration information extraction. The experimental results show that, when compared to the Random Forest and the Support Vector Machine algorithms, the Kernel-Based Extreme Learning Machine algorithm achieved the highest accuracy and the best effect in the extraction results. It closely matches the known mineral points and geochemical anomalies in the area, confirming that the method has a clear advantage in the extraction of hyperspectral alteration information.https://www.mdpi.com/2072-4292/16/19/3646spectral angle mapperkernel-based extreme learning machinealteration information extractionhyperspectral
spellingShingle Shuhan Yang
Shufang Tian
Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
Remote Sensing
spectral angle mapper
kernel-based extreme learning machine
alteration information extraction
hyperspectral
title Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
title_full Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
title_fullStr Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
title_full_unstemmed Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
title_short Extraction of Alteration Information from Hyperspectral Data Base on Kernel Extreme Learning Machine
title_sort extraction of alteration information from hyperspectral data base on kernel extreme learning machine
topic spectral angle mapper
kernel-based extreme learning machine
alteration information extraction
hyperspectral
url https://www.mdpi.com/2072-4292/16/19/3646
work_keys_str_mv AT shuhanyang extractionofalterationinformationfromhyperspectraldatabaseonkernelextremelearningmachine
AT shufangtian extractionofalterationinformationfromhyperspectraldatabaseonkernelextremelearningmachine