A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach

The increasing demand for precise and dependable models has led to the development of both sensors and statistical algorithms. However, numerous studies have demonstrated that model performance is highly dependent on a range of environmental factors, such as spatio-temporal fluctuations of moisture,...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaron Ogen, Michael Denk, Cornelia Glaesser, Holger Eichstaedt
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2022.2104173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850140067350183936
author Yaron Ogen
Michael Denk
Cornelia Glaesser
Holger Eichstaedt
author_facet Yaron Ogen
Michael Denk
Cornelia Glaesser
Holger Eichstaedt
author_sort Yaron Ogen
collection DOAJ
description The increasing demand for precise and dependable models has led to the development of both sensors and statistical algorithms. However, numerous studies have demonstrated that model performance is highly dependent on a range of environmental factors, such as spatio-temporal fluctuations of moisture, sensor type, sample variability, preprocessing methods, and model selection. These factors can impact prediction results, leading to erroneous comparisons across lab, field, or imaging models. Samples for this study were collected from a tailing settling basin of a porphyry copper deposit near Erdenet, Mongolia. The database contains lab and field spectra and hyperspectral imagery from a HySpex imaging sensor. In this study we propose a workflow that includes a simulation that yields an appropriate regression threshold while addressing data-driven uncertainty. The workflow consists of two regression models and five classification models at different scales for quantitative geochemical, mineralogical, and textural prediction of tailing samples. Each model is compared to the acquisition space's performance potential. Acceptable R2 values for regression models are 0.58 for laboratory, 0.40 for field, and 0.31 for hyperspectral airborne data. Results of this study are not limited to tailing samples but can be applied on other fields of research such as geology, pedology or agriculture.
format Article
id doaj-art-614105cc201f40318dc9127f89f18c82
institution OA Journals
issn 2279-7254
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-614105cc201f40318dc9127f89f18c822025-08-20T02:29:59ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542022-12-0155145347010.1080/22797254.2022.2104173A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approachYaron Ogen0Michael Denk1Cornelia Glaesser2Holger Eichstaedt3Institute of Geosciences and Geography, Martin-Luther-University Halle-Wittenberg, Halle (Saale), GermanyInstitute of Geosciences and Geography, Martin-Luther-University Halle-Wittenberg, Halle (Saale), GermanyInstitute of Geosciences and Geography, Martin-Luther-University Halle-Wittenberg, Halle (Saale), GermanyDimap-Spectral GmbH, Freiberg, GermanyThe increasing demand for precise and dependable models has led to the development of both sensors and statistical algorithms. However, numerous studies have demonstrated that model performance is highly dependent on a range of environmental factors, such as spatio-temporal fluctuations of moisture, sensor type, sample variability, preprocessing methods, and model selection. These factors can impact prediction results, leading to erroneous comparisons across lab, field, or imaging models. Samples for this study were collected from a tailing settling basin of a porphyry copper deposit near Erdenet, Mongolia. The database contains lab and field spectra and hyperspectral imagery from a HySpex imaging sensor. In this study we propose a workflow that includes a simulation that yields an appropriate regression threshold while addressing data-driven uncertainty. The workflow consists of two regression models and five classification models at different scales for quantitative geochemical, mineralogical, and textural prediction of tailing samples. Each model is compared to the acquisition space's performance potential. Acceptable R2 values for regression models are 0.58 for laboratory, 0.40 for field, and 0.31 for hyperspectral airborne data. Results of this study are not limited to tailing samples but can be applied on other fields of research such as geology, pedology or agriculture.https://www.tandfonline.com/doi/10.1080/22797254.2022.2104173tailingregressionclassificationhyperspectral remote sensinggeochemistryspectroscopy
spellingShingle Yaron Ogen
Michael Denk
Cornelia Glaesser
Holger Eichstaedt
A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
European Journal of Remote Sensing
tailing
regression
classification
hyperspectral remote sensing
geochemistry
spectroscopy
title A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
title_full A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
title_fullStr A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
title_full_unstemmed A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
title_short A novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification-based approach
title_sort novel method for predicting the geochemical composition of tailings with laboratory field and hyperspectral airborne data using a regression and classification based approach
topic tailing
regression
classification
hyperspectral remote sensing
geochemistry
spectroscopy
url https://www.tandfonline.com/doi/10.1080/22797254.2022.2104173
work_keys_str_mv AT yaronogen anovelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT michaeldenk anovelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT corneliaglaesser anovelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT holgereichstaedt anovelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT yaronogen novelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT michaeldenk novelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT corneliaglaesser novelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach
AT holgereichstaedt novelmethodforpredictingthegeochemicalcompositionoftailingswithlaboratoryfieldandhyperspectralairbornedatausingaregressionandclassificationbasedapproach