Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach
Abstract Geochemical variations of sedimentary records contain vital information for understanding paleoenvironment and paleoclimate. However, to obtain quantitative data in the laboratory is laborious, which ultimately restricts the temporal and spatial resolution. Quantification based on fast-acqu...
Published in: | Scientific Reports |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Nature Portfolio
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-022-25377-x https://doaj.org/article/c4fca907bb214a9f8b3871869be70ce9 |
id |
ftdoajarticles:oai:doaj.org/article:c4fca907bb214a9f8b3871869be70ce9 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:c4fca907bb214a9f8b3871869be70ce9 2023-05-15T18:25:36+02:00 Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach An-Sheng Lee Weng-Si Chao Sofia Ya Hsuan Liou Ralf Tiedemann Bernd Zolitschka Lester Lembke-Jene 2022-12-01T00:00:00Z https://doi.org/10.1038/s41598-022-25377-x https://doaj.org/article/c4fca907bb214a9f8b3871869be70ce9 EN eng Nature Portfolio https://doi.org/10.1038/s41598-022-25377-x https://doaj.org/toc/2045-2322 doi:10.1038/s41598-022-25377-x 2045-2322 https://doaj.org/article/c4fca907bb214a9f8b3871869be70ce9 Scientific Reports, Vol 12, Iss 1, Pp 1-11 (2022) Medicine R Science Q article 2022 ftdoajarticles https://doi.org/10.1038/s41598-022-25377-x 2022-12-30T20:13:55Z Abstract Geochemical variations of sedimentary records contain vital information for understanding paleoenvironment and paleoclimate. However, to obtain quantitative data in the laboratory is laborious, which ultimately restricts the temporal and spatial resolution. Quantification based on fast-acquisition and high-resolution provides a potential solution but is restricted to qualitative X-ray fluorescence (XRF) core scanning data. Here, we apply machine learning (ML) to advance the quantification progress and target calcium carbonate (CaCO3) and total organic carbon (TOC) for quantification to test the potential of such an XRF-ML approach. Raw XRF spectra are used as input data instead of software-based extraction of elemental intensities to avoid bias and increase information. Our dataset comprises Pacific and Southern Ocean marine sediment cores from high- to mid-latitudes to extend the applicability of quantification models from a site-specific to a multi-regional scale. ML-built models are carefully evaluated with a training set, a test set and a case study. The acquired ML-models provide better results with R2 of 0.96 for CaCO3 and 0.78 for TOC than conventional methods. In our case study, the ML-performance for TOC is comparably lower but still provides potential for future optimization. Altogether, this study allows to conveniently generate high-resolution bulk chemistry records without losing accuracy. Article in Journal/Newspaper Southern Ocean Directory of Open Access Journals: DOAJ Articles Southern Ocean Pacific Scientific Reports 12 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q An-Sheng Lee Weng-Si Chao Sofia Ya Hsuan Liou Ralf Tiedemann Bernd Zolitschka Lester Lembke-Jene Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
topic_facet |
Medicine R Science Q |
description |
Abstract Geochemical variations of sedimentary records contain vital information for understanding paleoenvironment and paleoclimate. However, to obtain quantitative data in the laboratory is laborious, which ultimately restricts the temporal and spatial resolution. Quantification based on fast-acquisition and high-resolution provides a potential solution but is restricted to qualitative X-ray fluorescence (XRF) core scanning data. Here, we apply machine learning (ML) to advance the quantification progress and target calcium carbonate (CaCO3) and total organic carbon (TOC) for quantification to test the potential of such an XRF-ML approach. Raw XRF spectra are used as input data instead of software-based extraction of elemental intensities to avoid bias and increase information. Our dataset comprises Pacific and Southern Ocean marine sediment cores from high- to mid-latitudes to extend the applicability of quantification models from a site-specific to a multi-regional scale. ML-built models are carefully evaluated with a training set, a test set and a case study. The acquired ML-models provide better results with R2 of 0.96 for CaCO3 and 0.78 for TOC than conventional methods. In our case study, the ML-performance for TOC is comparably lower but still provides potential for future optimization. Altogether, this study allows to conveniently generate high-resolution bulk chemistry records without losing accuracy. |
format |
Article in Journal/Newspaper |
author |
An-Sheng Lee Weng-Si Chao Sofia Ya Hsuan Liou Ralf Tiedemann Bernd Zolitschka Lester Lembke-Jene |
author_facet |
An-Sheng Lee Weng-Si Chao Sofia Ya Hsuan Liou Ralf Tiedemann Bernd Zolitschka Lester Lembke-Jene |
author_sort |
An-Sheng Lee |
title |
Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
title_short |
Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
title_full |
Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
title_fullStr |
Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
title_full_unstemmed |
Quantifying calcium carbonate and organic carbon content in marine sediments from XRF-scanning spectra with a machine learning approach |
title_sort |
quantifying calcium carbonate and organic carbon content in marine sediments from xrf-scanning spectra with a machine learning approach |
publisher |
Nature Portfolio |
publishDate |
2022 |
url |
https://doi.org/10.1038/s41598-022-25377-x https://doaj.org/article/c4fca907bb214a9f8b3871869be70ce9 |
geographic |
Southern Ocean Pacific |
geographic_facet |
Southern Ocean Pacific |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Scientific Reports, Vol 12, Iss 1, Pp 1-11 (2022) |
op_relation |
https://doi.org/10.1038/s41598-022-25377-x https://doaj.org/toc/2045-2322 doi:10.1038/s41598-022-25377-x 2045-2322 https://doaj.org/article/c4fca907bb214a9f8b3871869be70ce9 |
op_doi |
https://doi.org/10.1038/s41598-022-25377-x |
container_title |
Scientific Reports |
container_volume |
12 |
container_issue |
1 |
_version_ |
1766207159535665152 |