Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis
Hyperspectral imaging has recently emerged in the geosciences as a technology that provides rapid, accurate, and high-resolution information from lake sediment cores. Here we introduce a new methodology to infer particle size distribution, an insightful proxy that tracks past changes in aquatic ecos...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/23/3850 |
| _version_ | 1797546888570863616 |
|---|---|
| author | Hamid Ghanbari Olivier Jacques Marc-Élie Adaïmé Irene Gregory-Eaves Dermot Antoniades |
| author_facet | Hamid Ghanbari Olivier Jacques Marc-Élie Adaïmé Irene Gregory-Eaves Dermot Antoniades |
| author_sort | Hamid Ghanbari |
| collection | DOAJ |
| description | Hyperspectral imaging has recently emerged in the geosciences as a technology that provides rapid, accurate, and high-resolution information from lake sediment cores. Here we introduce a new methodology to infer particle size distribution, an insightful proxy that tracks past changes in aquatic ecosystems and their catchments, from laboratory hyperspectral images of lake sediment cores. The proposed methodology includes data preparation, spectral preprocessing and transformation, variable selection, and model fitting. We evaluated random forest regression and other commonly used statistical methods to find the best model for particle size determination. We tested the performance of combinations of spectral transformation techniques, including absorbance, continuum removal, and first and second derivatives of the reflectance and absorbance, along with different regression models including partial least squares, multiple linear regression, principal component regression, and support vector regression, and evaluated the resulting root mean square error (RMSE), R-squared, and mean relative error (MRE). Our results show that a random forest regression model built on spectra absorbance significantly outperforms all other models. The new workflow demonstrated herein represents a much-improved method for generating inferences from hyperspectral imagery, which opens many new opportunities for advancing the study of sediment archives. |
| first_indexed | 2024-03-10T14:36:37Z |
| format | Article |
| id | doaj.art-19705079d0b24bc2b0a0869120df7ebb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:36:37Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-19705079d0b24bc2b0a0869120df7ebb2023-11-20T22:08:22ZengMDPI AGRemote Sensing2072-42922020-11-011223385010.3390/rs12233850Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image AnalysisHamid Ghanbari0Olivier Jacques1Marc-Élie Adaïmé2Irene Gregory-Eaves3Dermot Antoniades4Department of Geography, Université Laval, Québec, QC G1V 0A6, CanadaDepartment of Geography, Université Laval, Québec, QC G1V 0A6, CanadaDepartment of Geography, Université Laval, Québec, QC G1V 0A6, CanadaGroupe de Recherche Interuniversitaire en Limnologie, Université de Montréal, C.P. 6128, Succursale Centre-Ville, Montréal, QC H3C 3J7, CanadaDepartment of Geography, Université Laval, Québec, QC G1V 0A6, CanadaHyperspectral imaging has recently emerged in the geosciences as a technology that provides rapid, accurate, and high-resolution information from lake sediment cores. Here we introduce a new methodology to infer particle size distribution, an insightful proxy that tracks past changes in aquatic ecosystems and their catchments, from laboratory hyperspectral images of lake sediment cores. The proposed methodology includes data preparation, spectral preprocessing and transformation, variable selection, and model fitting. We evaluated random forest regression and other commonly used statistical methods to find the best model for particle size determination. We tested the performance of combinations of spectral transformation techniques, including absorbance, continuum removal, and first and second derivatives of the reflectance and absorbance, along with different regression models including partial least squares, multiple linear regression, principal component regression, and support vector regression, and evaluated the resulting root mean square error (RMSE), R-squared, and mean relative error (MRE). Our results show that a random forest regression model built on spectra absorbance significantly outperforms all other models. The new workflow demonstrated herein represents a much-improved method for generating inferences from hyperspectral imagery, which opens many new opportunities for advancing the study of sediment archives.https://www.mdpi.com/2072-4292/12/23/3850hyperspectral imagerandom forestmean particle sizesediment corepaleolimnology |
| spellingShingle | Hamid Ghanbari Olivier Jacques Marc-Élie Adaïmé Irene Gregory-Eaves Dermot Antoniades Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis Remote Sensing hyperspectral image random forest mean particle size sediment core paleolimnology |
| title | Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis |
| title_full | Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis |
| title_fullStr | Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis |
| title_full_unstemmed | Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis |
| title_short | Remote Sensing of Lake Sediment Core Particle Size Using Hyperspectral Image Analysis |
| title_sort | remote sensing of lake sediment core particle size using hyperspectral image analysis |
| topic | hyperspectral image random forest mean particle size sediment core paleolimnology |
| url | https://www.mdpi.com/2072-4292/12/23/3850 |
| work_keys_str_mv | AT hamidghanbari remotesensingoflakesedimentcoreparticlesizeusinghyperspectralimageanalysis AT olivierjacques remotesensingoflakesedimentcoreparticlesizeusinghyperspectralimageanalysis AT marcelieadaime remotesensingoflakesedimentcoreparticlesizeusinghyperspectralimageanalysis AT irenegregoryeaves remotesensingoflakesedimentcoreparticlesizeusinghyperspectralimageanalysis AT dermotantoniades remotesensingoflakesedimentcoreparticlesizeusinghyperspectralimageanalysis |