Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm
AbstractThis study presents a novel Spectral Triad feature selection (STfs) technique based on music theory and compares it to the entire Sentinel-2 feature space and Random Forest-Recursive Feature Elimination (RF-RFE). The optimal subsets were evaluated with Random Forest for retrieving Leaf Area...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2024-01-01
|
Series: | Geocarto International |
Subjects: | |
Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2024.2309174 |
_version_ | 1797311806808522752 |
---|---|
author | Mahlatse Kganyago Clement Adjorlolo Paidamwoyo Mhangara |
author_facet | Mahlatse Kganyago Clement Adjorlolo Paidamwoyo Mhangara |
author_sort | Mahlatse Kganyago |
collection | DOAJ |
description | AbstractThis study presents a novel Spectral Triad feature selection (STfs) technique based on music theory and compares it to the entire Sentinel-2 feature space and Random Forest-Recursive Feature Elimination (RF-RFE). The optimal subsets were evaluated with Random Forest for retrieving Leaf Area Index (LAI), Leaf Chlorophyll Content (LCab), and Canopy Chlorophyll Content (CCC) in a semi-arid agricultural landscape. The results indicated that the proposed STfs algorithm obtained equivalent or better (i.e. by 1 – 3%) retrieval accuracies for LAI (R2cv of 66%, root mean squared error of cross-validation [RMSEcv] of 0.53 m2 m−2), LCab (R2cv: 74%, RMSEcv: 7.09 µg cm−2) and CCC (R2cv: 77%, RMSEcv: 33.69 µg cm−2), using only 5, 7 and 7 variables, respectively, when compared to RF-RFE and entire Sentinel-2 feature space. Overall, the proposed STfs algorithm has great potential to optimize the spectral feature space of quasi-hyperspectral sensors for rapid crop biophysical and biochemical parameter retrieval. |
first_indexed | 2024-03-08T02:05:08Z |
format | Article |
id | doaj.art-bc64413e5e4e448ababcaa1eed1e82da |
institution | Directory Open Access Journal |
issn | 1010-6049 1752-0762 |
language | English |
last_indexed | 2024-03-08T02:05:08Z |
publishDate | 2024-01-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Geocarto International |
spelling | doaj.art-bc64413e5e4e448ababcaa1eed1e82da2024-02-13T16:01:20ZengTaylor & Francis GroupGeocarto International1010-60491752-07622024-01-0139110.1080/10106049.2024.2309174Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithmMahlatse Kganyago0Clement Adjorlolo1Paidamwoyo Mhangara2Department of Geography, Environmental Management and Energy Studies, University of Johannesburg, Johannesburg, South AfricaSchool of Geography, Archaeology and Environmental Studies, University of the Witwatersrand, Johannesburg, South AfricaSchool of Geography, Archaeology and Environmental Studies, University of the Witwatersrand, Johannesburg, South AfricaAbstractThis study presents a novel Spectral Triad feature selection (STfs) technique based on music theory and compares it to the entire Sentinel-2 feature space and Random Forest-Recursive Feature Elimination (RF-RFE). The optimal subsets were evaluated with Random Forest for retrieving Leaf Area Index (LAI), Leaf Chlorophyll Content (LCab), and Canopy Chlorophyll Content (CCC) in a semi-arid agricultural landscape. The results indicated that the proposed STfs algorithm obtained equivalent or better (i.e. by 1 – 3%) retrieval accuracies for LAI (R2cv of 66%, root mean squared error of cross-validation [RMSEcv] of 0.53 m2 m−2), LCab (R2cv: 74%, RMSEcv: 7.09 µg cm−2) and CCC (R2cv: 77%, RMSEcv: 33.69 µg cm−2), using only 5, 7 and 7 variables, respectively, when compared to RF-RFE and entire Sentinel-2 feature space. Overall, the proposed STfs algorithm has great potential to optimize the spectral feature space of quasi-hyperspectral sensors for rapid crop biophysical and biochemical parameter retrieval.https://www.tandfonline.com/doi/10.1080/10106049.2024.2309174Remote sensingfeature selectionchlorophyll contentleaf area indexsentinel-2random forest |
spellingShingle | Mahlatse Kganyago Clement Adjorlolo Paidamwoyo Mhangara Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm Geocarto International Remote sensing feature selection chlorophyll content leaf area index sentinel-2 random forest |
title | Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
title_full | Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
title_fullStr | Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
title_full_unstemmed | Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
title_short | Optimizing Sentinel-2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
title_sort | optimizing sentinel 2 feature space for improved crop biophysical and biochemical variables retrieval using the novel spectral triad feature selection algorithm |
topic | Remote sensing feature selection chlorophyll content leaf area index sentinel-2 random forest |
url | https://www.tandfonline.com/doi/10.1080/10106049.2024.2309174 |
work_keys_str_mv | AT mahlatsekganyago optimizingsentinel2featurespaceforimprovedcropbiophysicalandbiochemicalvariablesretrievalusingthenovelspectraltriadfeatureselectionalgorithm AT clementadjorlolo optimizingsentinel2featurespaceforimprovedcropbiophysicalandbiochemicalvariablesretrievalusingthenovelspectraltriadfeatureselectionalgorithm AT paidamwoyomhangara optimizingsentinel2featurespaceforimprovedcropbiophysicalandbiochemicalvariablesretrievalusingthenovelspectraltriadfeatureselectionalgorithm |