Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning
Aboveground biomass (AGB) is a critical indicator for monitoring the crop growth status and predicting yields. UAV remote sensing technology offers an efficient and non-destructive method for collecting crop information in small-scale agricultural fields. High-resolution hyperspectral images provide...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/13/21/2978 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173270755246080 |
|---|---|
| author | Xia Liu Ruiqi Du Youzhen Xiang Junying Chen Fucang Zhang Hongzhao Shi Zijun Tang Xin Wang |
| author_facet | Xia Liu Ruiqi Du Youzhen Xiang Junying Chen Fucang Zhang Hongzhao Shi Zijun Tang Xin Wang |
| author_sort | Xia Liu |
| collection | DOAJ |
| description | Aboveground biomass (AGB) is a critical indicator for monitoring the crop growth status and predicting yields. UAV remote sensing technology offers an efficient and non-destructive method for collecting crop information in small-scale agricultural fields. High-resolution hyperspectral images provide abundant spectral-textural information, but whether they can enhance the accuracy of crop biomass estimations remains subject to further investigation. This study evaluates the predictability of winter canola AGB by integrating the narrowband spectra and texture features from UAV hyperspectral images. Specifically, narrowband spectra and vegetation indices were extracted from the hyperspectral images. The Gray Level Co-occurrence Matrix (GLCM) method was employed to compute texture indices. Correlation analysis and autocorrelation analysis were utilized to determine the final spectral feature scheme, texture feature scheme, and spectral-texture feature scheme. Subsequently, machine learning algorithms were applied to develop estimation models for winter canola biomass. The results indicate: (1) For spectra features, narrow-bands at 450~510 nm, 680~738 nm, 910~940 nm wavelength, as well as vegetation indices containing red-edge narrow-bands, showed outstanding performance with correlation coefficients ranging from 0.49 to 0.65; For texture features, narrow-band texture parameters CON, DIS, ENT, ASM, and vegetation index texture parameter COR demonstrated significant performance, with correlation coefficients between 0.65 and 0.72; (2) The Adaboost model using the spectra-texture feature scheme exhibited the best performance in estimating winter canola biomass (R<sup>2</sup> = 0.91; RMSE = 1710.79 kg/ha; NRMSE = 19.88%); (3) The combined use of narrowband spectra and texture feature significantly improved the estimation accuracy of winter canola biomass. Compared to the spectra feature scheme, the model’s R<sup>2</sup> increased by 11.2%, RMSE decreased by 29%, and NRMSE reduced by 17%. These findings provide a reference for studies on UAV hyperspectral remote sensing monitoring of crop growth status. |
| format | Article |
| id | doaj-art-cd2cd35ebafb4546ac803787d4ab259d |
| institution | Kabale University |
| issn | 2223-7747 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj-art-cd2cd35ebafb4546ac803787d4ab259d2024-11-08T14:39:09ZengMDPI AGPlants2223-77472024-10-011321297810.3390/plants13212978Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine LearningXia Liu0Ruiqi Du1Youzhen Xiang2Junying Chen3Fucang Zhang4Hongzhao Shi5Zijun Tang6Xin Wang7College of Water Conservancy and Civil Engineering, Inner Mongolia Agricultural University, Hohhot 010010, ChinaCollege of Water Conservancy and Civil Engineering, Inner Mongolia Agricultural University, Hohhot 010010, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architecture Engineering, Northwest A&F University, Yangling 712100, ChinaAboveground biomass (AGB) is a critical indicator for monitoring the crop growth status and predicting yields. UAV remote sensing technology offers an efficient and non-destructive method for collecting crop information in small-scale agricultural fields. High-resolution hyperspectral images provide abundant spectral-textural information, but whether they can enhance the accuracy of crop biomass estimations remains subject to further investigation. This study evaluates the predictability of winter canola AGB by integrating the narrowband spectra and texture features from UAV hyperspectral images. Specifically, narrowband spectra and vegetation indices were extracted from the hyperspectral images. The Gray Level Co-occurrence Matrix (GLCM) method was employed to compute texture indices. Correlation analysis and autocorrelation analysis were utilized to determine the final spectral feature scheme, texture feature scheme, and spectral-texture feature scheme. Subsequently, machine learning algorithms were applied to develop estimation models for winter canola biomass. The results indicate: (1) For spectra features, narrow-bands at 450~510 nm, 680~738 nm, 910~940 nm wavelength, as well as vegetation indices containing red-edge narrow-bands, showed outstanding performance with correlation coefficients ranging from 0.49 to 0.65; For texture features, narrow-band texture parameters CON, DIS, ENT, ASM, and vegetation index texture parameter COR demonstrated significant performance, with correlation coefficients between 0.65 and 0.72; (2) The Adaboost model using the spectra-texture feature scheme exhibited the best performance in estimating winter canola biomass (R<sup>2</sup> = 0.91; RMSE = 1710.79 kg/ha; NRMSE = 19.88%); (3) The combined use of narrowband spectra and texture feature significantly improved the estimation accuracy of winter canola biomass. Compared to the spectra feature scheme, the model’s R<sup>2</sup> increased by 11.2%, RMSE decreased by 29%, and NRMSE reduced by 17%. These findings provide a reference for studies on UAV hyperspectral remote sensing monitoring of crop growth status.https://www.mdpi.com/2223-7747/13/21/2978UAVhyperspectraltexturebiomassnarrowband |
| spellingShingle | Xia Liu Ruiqi Du Youzhen Xiang Junying Chen Fucang Zhang Hongzhao Shi Zijun Tang Xin Wang Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning Plants UAV hyperspectral texture biomass narrowband |
| title | Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning |
| title_full | Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning |
| title_fullStr | Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning |
| title_full_unstemmed | Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning |
| title_short | Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning |
| title_sort | estimating winter canola aboveground biomass from hyperspectral images using narrowband spectra texture features and machine learning |
| topic | UAV hyperspectral texture biomass narrowband |
| url | https://www.mdpi.com/2223-7747/13/21/2978 |
| work_keys_str_mv | AT xialiu estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT ruiqidu estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT youzhenxiang estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT junyingchen estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT fucangzhang estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT hongzhaoshi estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT zijuntang estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning AT xinwang estimatingwintercanolaabovegroundbiomassfromhyperspectralimagesusingnarrowbandspectratexturefeaturesandmachinelearning |