Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation
The incorporation of autonomous computation and artificial intelligence (AI) technologies into smart agriculture concepts is becoming an expected scientific procedure. The airborne hyperspectral system with its vast area coverage, high spectral resolution, and varied narrow-band selection is an exce...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/5/1114 |
| _version_ | 1797473979633500160 |
|---|---|
| author | Kai-Yun Li Raul Sampaio de Lima Niall G. Burnside Ele Vahtmäe Tiit Kutser Karli Sepp Victor Henrique Cabral Pinheiro Ming-Der Yang Ants Vain Kalev Sepp |
| author_facet | Kai-Yun Li Raul Sampaio de Lima Niall G. Burnside Ele Vahtmäe Tiit Kutser Karli Sepp Victor Henrique Cabral Pinheiro Ming-Der Yang Ants Vain Kalev Sepp |
| author_sort | Kai-Yun Li |
| collection | DOAJ |
| description | The incorporation of autonomous computation and artificial intelligence (AI) technologies into smart agriculture concepts is becoming an expected scientific procedure. The airborne hyperspectral system with its vast area coverage, high spectral resolution, and varied narrow-band selection is an excellent tool for crop physiological characteristics and yield prediction. However, the extensive and redundant three-dimensional (3D) cube data processing and computation have made the popularization of this tool a challenging task. This research integrated two important open-sourced systems (R and Python) combined with automated hyperspectral narrowband vegetation index calculation and the state-of-the-art AI-based automated machine learning (AutoML) technology to estimate yield and biomass, based on three crop categories (spring wheat, pea and oat mixture, and spring barley with red clover) with multifunctional cultivation practices in northern Europe and Estonia. Our study showed the estimated capacity of the empirical AutoML regression model was significant. The best coefficient of determination (R<sup>2</sup>) and normalized root mean square error (NRMSE) for single variety planting wheat were 0.96 and 0.12 respectively; for mixed peas and oats, they were 0.76 and 0.18 in the booting to heading stage, while for mixed legumes and spring barley, they were 0.88 and 0.16 in the reproductive growth stages. In terms of straw mass estimation, R<sup>2</sup> was 0.96, 0.83, and 0.86, and NRMSE was 0.12, 0.24, and 0.33 respectively. This research contributes to, and confirms, the use of the AutoML framework in hyperspectral image analysis to increase implementation flexibility and reduce learning costs under a variety of agricultural resource conditions. It delivers expert yield and straw mass valuation two months in advance before harvest time for decision-makers. This study also highlights that the hyperspectral system provides economic and environmental benefits and will play a critical role in the construction of sustainable and intelligent agriculture techniques in the upcoming years. |
| first_indexed | 2024-03-09T20:23:51Z |
| format | Article |
| id | doaj.art-f9415829012240e3b8881d7eef3be213 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T20:23:51Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f9415829012240e3b8881d7eef3be2132023-11-23T23:41:40ZengMDPI AGRemote Sensing2072-42922022-02-01145111410.3390/rs14051114Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass EstimationKai-Yun Li0Raul Sampaio de Lima1Niall G. Burnside2Ele Vahtmäe3Tiit Kutser4Karli Sepp5Victor Henrique Cabral Pinheiro6Ming-Der Yang7Ants Vain8Kalev Sepp9Institute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, 51006 Tartu, EstoniaInstitute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, 51006 Tartu, EstoniaCentre for Earth Observation, School of Applied Sciences, University of Brighton, Lewes Road, Brighton BN2 4GJ, UKEstonian Marine Institute, University of Tartu, Mäealuse 14, 12618 Tallinn, EstoniaEstonian Marine Institute, University of Tartu, Mäealuse 14, 12618 Tallinn, EstoniaAgricultural Research Center, 4/6 Teaduse St., 75501 Saku, EstoniaInstitution of Computer Science, Faculty of Science and Technology, University of Tartu, 50090 Tartu, EstoniaDepartment of Civil Engineering, and Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Taichung 402, TaiwanInstitute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, 51006 Tartu, EstoniaInstitute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, 51006 Tartu, EstoniaThe incorporation of autonomous computation and artificial intelligence (AI) technologies into smart agriculture concepts is becoming an expected scientific procedure. The airborne hyperspectral system with its vast area coverage, high spectral resolution, and varied narrow-band selection is an excellent tool for crop physiological characteristics and yield prediction. However, the extensive and redundant three-dimensional (3D) cube data processing and computation have made the popularization of this tool a challenging task. This research integrated two important open-sourced systems (R and Python) combined with automated hyperspectral narrowband vegetation index calculation and the state-of-the-art AI-based automated machine learning (AutoML) technology to estimate yield and biomass, based on three crop categories (spring wheat, pea and oat mixture, and spring barley with red clover) with multifunctional cultivation practices in northern Europe and Estonia. Our study showed the estimated capacity of the empirical AutoML regression model was significant. The best coefficient of determination (R<sup>2</sup>) and normalized root mean square error (NRMSE) for single variety planting wheat were 0.96 and 0.12 respectively; for mixed peas and oats, they were 0.76 and 0.18 in the booting to heading stage, while for mixed legumes and spring barley, they were 0.88 and 0.16 in the reproductive growth stages. In terms of straw mass estimation, R<sup>2</sup> was 0.96, 0.83, and 0.86, and NRMSE was 0.12, 0.24, and 0.33 respectively. This research contributes to, and confirms, the use of the AutoML framework in hyperspectral image analysis to increase implementation flexibility and reduce learning costs under a variety of agricultural resource conditions. It delivers expert yield and straw mass valuation two months in advance before harvest time for decision-makers. This study also highlights that the hyperspectral system provides economic and environmental benefits and will play a critical role in the construction of sustainable and intelligent agriculture techniques in the upcoming years.https://www.mdpi.com/2072-4292/14/5/1114hyperspectralautomated machine learningvegetation indexyield estimatesbiomass estimationprecision agriculture |
| spellingShingle | Kai-Yun Li Raul Sampaio de Lima Niall G. Burnside Ele Vahtmäe Tiit Kutser Karli Sepp Victor Henrique Cabral Pinheiro Ming-Der Yang Ants Vain Kalev Sepp Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation Remote Sensing hyperspectral automated machine learning vegetation index yield estimates biomass estimation precision agriculture |
| title | Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation |
| title_full | Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation |
| title_fullStr | Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation |
| title_full_unstemmed | Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation |
| title_short | Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation |
| title_sort | toward automated machine learning based hyperspectral image analysis in crop yield and biomass estimation |
| topic | hyperspectral automated machine learning vegetation index yield estimates biomass estimation precision agriculture |
| url | https://www.mdpi.com/2072-4292/14/5/1114 |
| work_keys_str_mv | AT kaiyunli towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT raulsampaiodelima towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT niallgburnside towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT elevahtmae towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT tiitkutser towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT karlisepp towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT victorhenriquecabralpinheiro towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT mingderyang towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT antsvain towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation AT kalevsepp towardautomatedmachinelearningbasedhyperspectralimageanalysisincropyieldandbiomassestimation |