Estimation of biomass in wheat using random forest regression algorithm and remote sensing data
Wheat biomass can be estimated using appropriate spectral vegetation indices. However, the accuracy of estimation should be further improved for on-farm crop management. Previous studies focused on developing vegetation indices, however limited research exists on modeling algorithms. The emerging Ra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2016-06-01
|
| Series: | Crop Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214514116300162 |
| _version_ | 1818823810546139136 |
|---|---|
| author | Li'ai Wang Xudong Zhou Xinkai Zhu Zhaodi Dong Wenshan Guo |
| author_facet | Li'ai Wang Xudong Zhou Xinkai Zhu Zhaodi Dong Wenshan Guo |
| author_sort | Li'ai Wang |
| collection | DOAJ |
| description | Wheat biomass can be estimated using appropriate spectral vegetation indices. However, the accuracy of estimation should be further improved for on-farm crop management. Previous studies focused on developing vegetation indices, however limited research exists on modeling algorithms. The emerging Random Forest (RF) machine-learning algorithm is regarded as one of the most precise prediction methods for regression modeling. The objectives of this study were to (1) investigate the applicability of the RF regression algorithm for remotely estimating wheat biomass, (2) test the performance of the RF regression model, and (3) compare the performance of the RF algorithm with support vector regression (SVR) and artificial neural network (ANN) machine-learning algorithms for wheat biomass estimation. Single HJ-CCD images of wheat from test sites in Jiangsu province were obtained during the jointing, booting, and anthesis stages of growth. Fifteen vegetation indices were calculated based on these images. In-situ wheat above-ground dry biomass was measured during the HJ-CCD data acquisition. The results showed that the RF model produced more accurate estimates of wheat biomass than the SVR and ANN models at each stage, and its robustness is as good as SVR but better than ANN. The RF algorithm provides a useful exploratory and predictive tool for estimating wheat biomass on a large scale in Southern China. |
| first_indexed | 2024-12-18T23:45:54Z |
| format | Article |
| id | doaj.art-88f7e1e8b6cb44f3a10cfe08e8446260 |
| institution | Directory Open Access Journal |
| issn | 2095-5421 2214-5141 |
| language | English |
| last_indexed | 2024-12-18T23:45:54Z |
| publishDate | 2016-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Crop Journal |
| spelling | doaj.art-88f7e1e8b6cb44f3a10cfe08e84462602022-12-21T20:47:12ZengKeAi Communications Co., Ltd.Crop Journal2095-54212214-51412016-06-014321221910.1016/j.cj.2016.01.008Estimation of biomass in wheat using random forest regression algorithm and remote sensing dataLi'ai Wang 0Xudong Zhou 1Xinkai Zhu 2Zhaodi Dong 3Wenshan Guo 4Key Laboratory of Crop Genetics and Physiology of Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaInformation Engineering College of Yangzhou University, Yangzhou 225009, ChinaKey Laboratory of Crop Genetics and Physiology of Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaKey Laboratory of Crop Genetics and Physiology of Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaKey Laboratory of Crop Genetics and Physiology of Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaWheat biomass can be estimated using appropriate spectral vegetation indices. However, the accuracy of estimation should be further improved for on-farm crop management. Previous studies focused on developing vegetation indices, however limited research exists on modeling algorithms. The emerging Random Forest (RF) machine-learning algorithm is regarded as one of the most precise prediction methods for regression modeling. The objectives of this study were to (1) investigate the applicability of the RF regression algorithm for remotely estimating wheat biomass, (2) test the performance of the RF regression model, and (3) compare the performance of the RF algorithm with support vector regression (SVR) and artificial neural network (ANN) machine-learning algorithms for wheat biomass estimation. Single HJ-CCD images of wheat from test sites in Jiangsu province were obtained during the jointing, booting, and anthesis stages of growth. Fifteen vegetation indices were calculated based on these images. In-situ wheat above-ground dry biomass was measured during the HJ-CCD data acquisition. The results showed that the RF model produced more accurate estimates of wheat biomass than the SVR and ANN models at each stage, and its robustness is as good as SVR but better than ANN. The RF algorithm provides a useful exploratory and predictive tool for estimating wheat biomass on a large scale in Southern China.http://www.sciencedirect.com/science/article/pii/S2214514116300162Above-ground dry biomassTriticum aestivumVegetation indicesWheat |
| spellingShingle | Li'ai Wang Xudong Zhou Xinkai Zhu Zhaodi Dong Wenshan Guo Estimation of biomass in wheat using random forest regression algorithm and remote sensing data Crop Journal Above-ground dry biomass Triticum aestivum Vegetation indices Wheat |
| title | Estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| title_full | Estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| title_fullStr | Estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| title_full_unstemmed | Estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| title_short | Estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| title_sort | estimation of biomass in wheat using random forest regression algorithm and remote sensing data |
| topic | Above-ground dry biomass Triticum aestivum Vegetation indices Wheat |
| url | http://www.sciencedirect.com/science/article/pii/S2214514116300162 |
| work_keys_str_mv | AT liaiwang estimationofbiomassinwheatusingrandomforestregressionalgorithmandremotesensingdata AT xudongzhou estimationofbiomassinwheatusingrandomforestregressionalgorithmandremotesensingdata AT xinkaizhu estimationofbiomassinwheatusingrandomforestregressionalgorithmandremotesensingdata AT zhaodidong estimationofbiomassinwheatusingrandomforestregressionalgorithmandremotesensingdata AT wenshanguo estimationofbiomassinwheatusingrandomforestregressionalgorithmandremotesensingdata |