Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications
Above-ground biomass (AGB) serves as an indicator of crop growth status, and acquiring timely AGB information is crucial for estimating crop yield and determining appropriate water and fertilizer inputs. Unmanned Aerial Vehicles (UAVs) equipped with RGB cameras offer an affordable and practical solu...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/14/3653 |
| _version_ | 1797587623411187712 |
|---|---|
| author | Weiguang Zhai Changchun Li Qian Cheng Bohan Mao Zongpeng Li Yafeng Li Fan Ding Siqing Qin Shuaipeng Fei Zhen Chen |
| author_facet | Weiguang Zhai Changchun Li Qian Cheng Bohan Mao Zongpeng Li Yafeng Li Fan Ding Siqing Qin Shuaipeng Fei Zhen Chen |
| author_sort | Weiguang Zhai |
| collection | DOAJ |
| description | Above-ground biomass (AGB) serves as an indicator of crop growth status, and acquiring timely AGB information is crucial for estimating crop yield and determining appropriate water and fertilizer inputs. Unmanned Aerial Vehicles (UAVs) equipped with RGB cameras offer an affordable and practical solution for efficiently obtaining crop AGB. However, traditional vegetation indices (VIs) alone are insufficient in capturing crop canopy structure, leading to poor estimation accuracy. Moreover, different flight heights and machine learning algorithms can impact estimation accuracy. Therefore, this study aims to enhance wheat AGB estimation accuracy by combining VIs, crop height, and texture features while investigating the influence of flight height and machine learning algorithms on estimation. During the heading and grain-filling stages of wheat, wheat AGB data and UAV RGB images were collected at flight heights of 30 m, 60 m, and 90 m. Machine learning algorithms, including Random Forest Regression (RFR), Gradient Boosting Regression Trees (GBRT), Ridge Regression (RR), Least Absolute Shrinkage and Selection Operator (Lasso) and Support Vector Regression (SVR), were utilized to construct wheat AGB estimation models. The research findings are as follows: (1) Estimation accuracy using VIs alone is relatively low, with R<sup>2</sup> values ranging from 0.519 to 0.695. However, combining VIs with crop height and texture features improves estimation accuracy, with R<sup>2</sup> values reaching 0.845 to 0.852. (2) Estimation accuracy gradually decreases with increasing flight height, resulting in R<sup>2</sup> values of 0.519–0.852, 0.438–0.837, and 0.445–0.827 for flight heights of 30 m, 60 m, and 90 m, respectively. (3) The choice of machine learning algorithm significantly influences estimation accuracy, with RFR outperforming other machine learnings. In conclusion, UAV RGB images contain valuable crop canopy information, and effectively utilizing this information in conjunction with machine learning algorithms enables accurate wheat AGB estimation, providing a new approach for precision agriculture management using UAV remote sensing technology. |
| first_indexed | 2024-03-11T00:41:32Z |
| format | Article |
| id | doaj.art-f1d49ecaea3c4ff782f6649d50f62e55 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:41:32Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f1d49ecaea3c4ff782f6649d50f62e552023-11-18T21:13:50ZengMDPI AGRemote Sensing2072-42922023-07-011514365310.3390/rs15143653Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm ImplicationsWeiguang Zhai0Changchun Li1Qian Cheng2Bohan Mao3Zongpeng Li4Yafeng Li5Fan Ding6Siqing Qin7Shuaipeng Fei8Zhen Chen9Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100193, ChinaInstitute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, ChinaAbove-ground biomass (AGB) serves as an indicator of crop growth status, and acquiring timely AGB information is crucial for estimating crop yield and determining appropriate water and fertilizer inputs. Unmanned Aerial Vehicles (UAVs) equipped with RGB cameras offer an affordable and practical solution for efficiently obtaining crop AGB. However, traditional vegetation indices (VIs) alone are insufficient in capturing crop canopy structure, leading to poor estimation accuracy. Moreover, different flight heights and machine learning algorithms can impact estimation accuracy. Therefore, this study aims to enhance wheat AGB estimation accuracy by combining VIs, crop height, and texture features while investigating the influence of flight height and machine learning algorithms on estimation. During the heading and grain-filling stages of wheat, wheat AGB data and UAV RGB images were collected at flight heights of 30 m, 60 m, and 90 m. Machine learning algorithms, including Random Forest Regression (RFR), Gradient Boosting Regression Trees (GBRT), Ridge Regression (RR), Least Absolute Shrinkage and Selection Operator (Lasso) and Support Vector Regression (SVR), were utilized to construct wheat AGB estimation models. The research findings are as follows: (1) Estimation accuracy using VIs alone is relatively low, with R<sup>2</sup> values ranging from 0.519 to 0.695. However, combining VIs with crop height and texture features improves estimation accuracy, with R<sup>2</sup> values reaching 0.845 to 0.852. (2) Estimation accuracy gradually decreases with increasing flight height, resulting in R<sup>2</sup> values of 0.519–0.852, 0.438–0.837, and 0.445–0.827 for flight heights of 30 m, 60 m, and 90 m, respectively. (3) The choice of machine learning algorithm significantly influences estimation accuracy, with RFR outperforming other machine learnings. In conclusion, UAV RGB images contain valuable crop canopy information, and effectively utilizing this information in conjunction with machine learning algorithms enables accurate wheat AGB estimation, providing a new approach for precision agriculture management using UAV remote sensing technology.https://www.mdpi.com/2072-4292/15/14/3653above-ground biomassunmanned aerial vehicleflight heightwheatmachine learning |
| spellingShingle | Weiguang Zhai Changchun Li Qian Cheng Bohan Mao Zongpeng Li Yafeng Li Fan Ding Siqing Qin Shuaipeng Fei Zhen Chen Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications Remote Sensing above-ground biomass unmanned aerial vehicle flight height wheat machine learning |
| title | Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications |
| title_full | Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications |
| title_fullStr | Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications |
| title_full_unstemmed | Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications |
| title_short | Enhancing Wheat Above-Ground Biomass Estimation Using UAV RGB Images and Machine Learning: Multi-Feature Combinations, Flight Height, and Algorithm Implications |
| title_sort | enhancing wheat above ground biomass estimation using uav rgb images and machine learning multi feature combinations flight height and algorithm implications |
| topic | above-ground biomass unmanned aerial vehicle flight height wheat machine learning |
| url | https://www.mdpi.com/2072-4292/15/14/3653 |
| work_keys_str_mv | AT weiguangzhai enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT changchunli enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT qiancheng enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT bohanmao enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT zongpengli enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT yafengli enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT fanding enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT siqingqin enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT shuaipengfei enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications AT zhenchen enhancingwheatabovegroundbiomassestimationusinguavrgbimagesandmachinelearningmultifeaturecombinationsflightheightandalgorithmimplications |