Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles
Accurate phenotyping of wheat traits is essential for advancing breeding programs and crop science research. This study employs the University of Saskatchewan Field Phenotyping Systems (UFPS), an uncrewed ground vehicle (UGV), across six Canadian research stations during the 2023 and 2024 field seas...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Canadian Journal of Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/07038992.2025.2516742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850094552004689920 |
|---|---|
| author | Prabahar Ravichandran Keshav D. Singh Scott D. Noble Raju Soolanayakanahally Jatinder S. Sangha Elizabeth K. Brauer Oscar Molina Kirby T. Nilsen Harpinder S. Randhawa Keith Halcro Clare Workman Shankar Pahari |
| author_facet | Prabahar Ravichandran Keshav D. Singh Scott D. Noble Raju Soolanayakanahally Jatinder S. Sangha Elizabeth K. Brauer Oscar Molina Kirby T. Nilsen Harpinder S. Randhawa Keith Halcro Clare Workman Shankar Pahari |
| author_sort | Prabahar Ravichandran |
| collection | DOAJ |
| description | Accurate phenotyping of wheat traits is essential for advancing breeding programs and crop science research. This study employs the University of Saskatchewan Field Phenotyping Systems (UFPS), an uncrewed ground vehicle (UGV), across six Canadian research stations during the 2023 and 2024 field seasons to explore LiDAR-based evaluation of plant height and lodging in spring wheat. A total of 90 plots of 30 historical wheat cultivars were planted in a Randomized Complete Block Design (RCBD), with LiDAR data collected at key growth stages. Four methods—height distribution vector, overhead projection, orthographic projection, and voxelized spatial grid—were assessed for height and lodging classification. For plant height, overhead projection (95.98%) and orthographic projection (96.05%) delivered the highest accuracy, with RMSE and MAPE at 3.7 cm and 3.55%. Voxelized spatial grid and height distribution vector methods showed lower performance, with R-squared values of 88.15% and 84.37%. For lodging, overhead projection excelled, achieving up to 0.97 Quadratic Weighted Kappa (QWK), and 98.51% Macro-F1 (MF1), especially in 2- and 3-class scenarios. The voxelized spatial grid performed well, while the height distribution vector and orthographic projection lagged with more classes. These results establish overhead projection as a robust method for high-throughput phenotyping in spring wheat. |
| format | Article |
| id | doaj-art-5d790b875d5b41998c638f37b3f46bd7 |
| institution | DOAJ |
| issn | 1712-7971 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Canadian Journal of Remote Sensing |
| spelling | doaj-art-5d790b875d5b41998c638f37b3f46bd72025-08-20T02:41:39ZengTaylor & Francis GroupCanadian Journal of Remote Sensing1712-79712025-12-0151110.1080/07038992.2025.25167422516742Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehiclesPrabahar Ravichandran0Keshav D. Singh1Scott D. Noble2Raju Soolanayakanahally3Jatinder S. Sangha4Elizabeth K. Brauer5Oscar Molina6Kirby T. Nilsen7Harpinder S. Randhawa8Keith Halcro9Clare Workman10Shankar Pahari11Agriculture and Agri-Food Canada (AAFC), Lethbridge Research CentreAgriculture and Agri-Food Canada (AAFC), Lethbridge Research CentreCollege of Engineering, University of SaskatchewanAgriculture and Agri-Food Canada (AAFC), Saskatoon Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Swift Current Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Ottawa Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Morden Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Brandon Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Lethbridge Research CentreCollege of Engineering, University of SaskatchewanAgriculture and Agri-Food Canada (AAFC), Brandon Research and Development CentreAgriculture and Agri-Food Canada (AAFC), Saskatoon Research and Development CentreAccurate phenotyping of wheat traits is essential for advancing breeding programs and crop science research. This study employs the University of Saskatchewan Field Phenotyping Systems (UFPS), an uncrewed ground vehicle (UGV), across six Canadian research stations during the 2023 and 2024 field seasons to explore LiDAR-based evaluation of plant height and lodging in spring wheat. A total of 90 plots of 30 historical wheat cultivars were planted in a Randomized Complete Block Design (RCBD), with LiDAR data collected at key growth stages. Four methods—height distribution vector, overhead projection, orthographic projection, and voxelized spatial grid—were assessed for height and lodging classification. For plant height, overhead projection (95.98%) and orthographic projection (96.05%) delivered the highest accuracy, with RMSE and MAPE at 3.7 cm and 3.55%. Voxelized spatial grid and height distribution vector methods showed lower performance, with R-squared values of 88.15% and 84.37%. For lodging, overhead projection excelled, achieving up to 0.97 Quadratic Weighted Kappa (QWK), and 98.51% Macro-F1 (MF1), especially in 2- and 3-class scenarios. The voxelized spatial grid performed well, while the height distribution vector and orthographic projection lagged with more classes. These results establish overhead projection as a robust method for high-throughput phenotyping in spring wheat.http://dx.doi.org/10.1080/07038992.2025.2516742high-throughput wheat phenotypingdeep learningplant height estimationlodging detectionuncrewed ground vehicle (ugv) |
| spellingShingle | Prabahar Ravichandran Keshav D. Singh Scott D. Noble Raju Soolanayakanahally Jatinder S. Sangha Elizabeth K. Brauer Oscar Molina Kirby T. Nilsen Harpinder S. Randhawa Keith Halcro Clare Workman Shankar Pahari Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles Canadian Journal of Remote Sensing high-throughput wheat phenotyping deep learning plant height estimation lodging detection uncrewed ground vehicle (ugv) |
| title | Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles |
| title_full | Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles |
| title_fullStr | Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles |
| title_full_unstemmed | Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles |
| title_short | Precision phenotyping in wheat: LiDAR-based plant height estimation and lodging classification using uncrewed ground vehicles |
| title_sort | precision phenotyping in wheat lidar based plant height estimation and lodging classification using uncrewed ground vehicles |
| topic | high-throughput wheat phenotyping deep learning plant height estimation lodging detection uncrewed ground vehicle (ugv) |
| url | http://dx.doi.org/10.1080/07038992.2025.2516742 |
| work_keys_str_mv | AT prabaharravichandran precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT keshavdsingh precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT scottdnoble precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT rajusoolanayakanahally precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT jatinderssangha precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT elizabethkbrauer precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT oscarmolina precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT kirbytnilsen precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT harpindersrandhawa precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT keithhalcro precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT clareworkman precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles AT shankarpahari precisionphenotypinginwheatlidarbasedplantheightestimationandlodgingclassificationusinguncrewedgroundvehicles |