Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data
Across-season biomass assessment is crucial in the cultivar selection process to accurately evaluate the yield performance of lines under different growing conditions. However, it has been difficult to have an accurate, reliable, and repeated fresh biomass (FM) estimation of large populations of pla...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.950720/full |
| _version_ | 1811314546594283520 |
|---|---|
| author | Phat T. Nguyen Phat T. Nguyen Fan Shi Junping Wang Pieter E. Badenhorst German C. Spangenberg German C. Spangenberg Kevin F. Smith Kevin F. Smith Hans D. Daetwyler Hans D. Daetwyler |
| author_facet | Phat T. Nguyen Phat T. Nguyen Fan Shi Junping Wang Pieter E. Badenhorst German C. Spangenberg German C. Spangenberg Kevin F. Smith Kevin F. Smith Hans D. Daetwyler Hans D. Daetwyler |
| author_sort | Phat T. Nguyen |
| collection | DOAJ |
| description | Across-season biomass assessment is crucial in the cultivar selection process to accurately evaluate the yield performance of lines under different growing conditions. However, it has been difficult to have an accurate, reliable, and repeated fresh biomass (FM) estimation of large populations of plants in the field without destructive harvesting, which incurs significant labor and operation costs. Sensor-based phenotyping platforms have advanced in the data collection of structural and vegetative information of plants, but the developed prediction models are still limited by low correlations at different growth stages and seasons. In this study, our objective was to develop and validate the global prediction models for across-season harvested fresh biomass (FM) yield based on the ground- and air-based sensor data including ground-based LiDAR, ground-based ultrasonic, and air-based multispectral camera to extract LiDAR plant volume (LV), LiDAR point density (LV_Den), height, and Normalized Difference Vegetative Index (NDVI). The study was conducted in a row-plot field trial with 480 rows (3 rows in a plot per cultivar) throughout the whole 2020 growing season up to the reproductive stage. We evaluated the performance of each plant parameter, their relationship, and the best subset prediction models using statistical stepwise selection at the row and plot levels through the seasonal and combined seasonal datasets. The best performing model: FM~LV∗LV_Den∗NDVI had a determination of coefficient R2 of at least 0.9 in vegetative stages and 0.8 in the reproductive stage. Similar results can be achieved in a simpler model with just two LiDAR variables—FM~LV∗LV_Den. In addition, LV and LV_Den showed a robust correlation with FM on their own over seasons and growth stages, while NDVI only performed well in some seasons. The simpler model based on only LiDAR data can be widely applied over season without the need of additional sensor data and may thus make the in-field across-season biomass assessment more feasible and practical for fast and cost-effective development of higher biomass yield cultivars. |
| first_indexed | 2024-04-13T11:14:31Z |
| format | Article |
| id | doaj.art-9ad5cbd6e7b84422b49c77e4f25d4e9b |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-13T11:14:31Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-9ad5cbd6e7b84422b49c77e4f25d4e9b2022-12-22T02:49:02ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-08-011310.3389/fpls.2022.950720950720Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor dataPhat T. Nguyen0Phat T. Nguyen1Fan Shi2Junping Wang3Pieter E. Badenhorst4German C. Spangenberg5German C. Spangenberg6Kevin F. Smith7Kevin F. Smith8Hans D. Daetwyler9Hans D. Daetwyler10School of Applied System Biology, La Trobe University, Bundoora, VIC, AustraliaAgriculture Victoria, AgriBio, Centre for AgriBioscience, Bundoora, VIC, AustraliaAgriculture Victoria, AgriBio, Centre for AgriBioscience, Bundoora, VIC, AustraliaAgriculture Victoria, Hamilton Centre, Hamilton, VIC, AustraliaAgriculture Victoria, Hamilton Centre, Hamilton, VIC, AustraliaSchool of Applied System Biology, La Trobe University, Bundoora, VIC, AustraliaAgriculture Victoria, AgriBio, Centre for AgriBioscience, Bundoora, VIC, AustraliaAgriculture Victoria, Hamilton Centre, Hamilton, VIC, AustraliaFaculty of Veterinary and Agricultural Sciences, School of Agriculture and Food, The University of Melbourne, Melbourne, VIC, AustraliaSchool of Applied System Biology, La Trobe University, Bundoora, VIC, AustraliaAgriculture Victoria, AgriBio, Centre for AgriBioscience, Bundoora, VIC, AustraliaAcross-season biomass assessment is crucial in the cultivar selection process to accurately evaluate the yield performance of lines under different growing conditions. However, it has been difficult to have an accurate, reliable, and repeated fresh biomass (FM) estimation of large populations of plants in the field without destructive harvesting, which incurs significant labor and operation costs. Sensor-based phenotyping platforms have advanced in the data collection of structural and vegetative information of plants, but the developed prediction models are still limited by low correlations at different growth stages and seasons. In this study, our objective was to develop and validate the global prediction models for across-season harvested fresh biomass (FM) yield based on the ground- and air-based sensor data including ground-based LiDAR, ground-based ultrasonic, and air-based multispectral camera to extract LiDAR plant volume (LV), LiDAR point density (LV_Den), height, and Normalized Difference Vegetative Index (NDVI). The study was conducted in a row-plot field trial with 480 rows (3 rows in a plot per cultivar) throughout the whole 2020 growing season up to the reproductive stage. We evaluated the performance of each plant parameter, their relationship, and the best subset prediction models using statistical stepwise selection at the row and plot levels through the seasonal and combined seasonal datasets. The best performing model: FM~LV∗LV_Den∗NDVI had a determination of coefficient R2 of at least 0.9 in vegetative stages and 0.8 in the reproductive stage. Similar results can be achieved in a simpler model with just two LiDAR variables—FM~LV∗LV_Den. In addition, LV and LV_Den showed a robust correlation with FM on their own over seasons and growth stages, while NDVI only performed well in some seasons. The simpler model based on only LiDAR data can be widely applied over season without the need of additional sensor data and may thus make the in-field across-season biomass assessment more feasible and practical for fast and cost-effective development of higher biomass yield cultivars.https://www.frontiersin.org/articles/10.3389/fpls.2022.950720/fullperennial ryegrasscross-season yieldhigh-throughput phenotypingsensorprediction modelunmanned vehicle |
| spellingShingle | Phat T. Nguyen Phat T. Nguyen Fan Shi Junping Wang Pieter E. Badenhorst German C. Spangenberg German C. Spangenberg Kevin F. Smith Kevin F. Smith Hans D. Daetwyler Hans D. Daetwyler Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data Frontiers in Plant Science perennial ryegrass cross-season yield high-throughput phenotyping sensor prediction model unmanned vehicle |
| title | Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data |
| title_full | Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data |
| title_fullStr | Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data |
| title_full_unstemmed | Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data |
| title_short | Within and combined season prediction models for perennial ryegrass biomass yield using ground- and air-based sensor data |
| title_sort | within and combined season prediction models for perennial ryegrass biomass yield using ground and air based sensor data |
| topic | perennial ryegrass cross-season yield high-throughput phenotyping sensor prediction model unmanned vehicle |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.950720/full |
| work_keys_str_mv | AT phattnguyen withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT phattnguyen withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT fanshi withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT junpingwang withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT pieterebadenhorst withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT germancspangenberg withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT germancspangenberg withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT kevinfsmith withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT kevinfsmith withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT hansddaetwyler withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata AT hansddaetwyler withinandcombinedseasonpredictionmodelsforperennialryegrassbiomassyieldusinggroundandairbasedsensordata |