Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data
Grassland ecosystems can be hotspots of biodiversity and act as carbon sinks while at the same time providing the basis of forage production for ruminants in dairy and meat production. Annual grassland dry matter yield (DMY) is one of the most important agronomic parameters reflecting differences in...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2068 |
| _version_ | 1797503021107642368 |
|---|---|
| author | Matthias Wengert Jayan Wijesingha Damian Schulze-Brüninghoff Michael Wachendorf Thomas Astor |
| author_facet | Matthias Wengert Jayan Wijesingha Damian Schulze-Brüninghoff Michael Wachendorf Thomas Astor |
| author_sort | Matthias Wengert |
| collection | DOAJ |
| description | Grassland ecosystems can be hotspots of biodiversity and act as carbon sinks while at the same time providing the basis of forage production for ruminants in dairy and meat production. Annual grassland dry matter yield (DMY) is one of the most important agronomic parameters reflecting differences in usage intensity such as number of harvests and fertilization. Current methods for grassland DMY estimation are labor-intensive and prone to error due to small sample size. With the advent of unmanned aerial vehicles (UAVs) and miniaturized hyperspectral sensors, a novel tool for remote sensing of grassland with high spatial, temporal and radiometric resolution and coverage is available. The present study aimed at developing a robust model capable of estimating grassland biomass across a gradient of usage intensity throughout one growing season. Therefore, UAV-borne hyperspectral data from eight grassland sites in North Hesse, Germany, originating from different harvests, were utilized for the modeling of fresh matter yield (FMY) and DMY. Four machine learning (ML) algorithms were compared for their modeling performance. Among them, the rule-based ML method Cubist regression (CBR) performed best, delivering high prediction accuracies for both FMY (nRMSE<sub>p</sub> 7.6%, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> 0.87) and DMY (nRMSE<sub>p</sub> 12.9%, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> 0.75). The model showed a high robustness across sites and harvest dates. The best models were employed to produce maps for FMY and DMY, enabling the detailed analysis of spatial patterns. Although the complexity of the approach still restricts its practical application in agricultural management, the current study proved that biomass of grassland sites being subject to different management intensities can be modeled from UAV-borne hyperspectral data at high spatial resolution with high prediction accuracies. |
| first_indexed | 2024-03-10T03:44:32Z |
| format | Article |
| id | doaj.art-050ec70fa392437db527e6c848a11826 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:44:32Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-050ec70fa392437db527e6c848a118262023-11-23T09:10:05ZengMDPI AGRemote Sensing2072-42922022-04-01149206810.3390/rs14092068Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral DataMatthias Wengert0Jayan Wijesingha1Damian Schulze-Brüninghoff2Michael Wachendorf3Thomas Astor4Grassland Science and Renewable Plant Resources, Universität Kassel, Steinstraße 19, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Universität Kassel, Steinstraße 19, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Universität Kassel, Steinstraße 19, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Universität Kassel, Steinstraße 19, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Universität Kassel, Steinstraße 19, D-37213 Witzenhausen, GermanyGrassland ecosystems can be hotspots of biodiversity and act as carbon sinks while at the same time providing the basis of forage production for ruminants in dairy and meat production. Annual grassland dry matter yield (DMY) is one of the most important agronomic parameters reflecting differences in usage intensity such as number of harvests and fertilization. Current methods for grassland DMY estimation are labor-intensive and prone to error due to small sample size. With the advent of unmanned aerial vehicles (UAVs) and miniaturized hyperspectral sensors, a novel tool for remote sensing of grassland with high spatial, temporal and radiometric resolution and coverage is available. The present study aimed at developing a robust model capable of estimating grassland biomass across a gradient of usage intensity throughout one growing season. Therefore, UAV-borne hyperspectral data from eight grassland sites in North Hesse, Germany, originating from different harvests, were utilized for the modeling of fresh matter yield (FMY) and DMY. Four machine learning (ML) algorithms were compared for their modeling performance. Among them, the rule-based ML method Cubist regression (CBR) performed best, delivering high prediction accuracies for both FMY (nRMSE<sub>p</sub> 7.6%, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> 0.87) and DMY (nRMSE<sub>p</sub> 12.9%, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> 0.75). The model showed a high robustness across sites and harvest dates. The best models were employed to produce maps for FMY and DMY, enabling the detailed analysis of spatial patterns. Although the complexity of the approach still restricts its practical application in agricultural management, the current study proved that biomass of grassland sites being subject to different management intensities can be modeled from UAV-borne hyperspectral data at high spatial resolution with high prediction accuracies.https://www.mdpi.com/2072-4292/14/9/2068UAVhyperspectralgrasslandbiomassmultisitemultitemporal |
| spellingShingle | Matthias Wengert Jayan Wijesingha Damian Schulze-Brüninghoff Michael Wachendorf Thomas Astor Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data Remote Sensing UAV hyperspectral grassland biomass multisite multitemporal |
| title | Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data |
| title_full | Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data |
| title_fullStr | Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data |
| title_full_unstemmed | Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data |
| title_short | Multisite and Multitemporal Grassland Yield Estimation Using UAV-Borne Hyperspectral Data |
| title_sort | multisite and multitemporal grassland yield estimation using uav borne hyperspectral data |
| topic | UAV hyperspectral grassland biomass multisite multitemporal |
| url | https://www.mdpi.com/2072-4292/14/9/2068 |
| work_keys_str_mv | AT matthiaswengert multisiteandmultitemporalgrasslandyieldestimationusinguavbornehyperspectraldata AT jayanwijesingha multisiteandmultitemporalgrasslandyieldestimationusinguavbornehyperspectraldata AT damianschulzebruninghoff multisiteandmultitemporalgrasslandyieldestimationusinguavbornehyperspectraldata AT michaelwachendorf multisiteandmultitemporalgrasslandyieldestimationusinguavbornehyperspectraldata AT thomasastor multisiteandmultitemporalgrasslandyieldestimationusinguavbornehyperspectraldata |