Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning
Precise and timely information on biomass yield and nitrogen uptake in intensively managed grasslands are essential for sustainable management decisions. Imaging sensors mounted on unmanned aerial vehicles (UAVs) along with photogrammetric structure-from-motion processing can provide timely data on...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/13/3066 |
| _version_ | 1827625445212815360 |
|---|---|
| author | Ulrike Lussem Andreas Bolten Ireneusz Kleppert Jörg Jasper Martin Leon Gnyp Jürgen Schellberg Georg Bareth |
| author_facet | Ulrike Lussem Andreas Bolten Ireneusz Kleppert Jörg Jasper Martin Leon Gnyp Jürgen Schellberg Georg Bareth |
| author_sort | Ulrike Lussem |
| collection | DOAJ |
| description | Precise and timely information on biomass yield and nitrogen uptake in intensively managed grasslands are essential for sustainable management decisions. Imaging sensors mounted on unmanned aerial vehicles (UAVs) along with photogrammetric structure-from-motion processing can provide timely data on crop traits rapidly and non-destructively with a high spatial resolution. The aim of this multi-temporal field study is to estimate aboveground dry matter yield (DMY), nitrogen concentration (N%) and uptake (Nup) of temperate grasslands from UAV-based image data using machine learning (ML) algorithms. The study is based on a two-year dataset from an experimental grassland trial. The experimental setup regarding climate conditions, N fertilizer treatments and slope yielded substantial variations in the dataset, covering a considerable amount of naturally occurring differences in the biomass and N status of grasslands in temperate regions with similar management strategies. Linear regression models and three ML algorithms, namely, random forest (RF), support vector machine (SVM), and partial least squares (PLS) regression were compared with and without a combination of both structural (sward height; SH) and spectral (vegetation indices and single bands) features. Prediction accuracy was quantified using a 10-fold 5-repeat cross-validation (CV) procedure. The results show a significant improvement of prediction accuracy when all structural and spectral features are combined, regardless of the algorithm. The PLS models were outperformed by their respective RF and SVM counterparts. At best, DMY was predicted with a median RMSE<sub>CV</sub> of 197 kg ha<sup>−1</sup>, N% with a median RMSE<sub>CV</sub> of 0.32%, and Nup with a median RMSE<sub>CV</sub> of 7 kg ha<sup>−1</sup>. Furthermore, computationally less expensive models incorporating, e.g., only the single multispectral camera bands and SH metrics, or selected features based on variable importance achieved comparable results to the overall best models. |
| first_indexed | 2024-03-09T12:36:49Z |
| format | Article |
| id | doaj.art-55eb13928cc94f91ad49669f445f513f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:36:49Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-55eb13928cc94f91ad49669f445f513f2023-11-30T22:22:52ZengMDPI AGRemote Sensing2072-42922022-06-011413306610.3390/rs14133066Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine LearningUlrike Lussem0Andreas Bolten1Ireneusz Kleppert2Jörg Jasper3Martin Leon Gnyp4Jürgen Schellberg5Georg Bareth6Institute of Geography, University of Cologne, 50923 Cologne, GermanyInstitute of Geography, University of Cologne, 50923 Cologne, GermanyInstitute of Geography, University of Cologne, 50923 Cologne, GermanyResearch Center Hanninghof, Yara International ASA, 48249 Dülmen, GermanyResearch Center Hanninghof, Yara International ASA, 48249 Dülmen, GermanyINRES—Institute of Crop Science and Resource Conservation, University of Bonn, 53113 Bonn, GermanyInstitute of Geography, University of Cologne, 50923 Cologne, GermanyPrecise and timely information on biomass yield and nitrogen uptake in intensively managed grasslands are essential for sustainable management decisions. Imaging sensors mounted on unmanned aerial vehicles (UAVs) along with photogrammetric structure-from-motion processing can provide timely data on crop traits rapidly and non-destructively with a high spatial resolution. The aim of this multi-temporal field study is to estimate aboveground dry matter yield (DMY), nitrogen concentration (N%) and uptake (Nup) of temperate grasslands from UAV-based image data using machine learning (ML) algorithms. The study is based on a two-year dataset from an experimental grassland trial. The experimental setup regarding climate conditions, N fertilizer treatments and slope yielded substantial variations in the dataset, covering a considerable amount of naturally occurring differences in the biomass and N status of grasslands in temperate regions with similar management strategies. Linear regression models and three ML algorithms, namely, random forest (RF), support vector machine (SVM), and partial least squares (PLS) regression were compared with and without a combination of both structural (sward height; SH) and spectral (vegetation indices and single bands) features. Prediction accuracy was quantified using a 10-fold 5-repeat cross-validation (CV) procedure. The results show a significant improvement of prediction accuracy when all structural and spectral features are combined, regardless of the algorithm. The PLS models were outperformed by their respective RF and SVM counterparts. At best, DMY was predicted with a median RMSE<sub>CV</sub> of 197 kg ha<sup>−1</sup>, N% with a median RMSE<sub>CV</sub> of 0.32%, and Nup with a median RMSE<sub>CV</sub> of 7 kg ha<sup>−1</sup>. Furthermore, computationally less expensive models incorporating, e.g., only the single multispectral camera bands and SH metrics, or selected features based on variable importance achieved comparable results to the overall best models.https://www.mdpi.com/2072-4292/14/13/3066grasslandmultispectralbiomasscanopy heightNconcentration |
| spellingShingle | Ulrike Lussem Andreas Bolten Ireneusz Kleppert Jörg Jasper Martin Leon Gnyp Jürgen Schellberg Georg Bareth Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning Remote Sensing grassland multispectral biomass canopy height N concentration |
| title | Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning |
| title_full | Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning |
| title_fullStr | Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning |
| title_full_unstemmed | Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning |
| title_short | Herbage Mass, N Concentration, and N Uptake of Temperate Grasslands Can Adequately Be Estimated from UAV-Based Image Data Using Machine Learning |
| title_sort | herbage mass n concentration and n uptake of temperate grasslands can adequately be estimated from uav based image data using machine learning |
| topic | grassland multispectral biomass canopy height N concentration |
| url | https://www.mdpi.com/2072-4292/14/13/3066 |
| work_keys_str_mv | AT ulrikelussem herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT andreasbolten herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT ireneuszkleppert herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT jorgjasper herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT martinleongnyp herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT jurgenschellberg herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning AT georgbareth herbagemassnconcentrationandnuptakeoftemperategrasslandscanadequatelybeestimatedfromuavbasedimagedatausingmachinelearning |