Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering
High throughput field phenotyping techniques employing multispectral cameras allow extracting a variety of variables and features to predict yield and yield related traits, but little is known about which types of multispectral features are optimal to forecast yield potential in the early growth pha...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1214931/full |
| _version_ | 1797367735738433536 |
|---|---|
| author | Moritz Paul Camenzind Kang Yu Kang Yu |
| author_facet | Moritz Paul Camenzind Kang Yu Kang Yu |
| author_sort | Moritz Paul Camenzind |
| collection | DOAJ |
| description | High throughput field phenotyping techniques employing multispectral cameras allow extracting a variety of variables and features to predict yield and yield related traits, but little is known about which types of multispectral features are optimal to forecast yield potential in the early growth phase. In this study, we aim to identify multispectral features that are able to accurately predict yield and aid in variety classification at different growth stages throughout the season. Furthermore, we hypothesize that texture features (TFs) are more suitable for variety classification than for yield prediction. Throughout 2021 and 2022, a trial involving 19 and 18 European wheat varieties, respectively, was conducted. Multispectral images, encompassing visible, Red-edge, and near-infrared (NIR) bands, were captured at 19 and 22 time points from tillering to harvest using an unmanned aerial vehicle (UAV) in the first and second year of trial. Subsequently, orthomosaic images were generated, and various features were extracted, including single-band reflectances, vegetation indices (VI), and TFs derived from a gray level correlation matrix (GLCM). The performance of these features in predicting yield and classifying varieties at different growth stages was assessed using random forest models. Measurements during the flowering stage demonstrated superior performance for most features. Specifically, Red reflectance achieved a root mean square error (RMSE) of 52.4 g m-2 in the first year and 64.4 g m-2 in the second year. The NDRE VI yielded the most accurate predictions with an RMSE of 49.1 g m-2 and 60.6 g m-2, respectively. Moreover, TFs such as CONTRAST and DISSIMILARITY displayed the best performance in predicting yield, with RMSE values of 55.5 g m-2 and 66.3 g m-2 across the two years of trial. Combining data from different dates enhanced yield prediction and stabilized predictions across dates. TFs exhibited high accuracy in classifying low and high-yielding varieties. The CORRELATION feature achieved an accuracy of 88% in the first year, while the HOMOGENEITY feature reached 92% accuracy in the second year. This study confirms the hypothesis that TFs are more suitable for variety classification than for yield prediction. The results underscore the potential of TFs derived from multispectral images in early yield prediction and varietal classification, offering insights for HTP and precision agriculture alike. |
| first_indexed | 2024-03-08T17:21:32Z |
| format | Article |
| id | doaj.art-2b1e396a10b74f2fbfa23f67f89c6f0a |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-08T17:21:32Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-2b1e396a10b74f2fbfa23f67f89c6f0a2024-01-03T04:28:21ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-01-011410.3389/fpls.2023.12149311214931Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before floweringMoritz Paul Camenzind0Kang Yu1Kang Yu2Precision Agriculture Lab, School of Life Sciences, Technical University of Munich, Freising, GermanyPrecision Agriculture Lab, School of Life Sciences, Technical University of Munich, Freising, GermanyWorld Agricultural Systems Center (Hans Eisenmann-Forum for Agricultural Sciences – HEF), Technical University of Munich, Freising, GermanyHigh throughput field phenotyping techniques employing multispectral cameras allow extracting a variety of variables and features to predict yield and yield related traits, but little is known about which types of multispectral features are optimal to forecast yield potential in the early growth phase. In this study, we aim to identify multispectral features that are able to accurately predict yield and aid in variety classification at different growth stages throughout the season. Furthermore, we hypothesize that texture features (TFs) are more suitable for variety classification than for yield prediction. Throughout 2021 and 2022, a trial involving 19 and 18 European wheat varieties, respectively, was conducted. Multispectral images, encompassing visible, Red-edge, and near-infrared (NIR) bands, were captured at 19 and 22 time points from tillering to harvest using an unmanned aerial vehicle (UAV) in the first and second year of trial. Subsequently, orthomosaic images were generated, and various features were extracted, including single-band reflectances, vegetation indices (VI), and TFs derived from a gray level correlation matrix (GLCM). The performance of these features in predicting yield and classifying varieties at different growth stages was assessed using random forest models. Measurements during the flowering stage demonstrated superior performance for most features. Specifically, Red reflectance achieved a root mean square error (RMSE) of 52.4 g m-2 in the first year and 64.4 g m-2 in the second year. The NDRE VI yielded the most accurate predictions with an RMSE of 49.1 g m-2 and 60.6 g m-2, respectively. Moreover, TFs such as CONTRAST and DISSIMILARITY displayed the best performance in predicting yield, with RMSE values of 55.5 g m-2 and 66.3 g m-2 across the two years of trial. Combining data from different dates enhanced yield prediction and stabilized predictions across dates. TFs exhibited high accuracy in classifying low and high-yielding varieties. The CORRELATION feature achieved an accuracy of 88% in the first year, while the HOMOGENEITY feature reached 92% accuracy in the second year. This study confirms the hypothesis that TFs are more suitable for variety classification than for yield prediction. The results underscore the potential of TFs derived from multispectral images in early yield prediction and varietal classification, offering insights for HTP and precision agriculture alike.https://www.frontiersin.org/articles/10.3389/fpls.2023.1214931/fullwheat variety testingyield predictionUAV remote sensingimage texture featuresmachine learningphenology |
| spellingShingle | Moritz Paul Camenzind Kang Yu Kang Yu Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering Frontiers in Plant Science wheat variety testing yield prediction UAV remote sensing image texture features machine learning phenology |
| title | Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering |
| title_full | Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering |
| title_fullStr | Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering |
| title_full_unstemmed | Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering |
| title_short | Multi temporal multispectral UAV remote sensing allows for yield assessment across European wheat varieties already before flowering |
| title_sort | multi temporal multispectral uav remote sensing allows for yield assessment across european wheat varieties already before flowering |
| topic | wheat variety testing yield prediction UAV remote sensing image texture features machine learning phenology |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1214931/full |
| work_keys_str_mv | AT moritzpaulcamenzind multitemporalmultispectraluavremotesensingallowsforyieldassessmentacrosseuropeanwheatvarietiesalreadybeforeflowering AT kangyu multitemporalmultispectraluavremotesensingallowsforyieldassessmentacrosseuropeanwheatvarietiesalreadybeforeflowering AT kangyu multitemporalmultispectraluavremotesensingallowsforyieldassessmentacrosseuropeanwheatvarietiesalreadybeforeflowering |