UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques
<i>Miscanthus</i> holds a great potential in the frame of the bioeconomy, and yield prediction can help improve <i>Miscanthus’</i> logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding <i>Miscanthus</i> hybrids bette...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/12/2927 |
| _version_ | 1797482681974390784 |
|---|---|
| author | Giorgio Impollonia Michele Croci Andrea Ferrarini Jason Brook Enrico Martani Henri Blandinières Andrea Marcone Danny Awty-Carroll Chris Ashman Jason Kam Andreas Kiesel Luisa M. Trindade Mirco Boschetti John Clifton-Brown Stefano Amaducci |
| author_facet | Giorgio Impollonia Michele Croci Andrea Ferrarini Jason Brook Enrico Martani Henri Blandinières Andrea Marcone Danny Awty-Carroll Chris Ashman Jason Kam Andreas Kiesel Luisa M. Trindade Mirco Boschetti John Clifton-Brown Stefano Amaducci |
| author_sort | Giorgio Impollonia |
| collection | DOAJ |
| description | <i>Miscanthus</i> holds a great potential in the frame of the bioeconomy, and yield prediction can help improve <i>Miscanthus’</i> logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding <i>Miscanthus</i> hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel <i>Miscanthus</i> hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha<sup>−1</sup>. The study demonstrates the potential of UAVs’ multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production. |
| first_indexed | 2024-03-09T22:36:00Z |
| format | Article |
| id | doaj.art-a5e3d08c13654f8dacf5f0e3ec8defa9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T22:36:00Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a5e3d08c13654f8dacf5f0e3ec8defa92023-11-23T18:49:03ZengMDPI AGRemote Sensing2072-42922022-06-011412292710.3390/rs14122927UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning TechniquesGiorgio Impollonia0Michele Croci1Andrea Ferrarini2Jason Brook3Enrico Martani4Henri Blandinières5Andrea Marcone6Danny Awty-Carroll7Chris Ashman8Jason Kam9Andreas Kiesel10Luisa M. Trindade11Mirco Boschetti12John Clifton-Brown13Stefano Amaducci14Department of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyInstitute of Biological, Environmental and Rural Sciences (IBERS), Aberystwyth University, Aberystwyth SY23 3EE, UKDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, ItalyInstitute of Biological, Environmental and Rural Sciences (IBERS), Aberystwyth University, Aberystwyth SY23 3EE, UKInstitute of Biological, Environmental and Rural Sciences (IBERS), Aberystwyth University, Aberystwyth SY23 3EE, UKTerravesta, Unit 4 Riverside Court, Skellingthorpe Road, Saxilby, Lincoln LN1 5AB, UKDepartment of Biobased Resources in the Bioeconomy, Institute of Crop Science, University of Hohenheim, 70599 Stuttgart, GermanyDepartment of Plant Breeding, Wageningen University & Research, 6700 AJ Wageningen, The NetherlandsInstitute for Electromagnetic Sensing of the Environment, National Research Council, 20133 Milan, ItalyInstitut für Pflanzenbau und Pflanzenzüchtung I, Justus-Liebig-Universität Gießen, Heinrich-Buff-Ring 26, 35392 Gießen, GermanyDepartment of Sustainable Crop Production, Università Cattolica del Sacro Cuore, 29122 Piacenza, Italy<i>Miscanthus</i> holds a great potential in the frame of the bioeconomy, and yield prediction can help improve <i>Miscanthus’</i> logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding <i>Miscanthus</i> hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel <i>Miscanthus</i> hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha<sup>−1</sup>. The study demonstrates the potential of UAVs’ multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production.https://www.mdpi.com/2072-4292/14/12/2927<i>Miscanthus</i>remote sensingUAVmultispectral imageshigh-throughput phenotypingmachine learning |
| spellingShingle | Giorgio Impollonia Michele Croci Andrea Ferrarini Jason Brook Enrico Martani Henri Blandinières Andrea Marcone Danny Awty-Carroll Chris Ashman Jason Kam Andreas Kiesel Luisa M. Trindade Mirco Boschetti John Clifton-Brown Stefano Amaducci UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques Remote Sensing <i>Miscanthus</i> remote sensing UAV multispectral images high-throughput phenotyping machine learning |
| title | UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques |
| title_full | UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques |
| title_fullStr | UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques |
| title_full_unstemmed | UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques |
| title_short | UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of <i>Miscanthus</i> by Machine Learning Techniques |
| title_sort | uav remote sensing for high throughput phenotyping and for yield prediction of i miscanthus i by machine learning techniques |
| topic | <i>Miscanthus</i> remote sensing UAV multispectral images high-throughput phenotyping machine learning |
| url | https://www.mdpi.com/2072-4292/14/12/2927 |
| work_keys_str_mv | AT giorgioimpollonia uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT michelecroci uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT andreaferrarini uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT jasonbrook uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT enricomartani uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT henriblandinieres uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT andreamarcone uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT dannyawtycarroll uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT chrisashman uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT jasonkam uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT andreaskiesel uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT luisamtrindade uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT mircoboschetti uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT johncliftonbrown uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques AT stefanoamaducci uavremotesensingforhighthroughputphenotypingandforyieldpredictionofimiscanthusibymachinelearningtechniques |