Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning
Abstract Miscanthus is a leading perennial biomass crop that can produce high yields on marginal lands. Moisture content is a highly relevant biomass quality trait with multiple impacts on efficiencies of harvest, transport, and storage. The dynamics of moisture content during senescence and overwin...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | GCB Bioenergy |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/gcbb.12930 |
| _version_ | 1828795157206532096 |
|---|---|
| author | Giorgio Impollonia Michele Croci Enrico Martani Andrea Ferrarini Jason Kam Luisa M. Trindade John Clifton‐Brown Stefano Amaducci |
| author_facet | Giorgio Impollonia Michele Croci Enrico Martani Andrea Ferrarini Jason Kam Luisa M. Trindade John Clifton‐Brown Stefano Amaducci |
| author_sort | Giorgio Impollonia |
| collection | DOAJ |
| description | Abstract Miscanthus is a leading perennial biomass crop that can produce high yields on marginal lands. Moisture content is a highly relevant biomass quality trait with multiple impacts on efficiencies of harvest, transport, and storage. The dynamics of moisture content during senescence and overwinter ripening are determined by genotype × environment interactions. In this paper, unmanned aerial vehicle (UAV)‐based remote sensing was used for high‐throughput plant phenotyping (HTPP) of the moisture content dynamics during autumn and winter senescence of 14 contrasting hybrid types (progeny of M. sinensis x M. sinensis [M. sin x M. sin, eight types] and M. sinensis x M. sacchariflorus [M. sin x M. sac, six types]). The time series of moisture content was estimated using machine learning (ML) models and a range of vegetation indices (VIs) derived from UAV‐based remote sensing. The most important VIs for moisture content estimation were selected by the recursive feature elimination (RFE) algorithm and were BNDVI, GDVI, and PSRI. The ML model transferability was high only when the moisture content was above 30%. The best ML model accuracy was achieved by combining VIs and categorical variables (5.6% of RMSE). This model was used for phenotyping senescence dynamics and identifying the stay‐green (SG) trait of Miscanthus hybrids using the generalized additive model (GAM). Combining ML and GAM modeling, applied to time series of moisture content values estimated from VIs derived from multiple UAV flights, proved to be a powerful tool for HTPP. |
| first_indexed | 2024-12-12T03:58:54Z |
| format | Article |
| id | doaj.art-8df2a3fb8a6d406e9e58d5316e103549 |
| institution | Directory Open Access Journal |
| issn | 1757-1693 1757-1707 |
| language | English |
| last_indexed | 2024-12-12T03:58:54Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | GCB Bioenergy |
| spelling | doaj.art-8df2a3fb8a6d406e9e58d5316e1035492022-12-22T00:39:08ZengWileyGCB Bioenergy1757-16931757-17072022-06-0114663965610.1111/gcbb.12930Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learningGiorgio Impollonia0Michele Croci1Enrico Martani2Andrea Ferrarini3Jason Kam4Luisa M. Trindade5John Clifton‐Brown6Stefano Amaducci7Department of Sustainable Crop Production Università Cattolica del Sacro Cuore Piacenza ItalyDepartment of Sustainable Crop Production Università Cattolica del Sacro Cuore Piacenza ItalyDepartment of Sustainable Crop Production Università Cattolica del Sacro Cuore Piacenza ItalyDepartment of Sustainable Crop Production Università Cattolica del Sacro Cuore Piacenza ItalyTerravesta Saxilby Lincoln UKWageningen University & Research, Plant Breeding Wageningen The NetherlandsInstitute of Biological, Environmental and Rural Sciences Aberystwyth University Aberystwyth UKDepartment of Sustainable Crop Production Università Cattolica del Sacro Cuore Piacenza ItalyAbstract Miscanthus is a leading perennial biomass crop that can produce high yields on marginal lands. Moisture content is a highly relevant biomass quality trait with multiple impacts on efficiencies of harvest, transport, and storage. The dynamics of moisture content during senescence and overwinter ripening are determined by genotype × environment interactions. In this paper, unmanned aerial vehicle (UAV)‐based remote sensing was used for high‐throughput plant phenotyping (HTPP) of the moisture content dynamics during autumn and winter senescence of 14 contrasting hybrid types (progeny of M. sinensis x M. sinensis [M. sin x M. sin, eight types] and M. sinensis x M. sacchariflorus [M. sin x M. sac, six types]). The time series of moisture content was estimated using machine learning (ML) models and a range of vegetation indices (VIs) derived from UAV‐based remote sensing. The most important VIs for moisture content estimation were selected by the recursive feature elimination (RFE) algorithm and were BNDVI, GDVI, and PSRI. The ML model transferability was high only when the moisture content was above 30%. The best ML model accuracy was achieved by combining VIs and categorical variables (5.6% of RMSE). This model was used for phenotyping senescence dynamics and identifying the stay‐green (SG) trait of Miscanthus hybrids using the generalized additive model (GAM). Combining ML and GAM modeling, applied to time series of moisture content values estimated from VIs derived from multiple UAV flights, proved to be a powerful tool for HTPP.https://doi.org/10.1111/gcbb.12930GAMhigh‐throughput plant phenotypingmachine learningMiscanthusmoisture contentmultispectral |
| spellingShingle | Giorgio Impollonia Michele Croci Enrico Martani Andrea Ferrarini Jason Kam Luisa M. Trindade John Clifton‐Brown Stefano Amaducci Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning GCB Bioenergy GAM high‐throughput plant phenotyping machine learning Miscanthus moisture content multispectral |
| title | Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning |
| title_full | Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning |
| title_fullStr | Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning |
| title_full_unstemmed | Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning |
| title_short | Moisture content estimation and senescence phenotyping of novel Miscanthus hybrids combining UAV‐based remote sensing and machine learning |
| title_sort | moisture content estimation and senescence phenotyping of novel miscanthus hybrids combining uav based remote sensing and machine learning |
| topic | GAM high‐throughput plant phenotyping machine learning Miscanthus moisture content multispectral |
| url | https://doi.org/10.1111/gcbb.12930 |
| work_keys_str_mv | AT giorgioimpollonia moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT michelecroci moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT enricomartani moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT andreaferrarini moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT jasonkam moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT luisamtrindade moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT johncliftonbrown moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning AT stefanoamaducci moisturecontentestimationandsenescencephenotypingofnovelmiscanthushybridscombininguavbasedremotesensingandmachinelearning |