High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data
Autori
Ranđelović, PredragĐorđević, Vuk
Miladinović, Jegor
Prodanović, Slaven
Ćeran, Marina
Vollmann, Johann
Članak u časopisu (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
Biomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index... (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained.
Ključne reči:
high-throughput phenotyping / biomass / soybean / machine learning / UAVIzvor:
Plant Methods, 2023, 19Izdavač:
- Springer Nature
Finansiranje / projekti:
- Ministarstvo nauke, tehnološkog razvoja i inovacija Republike Srbije, institucionalno finansiranje - 200032 (Naučni institut za ratarstvo i povrtarstvo, Novi Sad) (RS-MESTD-inst-2020-200032)
- ECOBREED (Increasing the efficiency and competitiveness of organic crop breeding) (EU-H2020-771367)
Kolekcije
Institucija/grupa
FiVeRTY - JOUR AU - Ranđelović, Predrag AU - Đorđević, Vuk AU - Miladinović, Jegor AU - Prodanović, Slaven AU - Ćeran, Marina AU - Vollmann, Johann PY - 2023 UR - http://fiver.ifvcns.rs/handle/123456789/4064 AB - Biomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained. PB - Springer Nature T2 - Plant Methods T1 - High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data VL - 19 DO - 10.1186/s13007-023-01054-6 ER -
@article{ author = "Ranđelović, Predrag and Đorđević, Vuk and Miladinović, Jegor and Prodanović, Slaven and Ćeran, Marina and Vollmann, Johann", year = "2023", abstract = "Biomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained.", publisher = "Springer Nature", journal = "Plant Methods", title = "High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data", volume = "19", doi = "10.1186/s13007-023-01054-6" }
Ranđelović, P., Đorđević, V., Miladinović, J., Prodanović, S., Ćeran, M.,& Vollmann, J.. (2023). High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data. in Plant Methods Springer Nature., 19. https://doi.org/10.1186/s13007-023-01054-6
Ranđelović P, Đorđević V, Miladinović J, Prodanović S, Ćeran M, Vollmann J. High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data. in Plant Methods. 2023;19. doi:10.1186/s13007-023-01054-6 .
Ranđelović, Predrag, Đorđević, Vuk, Miladinović, Jegor, Prodanović, Slaven, Ćeran, Marina, Vollmann, Johann, "High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data" in Plant Methods, 19 (2023), https://doi.org/10.1186/s13007-023-01054-6 . .