Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis

The rapid development of unmanned aerial vehicles (UAVs) and imaging technologies has opened new research avenues for precision agriculture, particularly in the context of plant phenotyping where their utilization has been intensive over the last decade. This review focuses on the interplay of machi...

Descripción completa

Detalles Bibliográficos
Autores principales: Ndour, Adama, Blasch, Gerald, Valente, João, Bisrat Gebrekidan, Sida, Tesfaye Shiferaw
Formato: Journal Article
Lenguaje:Inglés
Publicado: IOP Publishing 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/175812
_version_ 1855541381535105024
author Ndour, Adama
Blasch, Gerald
Valente, João
Bisrat Gebrekidan
Sida, Tesfaye Shiferaw
author_browse Bisrat Gebrekidan
Blasch, Gerald
Ndour, Adama
Sida, Tesfaye Shiferaw
Valente, João
author_facet Ndour, Adama
Blasch, Gerald
Valente, João
Bisrat Gebrekidan
Sida, Tesfaye Shiferaw
author_sort Ndour, Adama
collection Repository of Agricultural Research Outputs (CGSpace)
description The rapid development of unmanned aerial vehicles (UAVs) and imaging technologies has opened new research avenues for precision agriculture, particularly in the context of plant phenotyping where their utilization has been intensive over the last decade. This review focuses on the interplay of machine learning, UAV-based multispectral imagery and plant phenotyping. We systematically reviewed the current literature to catalog and assess the variety of machine learning methodologies applied to multispectral UAV data for the prediction of key phenotypic traits such as biomass, yield and nitrogen. In this study, we conducted a comprehensive meta-analysis to analyze the relationship between the machine learning model performance and variables such crop type, the type of aerial phenotyping platform, the phenological stage, etc A trait-based comparison of the efficiency and popularity of machine learning algorithms was conducted. Our findings showed that the multiple linear regression is the most effective model in predicting biomass while artificial neural networks showed up as the top performing algorithm in determining nitrogen content. Random forest was identified as the most popular algorithm in estimating those key phenotypic traits. The best combinations of UAV and sensors that significantly enhance model performance for predicting critical agronomic traits were thoroughly examined. Results highlighted, for instance, that pairing the DJI 2 UAV with Micasense sensor led to better machine learning performance in predicting biomass while Parrot Sequoia was identified as the most efficient multispectral sensor to phenotype leaf nitrogen content. Ultimately, the challenges and future research prospects of UAV-based predictions related to the phenotype data variability, the choice of UAV platform, the model complexity and interpretability are discussed. Since previous studies described the broad applications of UAVs and sensors in agriculture, this review aimed to provide a targeted, systematic and quantitative analysis of optimal use of machine learning algorithms and UAV-based multispectral imagery for plant phenotyping.
format Journal Article
id CGSpace175812
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher IOP Publishing
publisherStr IOP Publishing
record_format dspace
spelling CGSpace1758122025-10-26T12:56:54Z Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis Ndour, Adama Blasch, Gerald Valente, João Bisrat Gebrekidan Sida, Tesfaye Shiferaw unmanned aerial vehicles field crops phenotyping precision agriculture artificial intelligence forecasting modelling The rapid development of unmanned aerial vehicles (UAVs) and imaging technologies has opened new research avenues for precision agriculture, particularly in the context of plant phenotyping where their utilization has been intensive over the last decade. This review focuses on the interplay of machine learning, UAV-based multispectral imagery and plant phenotyping. We systematically reviewed the current literature to catalog and assess the variety of machine learning methodologies applied to multispectral UAV data for the prediction of key phenotypic traits such as biomass, yield and nitrogen. In this study, we conducted a comprehensive meta-analysis to analyze the relationship between the machine learning model performance and variables such crop type, the type of aerial phenotyping platform, the phenological stage, etc A trait-based comparison of the efficiency and popularity of machine learning algorithms was conducted. Our findings showed that the multiple linear regression is the most effective model in predicting biomass while artificial neural networks showed up as the top performing algorithm in determining nitrogen content. Random forest was identified as the most popular algorithm in estimating those key phenotypic traits. The best combinations of UAV and sensors that significantly enhance model performance for predicting critical agronomic traits were thoroughly examined. Results highlighted, for instance, that pairing the DJI 2 UAV with Micasense sensor led to better machine learning performance in predicting biomass while Parrot Sequoia was identified as the most efficient multispectral sensor to phenotype leaf nitrogen content. Ultimately, the challenges and future research prospects of UAV-based predictions related to the phenotype data variability, the choice of UAV platform, the model complexity and interpretability are discussed. Since previous studies described the broad applications of UAVs and sensors in agriculture, this review aimed to provide a targeted, systematic and quantitative analysis of optimal use of machine learning algorithms and UAV-based multispectral imagery for plant phenotyping. 2025-07-01 2025-07-25T17:17:50Z 2025-07-25T17:17:50Z Journal Article https://hdl.handle.net/10568/175812 en Open Access application/pdf IOP Publishing Ndour, A., Blasch, G., Valente, J., Gebrekidan, B. H., & Sida, T. S. (2025). Optimal Machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis. Environmental Research Communications, 7(7), art.072002. https://doi.org/10.1088/2515-7620/ade84f
spellingShingle unmanned aerial vehicles
field crops
phenotyping
precision agriculture
artificial intelligence
forecasting
modelling
Ndour, Adama
Blasch, Gerald
Valente, João
Bisrat Gebrekidan
Sida, Tesfaye Shiferaw
Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title_full Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title_fullStr Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title_full_unstemmed Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title_short Optimal machine learning algorithms and UAV multispectral imagery for crop phenotypic trait estimation: a comprehensive review and meta-analysis
title_sort optimal machine learning algorithms and uav multispectral imagery for crop phenotypic trait estimation a comprehensive review and meta analysis
topic unmanned aerial vehicles
field crops
phenotyping
precision agriculture
artificial intelligence
forecasting
modelling
url https://hdl.handle.net/10568/175812
work_keys_str_mv AT ndouradama optimalmachinelearningalgorithmsanduavmultispectralimageryforcropphenotypictraitestimationacomprehensivereviewandmetaanalysis
AT blaschgerald optimalmachinelearningalgorithmsanduavmultispectralimageryforcropphenotypictraitestimationacomprehensivereviewandmetaanalysis
AT valentejoao optimalmachinelearningalgorithmsanduavmultispectralimageryforcropphenotypictraitestimationacomprehensivereviewandmetaanalysis
AT bisratgebrekidan optimalmachinelearningalgorithmsanduavmultispectralimageryforcropphenotypictraitestimationacomprehensivereviewandmetaanalysis
AT sidatesfayeshiferaw optimalmachinelearningalgorithmsanduavmultispectralimageryforcropphenotypictraitestimationacomprehensivereviewandmetaanalysis