Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Published
Classification of maize hybrids using UAV-based multispectral remote sensing and machine learning algorithms
Clasificación de híbridos de maíz utilizando detección remota multiespectral basada en UAV y algoritmos de aprendizaje automático
DOI:
https://doi.org/10.15446/agron.colomb.v43n1.118781Keywords:
artificial neural networks, spectral bands, spectral curve, vegetation indices, machine learning classification, UAV-based image analysis (en)redes neuronales artificiales, bandas espectrales, curva espectral, índices de vegetación, clasificación mediante aprendizaje automático, análisis de imágenes basado en UAV (es)
Downloads
Novel methodologies for phenotypic evaluation in maize have been developed through the integration of advanced sensing technologies and machine learning algorithms. The aim of this study was to identify the most accurate machine learning algorithm for the classification of maize hybrids and to determine the optimal input data to enhance model performance. Seven maize hybrids were used in the experiment. After 60 d of crop emergence, the remotely piloted aircraft SenseFly® eBee RTK was used to obtain reflectance values at the following spectral bands (SB): blue (475 nm, B_475), green (550 nm, G_550), red (660 nm, R_660), red edge (735 nm, RE_735) and near-infrared (790 nm, NIR_790). Following the acquisition of spectral band (SB) data, vegetation indices (VIs) were calculated. The resulting dataset was subsequently analyzed using machine learning techniques, evaluating six algorithms: artificial neural networks (ANN), J48 decision trees (J48), REPTree (DT), random forest (RF), support vector machine (SVM) and logistic regression (LR) as the baseline model. Three accuracy metrics were used to evaluate the performance of the algorithms in classifying maize hybrids: correct classifications (CC), Kappa coefficient, and F-score. Among the algorithms tested, ANN showed the highest performance in all three metrics, proving its superiority and potential for real-world applications. Although all three input configurations enhanced classification accuracy for ANN algorithm, the optimal approach is to use only SB as input due to reduced data processing time and increased simplicity.
Se han desarrollado nuevas metodologías para la evaluación fenotípica en maíz mediante la integración de tecnologías de detección avanzadas y algoritmos de aprendizaje automatizado. El objetivo de este trabajo fue identificar el algoritmo de aprendizaje automático más preciso para la clasificación de híbridos de maíz y determinar los datos de entrada que mejoran el rendimiento del modelo. Se utilizaron siete híbridos de maíz. A los 60 d de emergencia del cultivo se utilizó la aeronave pilotada remotamente SenseFly® eBee RTK para obtener la reflectancia en las siguientes bandas espectrales (BE): azul (475 nm, B_475), verde (550 nm, G_550), rojo (660 nm, R_660), borde rojo (735 nm, RE_735) y NIR (790 nm, NIR_790). Luego de la adquisición de datos de la banda espectral (BE), se calcularon los índices de vegetación (Vis). El conjunto de datos resultante se analizó posteriormente utilizando técnicas de aprendizaje automático, evaluando seis algoritmos: redes neuronales artificiales (RNA), árboles de decisión J48 (J48), REPTree (DT), bosque aleatorio (BA), máquina de vectores de soporte (MVS) y regresión logística (RL) como enfoque de referencia. Se utilizaron tres métricas de precisión para evaluar el desempeño de los algoritmos en la clasificación de híbridos de maíz: clasificaciones correctas (CC), coeficiente Kappa y F-score. Entre los algoritmos probados, el algoritmo de ANN se destacó con el mayor desempeño en las tres métricas, demostrando su superioridad y potencial para aplicaciones reales en clasificación. Aunque las tres configuraciones de entrada mejoraron la precisión de clasificación para el algoritmo RNA, el enfoque óptimo es utilizar solo las BE como entrada debido al menor tiempo de procesamiento de datos y la mayor simplicidad.
References
Al Snousy, M. B., El-Deeb, H. M., Badran, K., & Al Khlil, I. A. (2011). Suite of decision tree-based classification algorithms on cancer gene expression data. Egyptian Informatics Journal, 12(1), 73–82. https://www.sciencedirect.com/science/article/pii/S1110866511000223 DOI: https://doi.org/10.1016/j.eij.2011.04.003
Andrade, S. M., Teodoro, L. P. R., Baio, F. H. R., Campos, C. N. S., Roque, C. G., Silva Junior, C. A., Coradi, P. C., & Teodoro, P. E. (2021). High-throughput phenotyping of soybean genotypes under base saturation stress conditions. Journal of Agronomy and Crop Science, 207(5), 814–822. https://doi.org/10.1111/jac.12513 DOI: https://doi.org/10.1111/jac.12513
Atta, B. M., Saleem, M., Bilal, M., ul Rehman, A., & Fayyaz, M. (2023). Early detection of stripe rust infection in wheat using light-induced fluorescence spectroscopy. Photochemical & Photobiological Sciences, 22, 115–134. https://doi.org/10.1007/s43630-022-00303-2 DOI: https://doi.org/10.1007/s43630-022-00303-2
Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011 DOI: https://doi.org/10.1016/j.isprsjprs.2016.01.011
Das Choudhury, S., Samal, A., & Awada, T. (2019). Leveraging image analysis for high-throughput plant phenotyping. Frontiers in Plant Science, 10, Article 508. https://doi.org/10.3389/fpls.2019.00508 DOI: https://doi.org/10.3389/fpls.2019.00508
Dawson, T. P., & Curran, P. J. (1998). A new technique for interpolating the reflectance red edge position. International Journal of Remote Sensing, 19(11), 2133–2139. https://doi.org/10.1080/014311698214910 DOI: https://doi.org/10.1080/014311698214910
Dobbels, A. A., & Lorenz, A. J. (2019). Soybean iron deficiency chlorosis high-throughput phenotyping using an unmanned aircraft system. Plant Methods, 15, Article 97. https://doi.org/10.1186/s13007-019-0478-9 DOI: https://doi.org/10.1186/s13007-019-0478-9
Egmont-Petersen, M., de Ridder, D., & Handels, H. (2002). Image processing with neural networks – A review. Pattern Recognition, 35(10), 2279–2301. https://doi.org/10.1016/S0031-3203(01)00178-9 DOI: https://doi.org/10.1016/S0031-3203(01)00178-9
Gava, R., Santana, D. C., Cotrim, M. F., Rossi, F. S., Teodoro, L. P. R., Silva Junior, C. A., & Teodoro, P. E. (2022). Soybean cultivars identification using remotely sensed image and machine learning models. Sustainability, 14(12), Article 7125. https://doi.org/10.3390/su14127125 DOI: https://doi.org/10.3390/su14127125
Gholizadeh, A., Mišurec, J., Kopačková, V., Mielke, C., & Rogass, C. (2016). Assessment of red-edge position extraction techniques: A case study for Norway spruce forests using Hymap and simulated Sentinel-2 data. Forests, 7(10), Article 226. https://doi.org/10.3390/f7100226 DOI: https://doi.org/10.3390/f7100226
Hennessy, A., Clarke, K., & Lewis, M. (2020). Hyperspectral classification of plants: A review of waveband selection generalisability. Remote Sensing, 12(1), Article 113. https://doi.org/10.3390/rs12010113 DOI: https://doi.org/10.3390/rs12010113
Herzig, P., Borrmann, P., Knauer, U., Klück, H. C., Kilias, D., Seiffert, U., Pillen, K., & Maurer, A. (2021). Evaluation of RGB and multispectral unmanned aerial vehicle (UAV) imagery for high-throughput phenotyping and yield prediction in barley breeding. Remote Sensing, 13(14), Article 2670. https://doi.org/10.3390/rs13142670 DOI: https://doi.org/10.3390/rs13142670
Iqbal, A., Khan, R. S., Khan, M. A., Gul, K., Jalil, F., Shah, D. A., Rahman, H., & Ahmed, T. (2021). Genetic engineering approaches for enhanced insect pest resistance in sugarcane. Molecular Biotechnology, 63, 557–568. https://doi.org/10.1007/s12033-021-00328-5 DOI: https://doi.org/10.1007/s12033-021-00328-5
Kar, S., Purbey, V. K., Suradhaniwar, S., Korbu, L. B., Kholová, J., Durbha, S. S., Adinarayana, J., & Vadez, V. (2021). An ensemble machine learning approach for determination of the optimum sampling time for evapotranspiration assessment from highthroughput phenotyping data. Computers and Electronics in Agriculture, 182, Article 105992. https://doi.org/10.1016/j.compag.2021.105992 DOI: https://doi.org/10.1016/j.compag.2021.105992
Li, Y., Xin, G., Wei, M., Shi, Q., Yang, F., & Wang, X. (2017). Carbohydrate accumulation and sucrose metabolism responses in tomato seedling leaves when subjected to different light qualities. Scientia Horticulturae, 225, 490–497. https://doi.org/10.1016/j.scienta.2017.07.053 DOI: https://doi.org/10.1016/j.scienta.2017.07.053
Liu, G., Yang, Y., Guo, X., Liu, W., Xie, R., Ming, B., Xue, J., Wang, K., Li, S., & Hou, P. (2023). A global analysis of dry matter accumulation and allocation for maize yield breakthrough from 1.0 to 25.0 Mg ha⁻¹. Resources, Conservation and Recycling, 188, Article 106656. https://doi.org/10.1016/j.resconrec.2022.106656 DOI: https://doi.org/10.1016/j.resconrec.2022.106656
Lu, Z., Meng, Y., Fan, H., Lu, J., Zhong, X., Ou, Y., Mo, H., & Zhou, L. (2021). Luminescent properties of Mn⁴⁺-doped LaTiSbO₆ deep-red-emitting phosphor for plant growth LEDs. Journal of Luminescence, 236, Article 118100. https://doi.org/10.1016/j.jlumin.2021.118100 DOI: https://doi.org/10.1016/j.jlumin.2021.118100
Maciel Junior, I. C., Dallacort, R., Boechat, C. L., Teodoro, P. E., Teodoro, L. P. R., Rossi, F. S., Oliveira-Júnior, J. F., Della-Silva, J. L., Baio, F. H. R., Lima, M., & Silva Junior, C. A. (2024). Maize crop detection through geo-object-oriented analysis using orbital multi-sensors on the Google Earth engine platform. AgriEngineering, 6(1), 491–508. https://doi.org/10.3390/agriengineering6010030 DOI: https://doi.org/10.3390/agriengineering6010030
Nalepa, J., & Kawulok, M. (2019). Selecting training sets for support vector machines: A review. Artificial Intelligence Review, 52, 857–900. https://doi.org/10.1007/s10462-017-9611-1 DOI: https://doi.org/10.1007/s10462-017-9611-1
Niazian, M., & Niedbała, G. (2020). Machine learning for plant breeding and biotechnology. Agriculture, 10(10), Article 436. https://doi.org/10.3390/agriculture10100436 DOI: https://doi.org/10.3390/agriculture10100436
Nishio, J. N. (2000). Why are higher plants green? Evolution of the higher plant photosynthetic pigment complement. Plant, Cell & Environment, 23(6), 539–548. https://doi.org/10.1046/j.1365-3040.2000.00563.x DOI: https://doi.org/10.1046/j.1365-3040.2000.00563.x
Oliveira, J. F., Alcântara, J. F., Santana, D. C., Teodoro, L. P. R., Baio, F. H. R., Coradi, P. C., Silva Junior, C. A., & Teodoro, P. E. (2023). Spectral variables as criteria for selection of soybean genotypes at different vegetative stages. Remote Sensing Applications: Society and Environment, 32, Article 101026. https://doi.org/10.1016/j.rsase.2023.101026 DOI: https://doi.org/10.1016/j.rsase.2023.101026
Oliveira, J. L. G., Santana, D. C., Oliveira, I. C., Gava, R., Baio, F. H. R., Silva Junior, C. A.,Teodoro, L. P. R., Teodoro, P. E., & Oliveira, J. T. (2025). Classification of irrigation management practices in maize hybrids using multispectral sensors and machine learning techniques. Engenharia Agrícola, 45, Article e20240164. https://doi.org/10.1590/1809-4430-Eng.Agric.v45e20240164/2025 DOI: https://doi.org/10.1590/1809-4430-eng.agric.v45e20240164/2025
Osco, L. P., Marcato Junior, J., Ramos, A. P. M., Furuya, D. E. G., Santana, D. C., Teodoro, L. P. R., Gonçalves, W. N., Baio, F. H. R., Pistori, H., & Silva Junior, C. A. (2020). Leaf nitrogen concentration and plant height prediction for maize using UAV-based multispectral imagery and machine learning techniques. Remote Sensing, 12(19), Article 3237. https://doi.org/10.3390/rs12193237 DOI: https://doi.org/10.3390/rs12193237
Pantaleão, A. A., Teodoro, L. P. R., Argentel Martínez, L., González Aguilera, J., Campos, C. N. S., Baio, F. H. R., Silva Júnior, C. A., & Teodoro, P. E. (2022). Soybean base saturation stress: Selecting populations for multiple traits using multivariate statistics. Journal of Agronomy and Crop Science, 208(2), 168–177. https://doi.org/10.1111/jac.12564 DOI: https://doi.org/10.1111/jac.12564
Qi, M., & Zhang, G. P. (2001). An investigation of model selection criteria for neural network time series forecasting. European Journal of Operational Research, 132(3), 666–680. https://doi.org/10.1016/S0377-2217(00)00171-5 DOI: https://doi.org/10.1016/S0377-2217(00)00171-5
Quinlan, J. R. (1993). C4.5: Programs for machine learning. Morgan Kaufmann. https://dl.acm.org/doi/10.5555/583200
Ramos, A. P. M., Osco, L. P., Furuya, D. E. G., Gonçalves, W. N., Santana, D. C., Teodoro, L. P. R., Silva Junior, C. A., Capristo-Silva, G. F., Li, J., & Baio, F. H. R. (2020). A random forest ranking approach to predict yield in maize with UAV-based vegetation spectral indices. Computers and Electronics in Agriculture, 178, Article 105791. https://doi.org/10.1016/j.compag.2020.105791 DOI: https://doi.org/10.1016/j.compag.2020.105791
R Core Team. (2013). R: A language and environment for statistical computing. R Foundation for Statistical Computing. https://cran.r-project.org/doc/manuals/r-release/fullrefman.pdf
Rivero, R. M., Mittler, R., Blumwald, E., & Zandalinas, S. I. (2022). Developing climate-resilient crops: Improving plant tolerance to stress combination. The Plant Journal, 109(2), 373–389. https://doi.org/10.1111/tpj.15483 DOI: https://doi.org/10.1111/tpj.15483
Santana, D. C., Cunha, M. P. O., Santos, R. G., Cotrim, M. F., Teodoro, L. P. R., Silva Junior, C. A., Baio, F. H. R., & Teodoro, P. E. (2022). High-throughput phenotyping allows the selection of soybean genotypes for earliness and high grain yield. Plant Methods, 18, Article 13. https://doi.org/10.1186/s13007-022-00848-4 DOI: https://doi.org/10.1186/s13007-022-00848-4
Santana, D. C., Santos, R. G., Teodoro, L. P. R., Silva Junior, C. A., Baio, F. H. R., Coradi, P. C., & Teodoro, P. E. (2022). Structural equation modelling and factor analysis of the relationship between agronomic traits and vegetation indices in corn. Euphytica, 218, Article 44. https://doi.org/10.1007/s10681-022-02997-y DOI: https://doi.org/10.1007/s10681-022-02997-y
Santana, D. C., Teixeira Filho, M. C. M., Silva, M. R., Chagas, P. H. M., Oliveira, J. L. G., Baio, F. H. R., Campos, C. N. S., Teodoro, L. P. R., Silva Junior, C. A., Teodoro, P. E., & Shiratsuchi, L. S. (2023). Machine learning in the classification of soybean genotypes for primary macronutrients’ content using UAV–multispectral sensor. Remote Sensing, 15(5), Article 1457. https://doi.org/10.3390/rs15051457 DOI: https://doi.org/10.3390/rs15051457
Santana, D. C., Teodoro, L. P. R., Baio, F. H. R., Santos, R. G., Coradi, P. C., Biduski, B., Silva Junior, C. A., Teodoro, P. E., & Shiratsuchi, L. S. (2023). Classification of soybean genotypes for industrial traits using UAV multispectral imagery and machine learning. Remote Sensing Applications: Society and Environment, 29, Article 100919. https://doi.org/10.1016/j.rsase.2023.100919 DOI: https://doi.org/10.1016/j.rsase.2023.100919
Santos, H. G., Jacomine, P. K. T., Anjos, L. H. C., Oliveira, V. A., Lumbreras, J. F., Coelho, M. R., Almeida, J. A., Araujo Filho, J. C., Oliveira, J. B., & Cunha, T. J. F. (2018). Sistema brasileiro de classificação de solos (5th ed.). Embrapa. https://www.infoteca.cnptia.embrapa.br/infoteca/handle/doc/1094003
Santos, T. T., & Yassitepe, J. E. C. T. (2014). Fenotipagem de plantas em larga escala: um novo campo de aplicação para a visão computacional na agricultura. In S. M. F. S. Massruhá, M. A. A. Leite, A. Luchiari Junior, & L. A. S. Romani (Eds.), Tecnologias da informação e comunicação e suas relações com a agricultura (pp. 85–100). Embrapa. https://www.alice.cnptia.embrapa.br/alice/bitstream/doc/1010708/1/capitulo0508814.pdf
Scott, A. J., & Knott, M. (1974). Cluster analysis method for grouping means in the analysis of variance. Biometrics, 30(3), 507–512. https://doi.org/10.2307/2529204 DOI: https://doi.org/10.2307/2529204
Shi, L., Han, Y. J., Wang, H., Shi, D., Geng, X., & Zhang, Z. (2019). High-efficiency and thermally stable far-red emission of Mn⁴⁺ in double cubic perovskite Sr₉Y₂W₄O₂₄ for plant cultivation. Journal of Luminescence, 208, 307–312. https://doi.org/10.1016/j.jlumin.2018.12.065 DOI: https://doi.org/10.1016/j.jlumin.2018.12.065
Silva, V. S., Silva, C. A., Mohan, M., Cardil, A., Rex, F. E., Loureiro, G. H., Almeida, D. R. A., Broadbent, E. N., Gorgens, E. B., Dalla Corte, A. P., Silva, E. A., Valbuena, & Klauberg, C. (2020). Combined impact of sample size and modeling approaches for predicting stem volume in Eucalyptus spp. forest plantations using field and LiDAR data. Remote Sensing, 12(9), Article 1438. https://doi.org/10.3390/rs12091438 DOI: https://doi.org/10.3390/rs12091438
Štepanovský, M., Ibrová, A., Buk, Z., & Velemínská, J. (2017). Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods. Forensic Science International, 279, 72–82. https://doi.org/10.1016/j.forsciint.2017.08.005 DOI: https://doi.org/10.1016/j.forsciint.2017.08.005
Swarup, S., Cargill, E. J., Crosby, K., Flagel, L., Kniskern, J., & Glenn, K. C. (2021). Genetic diversity is indispensable for plant breeding to improve crops. Crop Science, 61(2), 839–852. https://doi.org/10.1002/csc2.20377 DOI: https://doi.org/10.1002/csc2.20377
Taiz, L., Zeiger, E., Møller, I. M., & Murphy, A. (2017). Fisiologia e desenvolvimento vegetal (6th ed.). Artmed Editora.
Teodoro, P. E., Teodoro, L. P. R., Baio, F. H. R., Silva Junior, C. A., Santos, R. G., Ramos, A. P. M., Pinheiro, M. M. F., Osco, L. P., Gonçalves, W. N., Carneiro, A. M., Pistori, H., & Shiratsuchi, L. S. (2021). Predicting days to maturity, plant height, and grain yield in soybean: A machine and deep learning approach using multispectral data. Remote Sensing, 13(22), Article 4632. https://doi.org/10.3390/rs13224632 DOI: https://doi.org/10.3390/rs13224632
Van Eeuwijk, F. A., Bustos-Korts, D., Millet, E. J., Boer, M. P., Kruijer, W., Thompson, A., Malosetti, M., Iwata, H., Quiroz, R., Kuppe, C., Muller, O., Blazakis, K. N., Yu, K., Tardieu, F., & Chapman, S. C. (2019). Modelling strategies for assessing and increasing the effectiveness of new phenotyping techniques in plant breeding. Plant Science, 282, 23–39. https://doi.org/10.1016/j.plantsci.2018.06.018 DOI: https://doi.org/10.1016/j.plantsci.2018.06.018
Vidyarthi, V. K., Jain, A., & Chourasiya, S. (2020). Modeling rainfall-runoff process using artificial neural network with emphasis on parameter sensitivity. Modeling Earth Systems and Environment, 6, 2177–2188. https://doi.org/10.1007/s40808-020-00833-7 DOI: https://doi.org/10.1007/s40808-020-00833-7
Wu, Q., Su, N., Shen, W., & Cui, J. (2014). Analyzing photosynthetic activity and growth of Solanum lycopersicum seedlings exposed to different light qualities. Acta Physiologiae Plantarum, 36, 1411–1420. https://doi.org/10.1007/s11738-014-1519-7 DOI: https://doi.org/10.1007/s11738-014-1519-7
Zafar, M. M., Mustafa, G., Shoukat, F., Idrees, A., Ali, A., Sharif, F., Shakeel, A., Mo, H., Youlu, Y., Ali, Q., Razzaq, A., Ren, M., & Li, F. (2022). Heterologous expression of cry3Bb1 and cry3 genes for enhanced resistance against insect pests in cotton. Scientific Reports, 12, Article 10878. https://doi.org/10.1038/s41598-022-13295-x DOI: https://doi.org/10.1038/s41598-022-13295-x
Zahir, S. A. D. M., Omar, A. F., Jamlos, M. F., Azmi, M. A. M., & Muncan, J. (2022). A review of visible and near-infrared (Vis-NIR) application in plant stress detection. Sensors and Actuators A: Physical, 338, Article 113468. https://doi.org/10.1016/j.sna.2022.113468 DOI: https://doi.org/10.1016/j.sna.2022.113468
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2025 Agronomía Colombiana
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
© Centro Editorial de la Facultad de Ciencias Agrarias, Universidad Nacional de Colombia
Reproduction and quotation of material appearing in the journal is authorized provided the following are explicitly indicated: journal name, author(s) name, year, volume, issue and pages of the source. The ideas and observations recorded by the authors are their own and do not necessarily represent the views and policies of the Universidad Nacional de Colombia. Mention of products or commercial firms in the journal does not constitute a recommendation or endorsement on the part of the Universidad Nacional de Colombia; furthermore, the use of such products should comply with the product label recommendations.
The Creative Commons license used by Agronomia Colombiana journal is: Attribution - NonCommercial - ShareAlike (by-nc-sa)
Agronomia Colombiana by Centro Editorial of Facultad de Ciencias Agrarias, Universidad Nacional de Colombia is licensed under a Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional License.
Creado a partir de la obra en http://revistas.unal.edu.co/index.php/agrocol/.
