Monitoreo del desarrollo de cultivos de maíz mediante imágenes aéreas multiespectrales procesadas con inteligencia artificial
DOI:
https://doi.org/10.71112/5yx9sp43Palabras clave:
Teledetección;, agricultura de precisión;, Índice de vegetación;, segmentación de imágenes;, aprendizaje automático.Resumen
Distintos modelos de inteligencia artificial fueron evaluados para la segmentación de imágenes multiespectrales de cultivos de maíz obtenidas mediante dron, con el propósito de monitorear su desarrollo bajo condiciones de agricultura tradicional en El Salvador. Se aplicaron los modelos Binary Threshold, Random Forest, K-Means, DNN y CNN-MobileNet para discriminar áreas de maíz, malezas y suelo a partir imágenes con colores normalizados con base en el el índice GNDVI. Los resultados demostraron que Random Forest alcanzó la mayor precisión (0.95) y consistencia en la predicción de los índices de vegetación LAI y GNDVI, superando significativamente a los modelos de aprendizaje profundo, cuyos resultados se vieron limitados por la calidad de las máscaras generadas por K-Means. El método Binary Threshold también mostró desempeño aceptable por su sencillez y rapidez. Se concluyó que Random Forest ofreció resultados equilibrados entre precisión, costo y aplicabilidad práctica para el monitoreo de cultivos de subsistencia.
Descargas
Referencias
Bolfe, L., Parreiras, C., daSilva, L., Sano, E., Maranhão, G., Victoria, C, Del’Arco, I., & Eduardo Vicente, L. (2023). Mapping Agricultural Intensification in the Brazilian Savanna: A Machine Learning Approach Using Harmonized Data from Landsat Sentinel-2. ISPRS International Journal of Geo-Information. https://doi.org/10.3390/ijgi12070263 DOI: https://doi.org/10.3390/ijgi12070263
Buthelezi, S., Mutanga, O., Sibanda, M., Odindi, J., Clulow, A. D., Chimonyo, V. G. P., & Mabhaudhi, T. (2023). Assessing the Prospects of Remote Sensing Maize Leaf Area Index Using UAV-Derived Multi-Spectral Data in Smallholder Farms across the Growing Season. Remote Sensing, 15(6), 1597. https://doi.org/10.3390/rs15061597 DOI: https://doi.org/10.3390/rs15061597
Cedric, S., Hamilton, W. Y., Aworka, R., Thouakesseh, J., Kalala, F., Krichen, M., & Mberi, C. L. (2022). Crops yield prediction based on machine learning models: Case of West African countries. Smart Agricultural Technology. https://doi.org/10.1016/j.atech.2022.100049 DOI: https://doi.org/10.1016/j.atech.2022.100049
Chen, J., Liu, X., Du, S., Ma, Y., Liu, L. (2021). Effects of drought on the relationship between photosynthesis and chlorophyll fluorescence for maize. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/JSTARS.2021.3123111 DOI: https://doi.org/10.1109/JSTARS.2021.3123111
Chen, S., Liu, W., Feng, P., Ye, T., Ma, Y., & Zhang, Z. (2022). Improving Spatial Disaggregation of Crop Yield by Incorporating Machine Learning with Multisource Data: A Case Study of Chinese Maize Yield. Remote Sensing. https://doi.org/10.3390/rs14102340 DOI: https://doi.org/10.3390/rs14102340
Cheng, Q., Xu, H., Fei, S., Li, Z., & Chen, Z. (2022). Estimation of Maize LAI Using Ensemble Learning and UAV Multispectral Imagery under Different Water and Fertilizer Treatments. Agriculture. https://doi.org/10.3390/agriculture12081267 DOI: https://doi.org/10.3390/agriculture12081267
Danilevicz, M., Bayer, P., Boussaid, F., Bennamoun, M., & Edwards, D. (2021). Maize yield prediction at an early developmental stage using multispectral images and genotype data for preliminary hybrid selection. Remote Sensing, 13(19), 3976. https://doi.org/10.3390/rs13193976 DOI: https://doi.org/10.3390/rs13193976
Darwin, B., Dharmaraj, P., Prince, S., Popescu, D. E., & Hemanth, D. J. (2021). Recognition of bloom/yield in crop images using deep learning models for smart agriculture: A review. Agronomy, 11(4), 646. https://doi.org/10.3390/agronomy11040646 DOI: https://doi.org/10.3390/agronomy11040646
Deng, H., Zhang, W., Zheng, X., & Zhang, H. (2024). Crop Classification Combining Object-Oriented Method and Random Forest Model Using Unmanned Aerial Vehicle (UAV) Multispectral Image. Agriculture, 14(4), 548. https://doi.org/10.3390/agriculture14040548 DOI: https://doi.org/10.3390/agriculture14040548
DeSalvio, A., Adak, A., C. Murray, S., C. Wilde, S., & Isakeit, T. (2022). Phenomic data-facilitated rust and senescence prediction in maize using machine learning algorithms. Scientific Reports. https://doi.org/10.1038/s41598-022-11591-0 DOI: https://doi.org/10.21203/rs.3.rs-1108535/v1
Du, L., Yang, H., Song, X., Wei, N., Yu, C., Wang, W., & Zhao, Y. (2022). Estimating leaf area index of maize using UAV-based digital imagery and machine learning methods. Scientific Reports, 12, 15937. https://doi.org/10.1038/s41598-022-20299-0 DOI: https://doi.org/10.1038/s41598-022-20299-0
Guo, Y., Yin, G., Sun, H., Wang, H., Chen, S., Senthilnath, J., Wang, J., & Fu, Y. (2020). Scaling effects on chlorophyll content estimations with RGB camera mounted on a UAV platform using machine-learning methods. Sensors. https://doi.org/10.3390/s20185130 DOI: https://doi.org/10.3390/s20185130
Hernandez, A., Bushman, S., Johnson, P., Robbins, M. D., & Patten, K. (2024). Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach. Agronomy, 14(11), 2575. https://doi.org/10.3390/agronomy14112575 DOI: https://doi.org/10.3390/agronomy14112575
Huang, S., Tang, L., Hupy, J. P., Wang, Y., & Shao, G. (2021). A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forestry Research, 32, 1-12. https://doi.org/10.1007/s11676-020-01155-1 DOI: https://doi.org/10.1007/s11676-020-01155-1
Hunt, E. R., Jr., Hively, W. D., Fujikawa, S. J., Linden, D. S., Daughtry, C. S. T., & McCarty, G. W. (2010). Acquisition of NIR-green-blue digital photographs from unmanned aircraft for crop monitoring. Remote Sensing, 2(1), 290-305. https://doi.org/10.3390/rs2010290 DOI: https://doi.org/10.3390/rs2010290
Kim, N., Na, S., Park, C., Huh, M., Oh, J., Ha, K., Cho, J., & Lee, Y. (2020). An artificial intelligence approach to prediction of corn yields under extreme weather conditions using satellite and meteorological data. Applied Sciences, 10(11), 3785. https://doi.org/10.3390/app10113785 DOI: https://doi.org/10.3390/app10113785
Liu, J., Goering, C. E., & Tian, L. (2001). A neural network for setting target corn yields. Transactions of the American Society of Agricultural Engineers, 44(3), 705–710. https://doi.org/10.13031/2013.6097 DOI: https://doi.org/10.13031/2013.6097
Markov, N., Yorgov, D., Veleva, P., Petrova, A., & Atanasova, S. (2025). Assessing the applicability of drone-mounted multispectral camera measurements to characterize wheat status during the vegetation. AGRICULTURAL SCIENCE AND TECHNOLOGY, 17(1), 81-86. DOI: https://doi.org/10.15547/ast.2025.01.010
Marques, A. P., Prado, L., Garcia, D. E., Nunes, W., Cordeiro, D., Ribeiro, L. P., Silva, C. A. d., Capristo, G., Li, J., Rojo, F. H., Marcato, J. & Pistori, H. (2020). A random forest ranking approach to predict yield in maize with UAV-based vegetation spectral indices. Computers and Electronics in Agriculture. https://doi.org/10.1016/j.compag.2020.105791 DOI: https://doi.org/10.1016/j.compag.2020.105791
Mndela, Y., Ndou, N., & Nyamugama, A. (2023). Irrigation scheduling for small-scale crops based on crop water content patterns derived from UAV multispectral imagery. Sustainability, 15(15), 12034. https://doi.org/10.3390/su151512034 DOI: https://doi.org/10.3390/su151512034
Mohanty, S., Ghosh, H., Rahat, I. S., & Reddy, C. V. R. (2023). Advanced deep learning models for corn leaf disease classification: A field study in Bangladesh. Engineering Proceedings, 3(5), 59–69. https://doi.org/10.3390/engproc2023059069 DOI: https://doi.org/10.3390/engproc2023059069
Nan, F., Song, Y., Yu, X., Nie, C., Liu, Y., Bai, Y., Zou, D., Wang, C., Yin, D., Yang, W., & Jin, X. (2023). A novel method for maize leaf disease classification using the RGB-D post-segmentation image data. Frontiers in Plant Science. https://doi.org/10.3389/fpls.2023.1268015 DOI: https://doi.org/10.3389/fpls.2023.1268015
Nowakowski, A., Mrziglod, J., Spiller, D., Bonifacio, R., Ferrari, I., Mathieu, P. P., Garcia-Herranz, M., & Kim, D.-H. (2021). Crop type mapping by using transfer learning. International Journal of Applied Earth Observations and Geoinformation, 101, 102313. https://doi.org/10.1016/j.jag.2021.102313 DOI: https://doi.org/10.1016/j.jag.2021.102313
Pan, S., Qiao, J., Wang, R., Yu, H., Wang, C., Taylor, K., & Pan, H. (2022). Intelligent diagnosis of northern corn leaf blight with deep learning model. Journal of Integrative Agriculture, 21(1), 637–707. https://doi.org/10.1016/S2095-3119(21)63707-3 DOI: https://doi.org/10.1016/S2095-3119(21)63707-3
Radia, B., Assia, B., Narimene, S. R, & Ali, G. (2024). Evaluation of the Biochemical and Antioxidant Behaviour of Four Species Chenopodium quinoa Willd, Zea mays L., Triticosecale wittmack and Hordeum vulgare L. Effected by Oxidative Stress Caused by Water Stress. Basrah Journal of Agricultural Sciences, 37(2), 113–123. https://doi.org/10.37077/25200860.2024.37.2.10 DOI: https://doi.org/10.37077/25200860.2024.37.2.10
Radócz, L., Juhász, C., Tamás, A., Illés, Á., Ragán, P., & Radócz, L. (2024). Multispectral UAV-Based Disease Identification Using Vegetation Indices for Maize Hybrids. Agriculture, 14(11), 2002. https://doi.org/10.3390/agriculture14112002 DOI: https://doi.org/10.3390/agriculture14112002
Savitha, C., & Talari, R. (2025). Evaluating the performance of random forest, support vector machine, gradient tree boost, and CART for improved crop-type monitoring using greenest pixel composite in Google Earth Engine. Environmental Monitoring and Assessment, 197(4), 1-25. DOI: https://doi.org/10.1007/s10661-025-13880-3
Shao, G., Han, W., Zhang, H., Zhang, L., Wang, Y., & Zhang, Y. (2022). Prediction of maize crop coefficient from UAV multisensor remote sensing using machine learning methods. Agricultural Water Management. https://doi.org/10.1016/j.agwat.2022.108064 DOI: https://doi.org/10.1016/j.agwat.2022.108064
Shuai, G., & Basso, B. (2022). Subfield maize yield prediction improves when in-season crop water deficit is included in remote sensing imagery-based models. Remote Sensing of Environment, 268, 112938. https://doi.org/10.1016/j.rse.2022.112938 DOI: https://doi.org/10.1016/j.rse.2022.112938
Tseng, H., Yang, M., Saminathan, R., Hsu, Y., Yang, C., & Wu, D. (2022). Rice seedling detection in UAV images using transfer learning and machine learning. Remote Sensing, 14(12), 2837. https://doi.org/10.3390/rs14122837 DOI: https://doi.org/10.3390/rs14122837
Ubilava, D. & Abdolrahimi, M. (2019). The el niño impact on maize yields is amplified in lower income teleconnected countries. Environmental Research Letters. https://doi.org/10.1088/1748-9326/ab0cd0 DOI: https://doi.org/10.1088/1748-9326/ab0cd0
Xie, Y., Nhu, A. N., Song, X. P., Jia, X., Skakun, S., Li, H., & Wang, Z. (2025). Accounting for spatial variability with geo-aware random forest: A case study for US major crop mapping. Remote Sensing of Environment, 319, 114585. DOI: https://doi.org/10.1016/j.rse.2024.114585
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Carlos Roberto Martínez Martínez (Autor/a)
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
