Utilización de índices de vegetación satelitales para predecir niveles de rendimiento de Vicia villosa Roth

Otros responsables
Fecha
2025-06-01
Editorial
Sociedad Argentina de Informática e Investigación Operativa
Revista
SADIO Electronic Journal of Informatic and Operation Research
Título del libro
Nombre del evento
Fecha del evento
Institución organizadora
ISSN
1514-6774
eISSN
ISBN
Idioma
Español
Tipo del evento
Clasificación temática
Palabras clave
Resumen
En este trabajo se combinan las imágenes satelitales, los algoritmos de aprendizaje de máquina y las mediciones de campo para analizar si es posible generar un modelo de predicción del rendimiento de la leguminosa Vicia villosa Roth (VV) antes de su cosecha. En un estudio previo, se empleó información satelital de diferentes fechas a lo largo del ciclo fenológico completo de VV cultivada en varios lotes del partido de Guaminí (provincia de Buenos Aires) y se encontró una estrecha relación entre la serie temporal de los índices de vegetación y el rinde de dichos cultivos. En base a esos resultados, se evalúa la posibilidad de predecir el rendimiento a partir de nueve fechas de la campaña 2021-2022 entre la siembra y la cosecha. Las mismas se asocian de distintas maneras determinando su impacto sobre la precisión del modelo entrenado.Los resultados evidencian que con el monitoreo remoto de cinco fechas es posible clasificar adecuadamente el rendimiento de VV. Tener un modelo de predicción ayudaría en las decisiones in-situ optimizando el uso que puede darse al cultivo de VV (pastoreo directo, forraje o producción de semillas) en función del rendimiento esperado.
In this paper, satellite images, machine learning algorithms and field measurements are combined to analyze the possibility of generating a model that predicts the yield of the legume Vicia villosa Roth before harvest. In a previous study, satellite information from different dates throughout the complete phenological cycle of the legume cultivated in several plots of the Guaminí district (Buenos Aires) was used and a close relationship was found between yield level and the time series of vegetation indices. Based on these results, the possibility of predicting yield is evaluated considering nine dates of the 2021-2022 campaign between sowing and prior to harvest. They are associated in different ways, determining their impact on the accuracy of the trained model. Results show that legume yield can be adequately classifed with remote monitoring of five dates. To have a prediction model could help in in-situ decisions by optimizing the use given to the crop (direct grazing, forage or seed production) based on its expected profit.
In this paper, satellite images, machine learning algorithms and field measurements are combined to analyze the possibility of generating a model that predicts the yield of the legume Vicia villosa Roth before harvest. In a previous study, satellite information from different dates throughout the complete phenological cycle of the legume cultivated in several plots of the Guaminí district (Buenos Aires) was used and a close relationship was found between yield level and the time series of vegetation indices. Based on these results, the possibility of predicting yield is evaluated considering nine dates of the 2021-2022 campaign between sowing and prior to harvest. They are associated in different ways, determining their impact on the accuracy of the trained model. Results show that legume yield can be adequately classifed with remote monitoring of five dates. To have a prediction model could help in in-situ decisions by optimizing the use given to the crop (direct grazing, forage or seed production) based on its expected profit.
Colecciones
Aprobación
Revisión
Complementado por
Referenciado por
Licencia Creative Commons
Excepto donde se indique lo contrario, la licencia de este ítem se describe como by-nc-sa
