Authors:
Javier E. Gómez-Lagos
1
;
Marcela C. González-Araya
1
;
Rodrigo Ortega Blu
2
and
Luis G. Acosta Espejo
2
Affiliations:
1
Department of Industrial Engineering, Faculty of Engineering, Universidad de Talca, Camino a Los Niches km 1, Curicó and Chile
;
2
Departamento de Ingeniería Comercial, Universidad Técnica Federico Santa María, Avenida Santa María 6400, Vitacura, Santiago and Chile
Keyword(s):
NDVI, Data Mining Techniques, Neural Networks, Fruit Crop Variability.
Related
Ontology
Subjects/Areas/Topics:
Data Mining and Business Analytics
;
Forecasting
;
Methodologies and Technologies
;
Operational Research
Abstract:
The Normalized Difference Vegetation Index (NDVI) is a simple indicator that quantifies aerial biomass in fruit crops, which is correlated with the fruit yield and quality produced by an orchard. Therefore, knowing the NDVI values would allow predicting productive parameters above mentioned, which in turn would help planning operational activities such as harvesting. In this study, we estimated the NDVI of a Chilean table grape orchard based on past data using data mining techniques. For this purpose, we developed a three-step method, obtaining NDVI predictions with high accuracy.