Predicting rice yield from multi-temporal satellite data using artificial neural network
2014
Alibuyog, N.R. | Maloom, J.M. | Vives, M.J.C. | Bucao, D.S. | Tute, L.M.
Monitoring the growth of rice and forecasting its yield before harvest season is very important for crop and food management. Remote sensing images are capable of identifying crop health as well as predicting its yield. This study explored the potentials of the ANN model for developing rice yield prediction systems using the multi-temporal satellite data. The study used 16-day composite TERRA MODIS satellite images downloaded from the internet from November 2010 to April 2011 to predict rice yield in the province of Ilocos Norte. Two ANN rice yield prediction models, namely Rice Mod 3 and Rice Mod 5, were developed. Results showed that Rice Mod 3 and Rice Mod 5 were quite efficient in capturing the complex relationship between rice yield and crop spectral signature with R2 values of 0.542 and 0.732, respectively. The ability of Rice Mod 3 to reasonably forecast the expected rice yield some time ahead of the harvesting date provide some opportunities for a farm manager to make decisions before harvest. As such, it may be proven useful to use the model to provide farm advisories. The Rice Mod 5 on the other hand may be proved useful to provide timely prediction of crop yield over large areas and could be used as an alternate method for crop yield survey.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par University of the Philippines at Los Baños
Découvrez la collection de ce fournisseur de données dans AGRIS