Study on the Estimation of Frost Occurrence Classification Using Machine Learning Methods
2017
Kim, Y., National Institute of Agricultural Sciences, RDA, Wanju, Republic of Korea | Shim, K.M., National Institute of Agricultural Sciences, RDA, Wanju, Republic of Korea | Jung, M.P., National Institute of Agricultural Sciences, RDA, Wanju, Republic of Korea | Choi, I.T., National Institute of Agricultural Sciences, RDA, Wanju, Republic of Korea
In this study, a model to classify frost occurrence and frost free day was developed using the digital weather forecast data provided by Korea Meteorological Administration (KMA). The minimum temperature, average wind speed, relative humidity, and dew point temperature were identified as the meteorological variables useful for classification frost occurrence and frost-free days. It was found that frost-occurrence date tended to have relatively low values of the minimum temperature, dew point temperature, and average wind speed. On the other hand, relatively humidity on frost-free days was higher than on frost-occurrence dates. Models based on machine learning methods including Artificial Neural Network (ANN), Random Forest(RF), Support Vector Machine(SVM) with those meteorological factors had greater than 70% of accuracy. This results suggested that these models would be useful to predict the occurrence of frost using a digital weather forecast data.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Korea Agricultural Science Digital Library
Découvrez la collection de ce fournisseur de données dans AGRIS