생육시기 기상을 활용한 배추 가격 예측

Abstract

Domestic production of Chinese cabbage accounts for more than imports. As global warming intensifies, weather factors are expected to play an important role in the price fluctuations of Chinese cabbage due to the increase in the frequency and intensity of abnormal climates. Therefore, this study intends to predict the price of Chinese cabbage by using the weather factors for each growth stage considering the production of the main production area by cropping pattern. Based on the wholesale price of high-grade Chinese cabbage from May 20, 2015 to June 30, 2022, meteorological data for the same day and growth stage were also used in this study. The price of Chinese cabbage was predicted through Long Short-Term Memory(LSTM) and Gated Recurrent Unit(GRU), which are recurrent neural network models, and evaluated based on Root Mean Square Error(RMSE) and Mean Absolute Error(MAE). As a result of the analysis, the absolute difference in price was the smallest when forecasting reflecting the average of insolation during total growing, average of insolation during planting and sowing, and average of minimum grass temperature after planting and during harvest. When the price fluctuation trend was steep, more accurate prediction was possible when the weather of the day was also reflected. In this study, it is difficult to take into account the variation of individual growing seasons by day by applying the average data of a certain growth period to all cropping pattern in question. It is expected that a more accurate prediction can be obtained if the follow-up study is conducted by collecting the growth stage period by farmhouse. Through this study, it is expected that it will help farmers and consumers to sell and purchase based on the predicted price by properly applying weather variables after identifying the trend of the price of Chinese cabbage in the future.