New optimized grey derivative models for grain production forecasting in China

Abstract

Although the grey forecasting model has been successfully employed in various fields and demonstrates promising results, the literature shows that its performance could still be improved. Therefore, the aim of the present study was to continue the investigation and derive three hybrid models to predict grain production in China by combining particle swarm optimization (PSO) with the grey linear power index model, the grey logarithm power model and the grey parabola power model. In grey modelling, the use of PSO had the ability to search optimum grey parameters to construct three improved derivative grey models. The results concluded that the improved optimization models with high precision were superior to the traditional models, and PSO contributed more to precision improvement of the three grey models. Furthermore, results from the experiments demonstrated that the optimized models were reliable and valid.

Prediction of grain supply and demand structural balance in China based on grey models

“…And grey forecast models have also been applied by many scholars in the research of grain. Chen (Chen et al, 2016a, b) used a grey model to capture the main trend of grain production and establishes a modified model of BP neural networks and then analyzes the irregular events and its influencing direction and degree with Delphi methods; Fan (Fan et al, 2019) established a forecasting models with the error corrected GM (1,1) model and ARIMA method and reconstructed prediction model by adding all forecasting models together to predict grain yield of China; Lv (Lv et al, 2015) used the grey neural network to predict grain yield and experimented the beans yield, rice yield and corn yield respectively to evaluate the prediction performance; Fan (Fan et al, 2016) established a forecasting method based on the grey theory by yield series data from 1980 to 2012 and compared the prediction precision between the GM (1,1) and the moving average methods; Liu (Liu et al, 2015) derived three hybrid models to predict grain production in China by combining particle swarm optimization (PSO) with grey linear power index model, grey logarithm power model and grey parabola power model. Most of the above studies predicted grain demand based on low growth trends from the aspects of rations, feed grains, industrial use, and loss trends.…”

Forecasting the Agriculture Output Values in China Based on Grey Seasonal Model

“…An improved grey forecasting model based on a genetic algorithm was constructed for forecasting agricultural outputs [4]. Grain production in China was predicted by using three hybrid models comprising particle swarm optimization combined with the grey linear power index model, the grey logarithm power model, and the grey parabola power model [5]. e GM(1,1) model, logistic curve growth model, and exponential growth curve model were used for green agriculture prediction in China [6].…”