基于GM(1,1)模型的中国小杂粮种植面积预测分析
|
摘要
[目的]小杂粮在调整我国居民粮食消费结构以及改善膳食营养中始终占据着重要地位。科学预测全国小杂粮的种植面积,可为国家调整种植业结构、优化绿色优质产品供给、稳定小杂粮市场定价、提高农民收入提供依据。[方法]文章基于近20年全国小杂粮种植面积数据,建立灰色GM (1,1)预测模型,预测了未来10年中国小杂粮的种植面积。[结果]该预测模型预测精度较高,为1级,可用于我国小杂粮种植面积的中长期预测;预测结果显示,未来10年我国小杂粮的种植面积处于下降的态势。[结论]我国小杂粮播种面积逐年减少对我国绿色优质农产品供给和种植业结构调整可能会产生不利的影响。从长期看,为了扭转我国小杂粮种植面积下降的局面,要从政策导向、产业扶持(基础设施、补贴、信贷优惠)、科技支撑(良种引入、种植技术)、仓储以及市场等方面发力,从而保障我国小杂粮产业持续健康的发展。
Minor grains have always occupied an important position in adjusting China's food consumption structure and improving dietary nutrition. The scientific prediction of the sown area of minor grains in the whole country can provide an important reference for the country to adjust planting industry structure,optimize the supply of green and high-quality products,stabilize the market pricing of small and coarse grain markets,and improve farmers' income.Based on data of sown area of minor grains in the past 20 years,a grey GM( 1,1) prediction model was established to predict future minor grains area. The results showed that the accuracy of the prediction model was high,achieving to the first level,and that could be used for medium or long-term prediction of small grain crops sown area in China. And in the next 10 years,the predicted results indicated that the sown area of China's minor grains would be in a declining trend. The reduction in the sown area in China may negatively affect the supply of green and highquality agricultural products and the structural adjustment of crop production in China. From a long-term perspective,in order to reverse the decline in the sown area of China's minor grains and ensure the healthy and sustainable development of China's minor grains industry,supports of policy guidance,industrial development( infrastructure,subsidies,credit incentives),science and technology( improved variety,planting technology),warehousing,and markets are all needed.
Minor grains have always occupied an important position in adjusting China's food consumption structure and improving dietary nutrition. The scientific prediction of the sown area of minor grains in the whole country can provide an important reference for the country to adjust planting industry structure,optimize the supply of green and high-quality products,stabilize the market pricing of small and coarse grain markets,and improve farmers' income.Based on data of sown area of minor grains in the past 20 years,a grey GM( 1,1) prediction model was established to predict future minor grains area. The results showed that the accuracy of the prediction model was high,achieving to the first level,and that could be used for medium or long-term prediction of small grain crops sown area in China. And in the next 10 years,the predicted results indicated that the sown area of China's minor grains would be in a declining trend. The reduction in the sown area in China may negatively affect the supply of green and highquality agricultural products and the structural adjustment of crop production in China. From a long-term perspective,in order to reverse the decline in the sown area of China's minor grains and ensure the healthy and sustainable development of China's minor grains industry,supports of policy guidance,industrial development( infrastructure,subsidies,credit incentives),science and technology( improved variety,planting technology),warehousing,and markets are all needed.
引文
[1]龚梅,敖茂宏,彭杨.贵州小杂粮产业发展现状及对策.贵州农业科学,2016(7):156-158.
[2]李哲敏,刘磊,刘宏.保障我国农产品质量安全面临的挑战及对策研究.中国科技论坛,2012(10):132-137.
[3]农办农[2018] 1号.农业部种植业管理司. 2018年种植业工作要点. http://www. moa. gov. cn/ztzl/ncgzhy2017/zxdt/201802/t20180203_6136400. htm.
[4]李哲敏,许世卫,崔利国.基于动态混沌神经网络的预测研究——以马铃薯时间序列价格为例.系统工程理论与实践,2015(8):2083-2091.
[5] ZHANG G P. Time series forecasting using a hybrid ARIMa and neural network model. Neurocomputing,2003(50):159-175.
[6] Jain A,Kumar A M. Hybrid neural network models for hydrologic time series forecasting. Applied Soft Computing,2007,7(2):585-592.
[7]党耀国,王正新,钱吴永.灰色预测技术方法.北京:科学出版社,2015.
[8]宋家清.基于GM(1,1)模型的东营市冬枣栽植面积预测分析.现代农业科技,2015(13):343,345.
[9]朱登远,常晓凤.灰色预测GM(1,1)模型的MATLAB实现.河南城建学院学报,2013(3):40-46.
[10]尹连生,白玉皎. GM(1,1)模型建模条件及模型改造.北京,中国土地学会首届青年学术年会,1992(4):107-115.
[11]刘思峰,郭天榜,党耀国,等.灰色系统理论及其应用.北京:科学出版社,1999.
[12]黄锦祥,鄢新余,熊伟.基于GM(1,1)模型的宁化县油料产量和播种面积预测.亚热带水土保持,2014(2):12-14.
[13]傅鹤林,彭思甜,韩汝才,等.岩土工程数值分析新方法.长沙:中南大学出版社,2006.
[14]刘慧,矫健,李宁辉.我国杂粮价格波动与影响研究.北京:经济科学出版社,2013.
[15]周品,何正风. MATLAB数值分析.北京:机械工业出版社,2009.
[16]凡兰兴.发展我国杂粮生产的思考.山西农业科学,2012(10):1121-1124.
[17]牛婷婷.甘肃省小杂粮产业竞争力研究.兰州:甘肃农业大学,2010.
[18]刘祎鸿,赵贵宾,董孔军,等.甘肃小杂粮生产演变特征、存在问题及对策建议.中国农业资源与区划,2016(10):122-126.
[19]施政.供应链视角下白城市小杂粮产业研究.北京:中国农业科学院,2013.
[2]李哲敏,刘磊,刘宏.保障我国农产品质量安全面临的挑战及对策研究.中国科技论坛,2012(10):132-137.
[3]农办农[2018] 1号.农业部种植业管理司. 2018年种植业工作要点. http://www. moa. gov. cn/ztzl/ncgzhy2017/zxdt/201802/t20180203_6136400. htm.
[4]李哲敏,许世卫,崔利国.基于动态混沌神经网络的预测研究——以马铃薯时间序列价格为例.系统工程理论与实践,2015(8):2083-2091.
[5] ZHANG G P. Time series forecasting using a hybrid ARIMa and neural network model. Neurocomputing,2003(50):159-175.
[6] Jain A,Kumar A M. Hybrid neural network models for hydrologic time series forecasting. Applied Soft Computing,2007,7(2):585-592.
[7]党耀国,王正新,钱吴永.灰色预测技术方法.北京:科学出版社,2015.
[8]宋家清.基于GM(1,1)模型的东营市冬枣栽植面积预测分析.现代农业科技,2015(13):343,345.
[9]朱登远,常晓凤.灰色预测GM(1,1)模型的MATLAB实现.河南城建学院学报,2013(3):40-46.
[10]尹连生,白玉皎. GM(1,1)模型建模条件及模型改造.北京,中国土地学会首届青年学术年会,1992(4):107-115.
[11]刘思峰,郭天榜,党耀国,等.灰色系统理论及其应用.北京:科学出版社,1999.
[12]黄锦祥,鄢新余,熊伟.基于GM(1,1)模型的宁化县油料产量和播种面积预测.亚热带水土保持,2014(2):12-14.
[13]傅鹤林,彭思甜,韩汝才,等.岩土工程数值分析新方法.长沙:中南大学出版社,2006.
[14]刘慧,矫健,李宁辉.我国杂粮价格波动与影响研究.北京:经济科学出版社,2013.
[15]周品,何正风. MATLAB数值分析.北京:机械工业出版社,2009.
[16]凡兰兴.发展我国杂粮生产的思考.山西农业科学,2012(10):1121-1124.
[17]牛婷婷.甘肃省小杂粮产业竞争力研究.兰州:甘肃农业大学,2010.
[18]刘祎鸿,赵贵宾,董孔军,等.甘肃小杂粮生产演变特征、存在问题及对策建议.中国农业资源与区划,2016(10):122-126.
[19]施政.供应链视角下白城市小杂粮产业研究.北京:中国农业科学院,2013.