摘要
以上海市、江苏省、浙江省、安徽省三省一市为研究对象,选取2000年至2022年三省一市生鲜农产品产量作为数据研究,采用长短时记忆(long short-term memory,LSTM)神经网络模型和门控循环单元(gated recurrent unit,GRU)模型进行训练和验证。结果表明,通过两种模型的训练计算,在精度相似的情况下GRU模型的参数测试时长、训练速度、内存消耗更小,比LSTM模型平均减少0.035 s、106.295 s、1.55 MiB。选取GRU模型对长三角地区生鲜农产品产量进行预测,进而判断长三角地区冷链物流服务的需求程度。结果显示,2023年至2025年长三角地区生鲜农产品冷链物流需求持续上升,最后针对长三角地区三省一市持续上升的冷链物流需求给出几点建议。
Taking Shanghai Gty,Jiangsu Provinces cities,Zhejiang Provinces cities,and Anhui Provinces cities as research objects,the fresh agricultural product production from 2000 to 2022 was selected as data for the study.Long Short Term Memory(LSTM)neural network model and Gated Recurrent Unit(GRU)model were used for training and validation.The results showed that,under similar accuracy,the parameter testing time,training speed,and memory consumption of the GRU model were smaller,with an average reduction of 0.035 s,106.295 s,and 1.55 MiB compared to the LSTM model.The GRU model is selected to predict the production of fresh agricultural products in the Yangtze River Delta region,and to determine the degree of demand for cold chain logistics services in the region.The results show that the demand for cold chain logistics of fresh agricultural products in the Yangtze River Delta region has continued to rise from 2023 to 2025.Several suggestions are given for the continuous increase in cold chain logistics demand in the three provinces and one city of the Yangtze River Delta region.
作者
徐超毅
胡望敏
XU Chaoyi;HU Wangmin(School of Economics and Management,Anhui University of Science and Technology,Huainan 232001,China)
出处
《枣庄学院学报》
2024年第5期25-32,共8页
Journal of Zaozhuang University
基金
国家自然科学基金项目(71973001)
安徽理工大学研究生创新基金项目(2023CX2171)。
关键词
高质量发展
长三角地区
GRU模型
LSTM模型
冷链物流
需求预测
high quality development
the Yangtze River Delta region
GRU model
LSTM model
cold chain logistics
demand forecast
