中国农业气象 ›› 2025, Vol. 46 ›› Issue (10): 1405-1413.doi: 10.3969/j.issn.1000-6362.2025.10.003

• 农业生态环境栏目 • 上一篇    下一篇

基于BP神经网络四连栋塑料大棚的温湿度模拟

周宇,谢烨,黄文娟   

  1. 上海市气候中心,上海 200030
  • 收稿日期:2024-10-27 出版日期:2025-10-20 发布日期:2025-10-16
  • 作者简介:周宇,高级工程师,主要从事农业气象与气候变化研究,E-mail:zhouyu99@foxmail.com
  • 基金资助:
    上海市农业科技创新项目“智能农业气象灾害风险预警技术开发与示范”(2023−02−08−00−12−F04619)

Temperature and Relative Humidity Simulation of Four-span Plastic Greenhouse Based on BP Neural Network

ZHOU Yu, XIE Ye, HUANG Wen-juan   

  1. Shanghai Climate Center, Shanghai 200030, China
  • Received:2024-10-27 Online:2025-10-20 Published:2025-10-16

摘要:

为研究晴天、多云和阴天3种天气类型BP神经网络对设施大棚内平均气温和平均相对湿度的模拟能力,选取上海市松江区2021年3月1日−2022年2月28日四连栋塑料大棚内和同期气象站气象资料,以棚外平均气温、平均相对湿度、平均风速和太阳高度角为输入因子,构建年和季节尺度下3种天气类型的棚内温湿度BP神经网络预测模型,并对模型进行检验。结果表明:(1)年尺度下平均气温模型的均方根误差(RMSE)0.8~1.1℃,决定系数R2≥0.9890P<0.001);平均相对湿度模型的RMSE2.9~4.0个百分点,R2≥0.9434(P<0.001)。阴天的模拟效果最好,多云次之,晴天最低。(2)季节尺度下平均气温模型的RMSE平均值在0.7~0.9℃,R2平均值≥0.9765(P<0.001);平均相对湿度模型的RMSE平均值在2.2~3.2个百分点,R2平均值≥0.9451(P<0.001)。其中,夏季的模拟效果最好,秋季次之,春季和冬季最低。季节尺度模型的模拟效果好于年尺度模型。3)年和季节尺度下平均气温和平均相对湿度模型均通过0.001水平的独立样本显著性检验,表明模型模拟效果较好,可用于模拟温室内温湿度并推广。

关键词: 四连栋塑料大棚, 天气类型, 温湿度模拟, BP神经网络, 时间尺度

Abstract:

In order to study the simulation ability of BP neural network on the average temperature and average relative humidity in the facility greenhouse under three weather types of sunny, cloudy and overcast days, the meteorological data of the four-span plastic greenhouses in Songjiang district, Shanghai from March 1, 2021 to February 28, 2022 and the meteorological station of the same period were selected, and the average temperature, average relative humidity, average wind speed and solar altitude angle outside the greenhouse were used as input factors to construct temperature and humidity BP neural network prediction models for three weather types at the annual and seasonal scales, and the models were validated. The results showed that: (1) at the annual scale, the RMSE of the average temperature model was 0.81.1, and the R20.9890 (P<0.001). The RMSE of the average relative humidity model was 2.94.0pp (percent point), and the R20.9434 (P<0.001). Overcast days were the best simulations results, followed by cloudy days and sunny days at the lowest levels. (2) At the seasonal scale, the average RMSE value of the average temperature model was 0.70.9, and the average R20.9765 (P<0.001). The average RMSE value of the average relative humidity model was 2.23.2pp (percent point), and the average R20.9451 (P<0.001). Of these, the simulation accuracy was best in summer, followed by autumn, and the lowest in spring and winter. The simulation performance of the seasonal scale model was better than that of the annual scale model. (3) The average temperature and average relative humidity models at the annual and seasonal scales passed the independent sample test of the significant level of 0.001, indicating that the model has a good simulation effect and can be used to simulate the temperature and humidity in the greenhouse and practical application.

Key words: Four-span plastic greenhouse, Weather type, Temperature and humidity simulation, BP neural network, Time scale