摘要
南疆降雨量少,气候干燥,农业用水紧张,水资源节约尤为重要,针对此问题设计一套智能灌溉系统。系统使用阿里云服务器作为上位机,树莓派作为下位机,并搭建相应的操作页面。根据Penman-Monteith公式中需要的气象数据、过去7天需水量以及前1天气象数据为输入向量,作物需水量为输出向量,构建基于随机森林、BP神经网络与岭回归的Stacking集成学习预测模型。结果表明Stacking集成学习预测模型拟合系数R 2为0.973,且MAE、RMSE、MAPE三类误差更小,Stacking集成学习预测模型预测效果更强。灌溉试验中自动灌溉决策正确,系统运行稳定,为新疆地区农业提高水资源利用问题提供思路。
In the south of Xinjiang,the rainfall is low,the climate is dry,agricultural water is scarce,and water conservation is particularly important.An intelligent irrigation system is designed to solve this problem.The system uses Alibaba Cloud server as the upper computer and raspberry pie as the lower computer,and sets up corresponding operation pages.In this paper,according to the meteorological data required in Penman-Monteith formula,the water demand of the past seven days and the meteorological data of the previous day as the input vector,and the crop water demand as the output vector,the Stacking integrated learning prediction model based on random forest,BP neural network and ridge regression is constructed.The results show that the fitting coefficient R 2 of Stacking integrated learning prediction model is 0.973,and the three types of errors of MAE,RMSE and MAPE are smaller.The prediction effect of Stacking integrated learning prediction model is stronger.In the irrigation experiment,the automatic irrigation decision is correct,and the system operates stably,which provides ideas for improving the utilization of water resources in agriculture in Xinjiang.
作者
窦文豪
孙三民
徐鹏翔
Dou Wenhao;Sun Sanmin;Xu Pengxiang(College of Water Resources and Architecture Engineering,Tarim University,Alar,843300,China;Key Laboratory of Modern Agricultural Engineering,Tarim University,Alar,843300,China)
出处
《中国农机化学报》
北大核心
2024年第6期270-276,共7页
Journal of Chinese Agricultural Mechanization
基金
新疆生产建设兵团科技项目(2021CB021)
第一师阿拉尔市科技计划项目(2022XX01)。