节点文献
基于门控循环单元神经网络的PM2.5浓度预测
Prediction of PM2.5 concentration based on gated recurrent unit neural network
【摘要】 文章首先针对延安市市监测站单站点观测数据与PM2.5的关系,从中抽取了影响PM2.5较为明显的14组特征数据。依据所抽取的数据,利用LSTM深度神经网络的一种变体GRU建立了未来数小时的PM2.5浓度预测模型,通过仿真实验,该模型对PM2.5预测有较高的一致性,可以较好地满足日常预测业务需求。
【Abstract】 This paper firstly analyzes the relationship between single-site observation data and PM2.5 of Yan’an City Monitoring Station,and extracts 14 sets of characteristic data that affect PM2.5.Based on the extracted data, the GRU, a variant of the LSTM deep neural network, is used to establish a PM2.5 concentration prediction model for the next few hours. Through simulation experiments, the model has a high consistency for PM2.5 prediction, and goodly meet the daily forecast business needs.
【关键词】 PM2.5浓度预测;
LSTM;
GRU;
机器学习;
循环神经网络;
【Key words】 prediction of PM2.5 concentration; LSTM; GRU; machine learning; recurrent neural network;
【Key words】 prediction of PM2.5 concentration; LSTM; GRU; machine learning; recurrent neural network;
【基金】 国家自然科学基金;项目编号:61763046
- 【文献出处】 无线互联科技 ,Wireless Internet Technology , 编辑部邮箱 ,2019年04期
- 【分类号】TP183;X831
- 【被引频次】5
- 【下载频次】197