基于BP神经网络预测林内PM_(2.5)浓度  

Prediction of PM_(2.5) Concentration in Forest Based on BP Artificial Neural Network

作　　者：陈博[1] 李迎春 夏振平[1] CHEN Bo;LI Ying-chun;XIA Zhen-ping(Beijing Vocational College of Agriculture,Beijing 102442;Huangfa Nursery,Beijing 102604)

机构地区：[1]北京农业职业学院,北京102442 [2]黄垡苗圃,北京102604

出　　处：《安徽农业科学》2019年第1期107-110,共4页Journal of Anhui Agricultural Sciences

基　　金：国家林业公益性行业科研项目(201304301)

摘　　要：[目的]利用BP神经网络预测林内PM_(2.5)浓度。[方法]利用人工神经网络理论,采用2013年7月—2014年5月野外实时监测数据,建立了以气象参数、污染源强变量和林分结构特征为输入因子,林内PM_(2.5)小时平均浓度为输出因子的预测模型,并对其预测精度进行了评价。[结果]BP人工神经网络模型能够很好地捕捉污染物浓度与气象因素和林分结构间的非线性影响规律,预测结果的平均相对误差为1.71×10^(-3),均方根误差为6.77,拟合优度达0.98,模型具有很高的预测精度。而传统的多元线性回归(MLR)模型预测结果的平均相对误差、均方根误差和拟合优度分别为0.27、22.92和0.93。[结论]研究成果印证了应用BP人工神经网络模型预测林内PM_(2.5)浓度的可行性和准确性。[Objective]BP neural network was used to predict PM2.5 concentration in forest.[Method]An artificial neural network model was established with meteorological data,atmospheric PM2.5 concentration outside the forest and forest structure as the input factors,and PM2.5 hourly average concentration inside the forest as the output factors.Its prediction accuracy was also evaluated in this paper.[Result]BP artificial neural network model can be trained to model the highly non-linear relationships between meteorological parameters,forest structure and PM2.5 concentration.Mean relative error(E MR),root mean square error(E RMS)and goodness of fit(R2)between BP simulated PM2.5 concentrations in the forest and observed ones were 1.71×10^-3,6.77 and 0.98,respectively.The mean relative error,root mean square error and goodness of fit of traditional MLR model were 0.27,22.92 and 0.93,respectively.[Conclusion]It can be concluded that BP artificial neural network model is a promising approach in predicting PM2.5 concentration inside a forest.

关 键 词：PM2.5 BP人工神经网络 多元线性回归 林分结构 

分 类 号：S771.8[农业科学—森林工程]