[1]张钰洁,王 钰,杨杏丽.融合深度神经网络特征的 ARIMAX 雾霾 PM2. 5 预测[J].计算机技术与发展,2023,33(02):167-172.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 025]
　ZHANG Yu-jie,WANG Yu,YANG Xing-li.Haze PM2. 5 Concentration Prediction Based on ARIMAX Model with Deep Convolutional Neural Network Features[J].,2023,33(02):167-172.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 025]
点击复制

融合深度神经网络特征的 ARIMAX 雾霾 PM2. 5 预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年02期
页码:
167-172
栏目:
人工智能
出版日期:
2023-02-10

文章信息/Info

Title:
Haze PM2. 5 Concentration Prediction Based on ARIMAX Model with Deep Convolutional Neural Network Features
文章编号:
1673-629X(2023)02-0167-06
作者:
张钰洁1 ; 王 钰2 ; 杨杏丽1
1. 山西大学 数学科学学院,山西 太原 030006;
2. 山西大学 现代教育技术学院,山西 太原 030006
Author(s):
ZHANG Yu-jie1 ; WANG Yu2 ; YANG Xing-li1
1. School of Mathematical Sciences,Shanxi University,Taiyuan 030006,China;
2. School of Modern Educational Technology,Shanxi University,Taiyuan 030006,China
关键词:
PM2. 5 预测; ARIMAX 模型; ResNet 神经网络; 主成分分析技术; 深度语义特征
Keywords:
PM2. 5 prediction; ARIMAX; ResNet; principal component analysis; deep semantic feature
分类号:
TP183;TP181
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 02. 025
摘要:
目前,雾霾污染问题是关乎国计民生的重大问题,它已经对人们的生产、生活、身体健康,以及生态环境和气候变化都产生了很大的影响。 这样,如何通过监测雾霾变化获取的雾霾相关信息去准确预测雾霾污染物的浓度,以防治和减轻雾霾造成的严重后果变得尤为重要。 因此,通过在简单有效的传统 ARIMAX 模型基础上融入深度神经网络语义特征,提出了一种新的雾霾 PM2. 5 浓度预测框架。 首先,把对雾霾预测有显著影响的气象因子温度、压力、相对湿度数据转换为图像数据; 然后, 运用 ResNet - 50 ( Residual Network - 50) 卷积神经网络模型提取深度语义特征, 进而运用主成分分析(Principal Component Analysis,PCA) 技术处理高维特征,得到最佳深度神经网络特征组合;最后,用 ARIMAX 技术建立雾霾PM2. 5 浓度预测模型。 在收集的山西省 2015 ~ 2019 年 PM2. 5 浓度和气象因子数据集上验证了该预测框架在皮尔逊相关系数(Pearson’s Correlation Coefficient,PCC) 、均方误差( Mean Square Error,MSE) 、均方根误差( Root Mean Squared Error,RMSE) 和平均绝对误差( Mean Absolute Error, MAE) 度量下,对于 1、3、5 和 7 天长短期预测,都始终优于传统的简单差分自回归滑动平均( Autoregressive Integrated Moving Average,ARIMA) 模型、三因素 ARIMAX 模型、多元回归模型、ResNet-多元回归模型、长短期记忆网络(Long and Short-Term Memory,LSTM) 模型和支持向量机(Support Vector Machine,SVM) 模型。
Abstract:
At present,the problem of haze pollution is a major issue related to the national economy and people’s livelihood,which hasalready had a great impact on people ’s production, life, health, and ecological environment and climate change. In this way, how toaccurately predict the concentration of haze pollution by monitoring the haze-related information obtained by monitoring the haze changesin order to prevent and reduce the serious consequences of haze has become particularly important. Therefore, by incorporating thesemantic features of deep neural networks on the basis of the ARIMAX model,we propose a new haze PM2. 5 concentration predictionframework. Firstly,the numerical meteorological data ( temperature,pressure and relative humidity that have a significant impact on hazeprediction) is transformed into image data. Secondly,the ResNet-50 ( Residual Network-50) model is used to extract deep semanticfeatures and PCA ( Principal Component Analysis) is to process high - dimensional features for the best combination of deep neuralnetwork features. Finally,ARIMAX technology is used to establish a haze PM2. 5 concentration prediction model. Furthermore,on thecollected data set of PM2. 5 concentration and meteorological factors in Shanxi Province from 2015 to 2019, under the Pearson’sCorrelation Coefficient ( PCC) ,Mean Square Error ( MSE) , Root Mean Squared Error ( RMSE) and Mean Absolute Error ( MAE)measurements, the experimental results demonstrate the proposed prediction frameworks are always superior to the traditional Autoregressive Integrated Moving Average ( ARIMA) ,three-factor ARIMAX,multiple regression,ResNet-multiple regression,Long andShort-Term Memory ( LSTM) and Support Vector Machine ( SVM) ,for 1, 3, 5 and 7-day long and short-term prediction.

相似文献/References:

[1]王 健,宋 颖,吴 涛.基于 LSTM 网络与误差补偿的预测模型[J].计算机技术与发展,2023,33(03):133.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 020]
　WANG Jian,SONG Ying,WU Tao.Prediction Model Based on LSTM Network and Error Compensation[J].,2023,33(02):133.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 020]

更新日期/Last Update: 2023-02-10