Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weathe...Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.展开更多
[ Objective] The research aimed to analyze characteristics of the atmospheric particulate pollutants （ PMlo and PM2.s） in Wenzhou City. [Method] We analyzed interannual change rule of the dust haze in Wenzhou during...[ Objective] The research aimed to analyze characteristics of the atmospheric particulate pollutants （ PMlo and PM2.s） in Wenzhou City. [Method] We analyzed interannual change rule of the dust haze in Wenzhou during 1978 -2008. Moreover, we respectively set monitoring points in urban district, industrial park and beauty spot of Wenzhou in summer and winter of 2010. Element, ion and polycyclic aromatic hydrocarbon com- positions and morphology of the particulate matter were analyzed. [ Result] Dust haze in Wenzhou City mainly appeared in winter and spring, which was related to local meteorological condition. In summer and winter, both PMlo and PM2.s concentrations presented the characteristic of industrial park 〉 commercial area 〉 beauty spot. Chain-like particle aggregates and ultrafine particles were main composition of the atmospheric particulate matter in Wenzhou. Contribution rate of the spherical particle amount was smaller than metropolis, which was related to local industry and traffic. Fe element had the most content in particulate matter. Mass concentration was mainly composed of 6 elements, such as Na, Si, S, K, Ca and Fe. Total concentration of the six elements occupied 70% -80% of the 16 elements. SO^- and NH4＊ in particulate matter were higher. They were mainly from human activity. Main compositions of the polycyclic aromatic hydrocarbon were naphthalene, anthracene, benzo （b） fluoranthene, indeno （1,2, 3-cd） pyrene and benzo （g, h, i） perylene, which was related to abrupt increase of the motor vehicle. [ Condusion] The research provided scientific basis and technology support for controlling atmospheric particulate matter pollution in Wenzhou City by government and related department.展开更多
The prediction of particles less than 2.5 micrometers in diameter(PM2.5)in fog and haze has been paid more and more attention,but the prediction accuracy of the results is not ideal.Haze prediction algorithms based on...The prediction of particles less than 2.5 micrometers in diameter(PM2.5)in fog and haze has been paid more and more attention,but the prediction accuracy of the results is not ideal.Haze prediction algorithms based on traditional numerical and statistical prediction have poor effects on nonlinear data prediction of haze.In order to improve the effects of prediction,this paper proposes a haze feature extraction and pollution level identification pre-warning algorithm based on feature selection and integrated learning.Minimum Redundancy Maximum Relevance method is used to extract low-level features of haze,and deep confidence network is utilized to extract high-level features.eXtreme Gradient Boosting algorithm is adopted to fuse low-level and high-level features,as well as predict haze.Establish PM2.5 concentration pollution grade classification index,and grade the forecast data.The expert experience knowledge is utilized to assist the optimization of the pre-warning results.The experiment results show the presented algorithm can get better prediction effects than the results of Support Vector Machine(SVM)and Back Propagation(BP)widely used at present,the accuracy has greatly improved compared with SVM and BP.展开更多
文摘Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.
基金Supported by Study on Formation Reason and Early Warning of the Dust Haze and Atmospheric Complex Pollution Control in Wenzhou City ( R20090124)
文摘[ Objective] The research aimed to analyze characteristics of the atmospheric particulate pollutants （ PMlo and PM2.s） in Wenzhou City. [Method] We analyzed interannual change rule of the dust haze in Wenzhou during 1978 -2008. Moreover, we respectively set monitoring points in urban district, industrial park and beauty spot of Wenzhou in summer and winter of 2010. Element, ion and polycyclic aromatic hydrocarbon com- positions and morphology of the particulate matter were analyzed. [ Result] Dust haze in Wenzhou City mainly appeared in winter and spring, which was related to local meteorological condition. In summer and winter, both PMlo and PM2.s concentrations presented the characteristic of industrial park 〉 commercial area 〉 beauty spot. Chain-like particle aggregates and ultrafine particles were main composition of the atmospheric particulate matter in Wenzhou. Contribution rate of the spherical particle amount was smaller than metropolis, which was related to local industry and traffic. Fe element had the most content in particulate matter. Mass concentration was mainly composed of 6 elements, such as Na, Si, S, K, Ca and Fe. Total concentration of the six elements occupied 70% -80% of the 16 elements. SO^- and NH4＊ in particulate matter were higher. They were mainly from human activity. Main compositions of the polycyclic aromatic hydrocarbon were naphthalene, anthracene, benzo （b） fluoranthene, indeno （1,2, 3-cd） pyrene and benzo （g, h, i） perylene, which was related to abrupt increase of the motor vehicle. [ Condusion] The research provided scientific basis and technology support for controlling atmospheric particulate matter pollution in Wenzhou City by government and related department.
基金The work was financially supported by National Natural Science Fund of China,specific grant numbers were 61371143 and 61662033initials of authors who received the grants were respectively Z.YM,H.L,and the URLs to sponsors’websites was http://www.nsfc.gov.cn/.This paper was supported by National Natural Science Fund of China(Grant Nos.61371143,61662033).
文摘The prediction of particles less than 2.5 micrometers in diameter(PM2.5)in fog and haze has been paid more and more attention,but the prediction accuracy of the results is not ideal.Haze prediction algorithms based on traditional numerical and statistical prediction have poor effects on nonlinear data prediction of haze.In order to improve the effects of prediction,this paper proposes a haze feature extraction and pollution level identification pre-warning algorithm based on feature selection and integrated learning.Minimum Redundancy Maximum Relevance method is used to extract low-level features of haze,and deep confidence network is utilized to extract high-level features.eXtreme Gradient Boosting algorithm is adopted to fuse low-level and high-level features,as well as predict haze.Establish PM2.5 concentration pollution grade classification index,and grade the forecast data.The expert experience knowledge is utilized to assist the optimization of the pre-warning results.The experiment results show the presented algorithm can get better prediction effects than the results of Support Vector Machine(SVM)and Back Propagation(BP)widely used at present,the accuracy has greatly improved compared with SVM and BP.
