Adjoint sensitivity analysis allows to assess the areas that have the largest impact on a given receptor site. The adjoint version of the Community Multiscale Air Quality (CMAQ v4.5) model was employed to perform a se...Adjoint sensitivity analysis allows to assess the areas that have the largest impact on a given receptor site. The adjoint version of the Community Multiscale Air Quality (CMAQ v4.5) model was employed to perform a sensitivity analysis of ground level ozone for the episodic event of June 24, 2003, in the city of Athens assuming as a receptor site that of Agia Paraskevi Station. The 3-dimensional meteorology fields calculated using the Mesoscale Model 5 (MM5, Penn State University version 3.7.2) were used to produce high resolution daily air emissions inventories for the main anthropogenic and biogenic pollutants with 1-hour time step by an in-house built processor named EMISLAB. The meteorological prediction fields in combination with the emissions inventories were consequently fed as inputs to the CMAQ model. The ozone sensitivities were obtained with respect to pollutant concentrations and emissions. The distribution of the sensitivities in the computational domain for different times delineated the regions where perturbations in some concentrations would result in significant changes in the ozone concentrations in the area of interest (Agia Paraskevi, in this case) at the final time. The investigation yielded that the most significant influences were the transported O3 and NOx concentrations from the industrial area in the northern parts of the city and the road traffic from the city centre.展开更多
The present paper discusses the application of localized linear models for the prediction of hourly PM10 concentration values. The advantages of the proposed approach lies in the clustering of the data based on a comm...The present paper discusses the application of localized linear models for the prediction of hourly PM10 concentration values. The advantages of the proposed approach lies in the clustering of the data based on a common property and the utilization of the target variable during this process, which enables the development of more coherent models. Two alternative localized linear modelling approaches are developed and compared against benchmark models, one in which data are clustered based on their spatial proximity on the embedding space and one novel approach in which grouped data are described by the same linear model. Since the target variable is unknown during the prediction stage, a complimentary pattern recognition approach is developed to account for this lack of information. The application of the developed approach on several PM10 data sets from the Greater Athens Area, Helsinki and London monitoring networks returned a significant reduction of the prediction error under all examined metrics against conventional forecasting schemes such as the linear regression and the neural networks.展开更多
Numerical Weather Prediction(NWP)simulations produce meteorological data in various spatial and temporal scales,depending on the application requirements.In the current study,a deep learning approach,based on convolut...Numerical Weather Prediction(NWP)simulations produce meteorological data in various spatial and temporal scales,depending on the application requirements.In the current study,a deep learning approach,based on convolutional autoencoders,is explored to effectively correct the error of the NWP simulation.An undercomplete convolutional autoencoder(CAE)is applied as part of the dynamic error correction of NWP data.This work is an attempt to improve the seasonal forecast(3-6 months ahead)data accuracy for Greece using a global reanalysis dataset(that incorporates observations,satellite imaging,etc.)of higher spatial resolution.More specifically,the publically available Meteo France Seasonal(Copernicus platform)and the National Centers for Environmental Prediction(NCEP)Final Analysis(FNL)(NOAA)datasets are utilized.In addition,external information is used as evidence transfer,concerning the time conditions(month,day,and season)and the simulation characteristics(initialization of simulation).It is found that convolutional autoencoders help to improve the resolution of the seasonal data and successfully reduce the error of the NWP data for 6-months ahead forecasting.Interestingly,the month evidence yields the best agreement indicating a seasonal dependence of the performance.展开更多
文摘Adjoint sensitivity analysis allows to assess the areas that have the largest impact on a given receptor site. The adjoint version of the Community Multiscale Air Quality (CMAQ v4.5) model was employed to perform a sensitivity analysis of ground level ozone for the episodic event of June 24, 2003, in the city of Athens assuming as a receptor site that of Agia Paraskevi Station. The 3-dimensional meteorology fields calculated using the Mesoscale Model 5 (MM5, Penn State University version 3.7.2) were used to produce high resolution daily air emissions inventories for the main anthropogenic and biogenic pollutants with 1-hour time step by an in-house built processor named EMISLAB. The meteorological prediction fields in combination with the emissions inventories were consequently fed as inputs to the CMAQ model. The ozone sensitivities were obtained with respect to pollutant concentrations and emissions. The distribution of the sensitivities in the computational domain for different times delineated the regions where perturbations in some concentrations would result in significant changes in the ozone concentrations in the area of interest (Agia Paraskevi, in this case) at the final time. The investigation yielded that the most significant influences were the transported O3 and NOx concentrations from the industrial area in the northern parts of the city and the road traffic from the city centre.
文摘The present paper discusses the application of localized linear models for the prediction of hourly PM10 concentration values. The advantages of the proposed approach lies in the clustering of the data based on a common property and the utilization of the target variable during this process, which enables the development of more coherent models. Two alternative localized linear modelling approaches are developed and compared against benchmark models, one in which data are clustered based on their spatial proximity on the embedding space and one novel approach in which grouped data are described by the same linear model. Since the target variable is unknown during the prediction stage, a complimentary pattern recognition approach is developed to account for this lack of information. The application of the developed approach on several PM10 data sets from the Greater Athens Area, Helsinki and London monitoring networks returned a significant reduction of the prediction error under all examined metrics against conventional forecasting schemes such as the linear regression and the neural networks.
基金the data provision by Copernicus platform and the National Oceanic and Atmospheric Administration(NOAA).
文摘Numerical Weather Prediction(NWP)simulations produce meteorological data in various spatial and temporal scales,depending on the application requirements.In the current study,a deep learning approach,based on convolutional autoencoders,is explored to effectively correct the error of the NWP simulation.An undercomplete convolutional autoencoder(CAE)is applied as part of the dynamic error correction of NWP data.This work is an attempt to improve the seasonal forecast(3-6 months ahead)data accuracy for Greece using a global reanalysis dataset(that incorporates observations,satellite imaging,etc.)of higher spatial resolution.More specifically,the publically available Meteo France Seasonal(Copernicus platform)and the National Centers for Environmental Prediction(NCEP)Final Analysis(FNL)(NOAA)datasets are utilized.In addition,external information is used as evidence transfer,concerning the time conditions(month,day,and season)and the simulation characteristics(initialization of simulation).It is found that convolutional autoencoders help to improve the resolution of the seasonal data and successfully reduce the error of the NWP data for 6-months ahead forecasting.Interestingly,the month evidence yields the best agreement indicating a seasonal dependence of the performance.
