Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data predic...Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.展开更多
Urban Nitrogen Oxide(NO_(x))air pollution poses significant public health risks,and therefore spatiotemporal knowledge of NO_(x) is crucial for air quality regulation.However,few studies have examined long-term NO_(x)...Urban Nitrogen Oxide(NO_(x))air pollution poses significant public health risks,and therefore spatiotemporal knowledge of NO_(x) is crucial for air quality regulation.However,few studies have examined long-term NO_(x) dynamics in Manchester by integrating spatial,temporal,and mechanistic perspectives.This study investigates the long-term trends and drivers of NO and NO_(2) in the urban atmosphere of Manchester from 2015 to 2025.Data from five AURN monitoring sites,ERA5 meteorological reanalysis datasets,and UK Department for Transport traffic statistics were analysed using linear regression for trend estimation,seasonal decomposition,and spatial pattern analysis.A hybrid statistical-machine learning framework was additionally employed,combining Ordinary Least Squares(OLS)regression with XGBoost models interpreted through Shapley Additive Explanations(SHAP).The results indicate statistically significant declining trends in both pollutants,with average annual decreases of approximately 4.8%,and dramatic short-term reductions during COVID-19 lockdowns,highlighting the dominant influence of traffic.Seasonal patterns persisted,with winter concentrations 1.9 times greater than summer levels,and spatial analysis revealed strong NO_(2) heterogeneity among monitoring sites.Machine learning models performed substantially better than linear regression(R^(2)=0.475 vs.0.29),and SHAP analysis showed ozone,boundary layer height,and temperature as the main drivers of NO_(2) variations.Overall,the findings confirm substantial air-quality improvements while revealing nonlinear processes in urban pollution dynamics,supporting continued emission-reduction policies and enhanced monitoring strategies.展开更多
基金the National Natural Science Foundation of China(22108307)the Natural Science Foundation of Shandong Province(ZR2020KB006)the Outstanding Youth Fund of Shandong Provincial Natural Science Foundation(ZR2020YQ17).
文摘Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.
文摘Urban Nitrogen Oxide(NO_(x))air pollution poses significant public health risks,and therefore spatiotemporal knowledge of NO_(x) is crucial for air quality regulation.However,few studies have examined long-term NO_(x) dynamics in Manchester by integrating spatial,temporal,and mechanistic perspectives.This study investigates the long-term trends and drivers of NO and NO_(2) in the urban atmosphere of Manchester from 2015 to 2025.Data from five AURN monitoring sites,ERA5 meteorological reanalysis datasets,and UK Department for Transport traffic statistics were analysed using linear regression for trend estimation,seasonal decomposition,and spatial pattern analysis.A hybrid statistical-machine learning framework was additionally employed,combining Ordinary Least Squares(OLS)regression with XGBoost models interpreted through Shapley Additive Explanations(SHAP).The results indicate statistically significant declining trends in both pollutants,with average annual decreases of approximately 4.8%,and dramatic short-term reductions during COVID-19 lockdowns,highlighting the dominant influence of traffic.Seasonal patterns persisted,with winter concentrations 1.9 times greater than summer levels,and spatial analysis revealed strong NO_(2) heterogeneity among monitoring sites.Machine learning models performed substantially better than linear regression(R^(2)=0.475 vs.0.29),and SHAP analysis showed ozone,boundary layer height,and temperature as the main drivers of NO_(2) variations.Overall,the findings confirm substantial air-quality improvements while revealing nonlinear processes in urban pollution dynamics,supporting continued emission-reduction policies and enhanced monitoring strategies.
