Integrating Chemical Mass Balance and the Community Multiscale Air Quality models for source identification and apportionment of PM2.5

Exploring ozone formation rules and concentration response to the change of precursors based on artificial neural network simulation in a typical industrial park

“…After optimizing the parameters, the number of neural units in the hidden layer was adjusted. The simulation performances [ 3 , 18 ] of the finally optimized ANNs were evaluated by R-square (R 2 ), mean squared error (MSE), mean absolute error (MAE), and the sum of squares due to error (SSE), as shown in Eqs. (4)–(7) .…”

“…Meanwhile, the State Council requires governments at all levels to promote the action of withdrawing from the city and entering the park , resulting in enhanced production concentration within these parks alongside intensified pollutant emissions [ [8] , [9] , [10] , [11] ]. The atmospheric condition in industrial parks is different with that in relatively low polluted areas, due to the characterization of small-scale, dense enterprises and various chemical and complex production processes [ [12] , [13] , [14] ], as well as the intermittent and fugitive emissions of VOCs [ 15 , 16 ] and the inevitable emissions of NO X [ 17 , 18 ], resulting in more complex in O 3 formation rules [ 19 ].…”

Complex Real-Time Monitoring and Decision-Making Assistance System Based on Hybrid Forecasting Module and Social Network Analysis

“…Looking back at past studies, researchers have created prediction models based on physical, statistical, machine learning and deep learning. Physical models can obtain theorybased accuracy by simulating physical processes such as the production and diffusion of pollutant gases [16,17]. However, their strict assumptions, specific environments and long-term observations make the models severely limited in their application.…”

PM<sub>2.5</sub> Source Apportionment using Organic Marker-based CMB Modeling: Influence of Inorganic Markers and Sensitivity to Source Profiles

“…The information on the impacting sources can play an important role in designing effective PM2.5 reduction strategies. Many studies have estimated the potential source contributions to PM2.5 in megacities using various methods, such as receptor models (Lu et al, 2018;Wang et al, 2013;Perrone et al, 2012;Mor et al, 2021;Song et al, 2021;Zhang et al, 2021a), and air quality models (Clappier et al, 2015;Zhang et al, 2017;Li et al, 2020a;Guan et al, 2021). Among the receptor models, the chemical mass balance (CMB) model approach has been used for source apportionment of PM at many locations, worldwide (Zheng et al, 2002;Perrone et al, 2012;Yin et al, 2015;Chen et al,2015;Lu et al, 2018;Wu et al, 2020;Wong et al, 2021).…”