Novel approach for identifying VOC emission characteristics based on mobile monitoring platform data and deep learning: Application of source apportionment in a chemical industrial park.

Refined volatile organic compound (VOC) emission characteristics are crucial for accurate source apportionment in chemical industrial parks. The data from mobile monitoring platforms in chemical industrial parks contain pollution information that is not intuitively displayed, requiring further excavation. A novel approach was proposed to identify VOC emission characteristics using the class activation map (CAM) technology of convolutional neural network (CNN), which was applied on the mobile monitoring platform data (MD) derived from a typical fine chemical industrial park. It converts a large amount of monitoring data with high spatiotemporal complexity into simple and interpretable characteristic maps, effectively improving the identification effect of VOC emission characteristics, supporting more accurate source apportionment of VOC pollution around the park. Using this method, the VOC emission characteristics of eight key factories were identified. VOC source apportionment in the park was conducted for one day using a positive matrix factorization (PMF) model and seven combined factor profiles (CFPs) were calculated. Based on the identified VOC emission characteristics, the main pollution sources and their contributions to surrounding schools and residential areas were determined, revealing that one pesticide factory (named LKA) had the highest contribution ratio. The source apportionment results indicated that the impact of the chemical industrial park on the surrounding areas varied from morning to afternoon, which to some extent reflected the intermittent production methods employed for fine chemicals.

A supplementary assessment system of AQI-V for comprehensive management and control of air quality in chemical industrial parks.

Volatile organic compounds (VOCs) are the dominant pollutants in industrial parks. However, they are not generally considered as part of the air quality index (AQI) system, which leads to a biased assessment of pollution in industrial parks. In this study, a supplementary assessment system of AQI-V was established by analyzing VOCs characteristics with vehicle-mounted PTR-TOFMS instrument, correlation analysis and the standards analysis. Three hourly and daily scenarios were considered, and the hierarchical parameter setting was further optimized by field application. The hourly and daily assessments revealed the evaluation factors for the discriminability of different air quality levels, practiced value for regional air quality improvement, and the reservation of general dominant pollutants. Finally, the universality testing in ZPIP successfully recognized most of the peaks, with 54.76%, 38.39% and 6.85% for O3, VOCs and NO2 as the dominant pollutant, and reflected the daily ambient air quality condition, together with the dominant pollutant. The AQI-V system with VOCs sub-index is essential for air quality evaluation in industrial parks, which can further provide scientific support to control the pollution of VOCs and the secondary pollutant, therefore significantly improve the air quality in local industrial parks.

A novel approach for VOC source apportionment combining characteristic factor and pattern recognition technology in a Chinese industrial area.

Volatile organic compound (VOC) emission control and source apportionment in small-scale industrial areas have become key topics of air pollution control in China. This study proposed a novel characteristic factor and pattern recognition (CF-PR) model for VOC source apportionment based on the similarity of characteristic factors between sources and receptors. A simulation was carried out in a typical industrial area with the CF-PR model involving simulated receptor samples. Refined and accurate source profiles were constructed through in situ sampling and analysis, covering rubber, chemicals, coating, electronics, plastics, printing, incubation and medical treatment industries. Characteristic factors of n-undecane, styrene, o-xylene and propane were identified. The source apportionment simulation results indicated that the predicted contribution rate was basically consistent with the real contribution rate. Compared to traditional receptor models, this method achieves notable advantages in terms of refinement and timeliness at similar accuracy, which is more suitable for VOC source identification and apportionment in small-scale industrial areas.