Modelling driving factors of PM2.5 concentrations in port cities of the Yangtze River Delta

Hourly PM2.5 concentration prediction for dry bulk port clusters considering spatiotemporal correlation: A novel deep learning blending ensemble model

Accurate prediction of PM2.5 concentrations in ports is crucial for authorities to combat ambient air pollution effectively and protect the health of port staff. However, in port clusters formed by multiple neighboring ports, we encountered several challenges owing to the impact of unique meteorological conditions, potential correlation between PM2.5 levels in neighboring ports, and coupling influence of background pollutants in city zones. Therefore, considering the spatiotemporal correlation among the factors influencing PM2.5 concentration variations within the harbor cluster, we developed a novel blending ensemble deep learning model. The proposed model combined the strengths of four deep learning architectures: graph convolutional networks (GCN), long short-term memory networks (LSTM), residual neural networks (ResNet), and convolutional neural networks (CNN). GCN, LSTM, and ResNet served as the base models aimed at capturing the spatial correlation of PM2.5 concentrations in neighboring ports, the potential long-term dependence of meteorological factors and PM2.5 concentrations, and the effects of urban ambient air pollutants, respectively. Following the blending ensemble technique, the prediction outcomes of three base models were used as the input data for the meta-model CNN, which employs the blending ensemble technique to produce the final prediction results. Based on actual data obtained from 18 ports in Nanjing, the proposed model was compared and analyzed for its prediction performance against six state-of-the-art models. The findings revealed that the proposed model provided more accurate predictions. It reduced mean absolute error (MAE) by 10.59 %-20.00 %, reduced root mean square error (RMSE) by 13.22 %-17.11 %, improved coefficient of determination (R2) by 10 %-35.38 %, and improved accuracy (ACC) by 3.48 %-7.08 %. Additionally, the contribution of each component to the prediction performance of the proposed model was measured using a systematic ablation study. The results demonstrated that the GCN model exerted the most substantial influence on the prediction performance of the GCN-LSTM-ResNet model, followed by the LSTM model. The influence of urban background pollutants can significantly enhance the generalizability of the complete model. Moreover, a comparison with three blended ensemble models incorporating any two base models demonstrated that the GCN-LSTM-ResNet model exhibited superior prediction performance and was particularly excellent in predicting the occurrence of high-concentration events. Specifically, the GCN-LSTM-ResNet model improved MAE and RMSE by at least 12.3% and 9.2%, respectively, but reduced R2 and ACC by 26.1% and 6.8%, respectively. The proposed model provided reliable PM2.5 concentration prediction outcomes and decision support for air quality management strategies in dry bulk port clusters.

Ports and their influence on local air pollution and public health: A global analysis

Despite the skyrocketing growth in recent decades of environmental studies on ports and shipping, their local health impacts remain largely under-researched. This article tackles this gap in research by statistically analyzing data on global shipping flows across nearly 5000 ports in 35 OECD countries between 2001 and 2018. The different traffic types, from containers to bulk and passengers, are analyzed jointly with data on natural conditions, air pollution, socio-economic indicators, and public health. The principal results show that port regions pollute more than non-port regions on average, while health impacts vary according to the size and specialization of the port region. Three types of port regions are clearly differentiated: industrial, intermediate, and metropolitan port regions.

Spatiotemporal heterogeneity of the relationships between PM2.5 concentrations and their drivers in China's coastal ports

PM2.5 is one of the primary air pollutants that affect air quality and threat human health in the port areas. To prevent and control air pollution, it is essential to understand the spatiotemporal distributions of PM2.5 concentrations and their key drivers in ports. 19 coastal ports of China are selected to examine the spatiotemporal distributions of PM2.5 concentrations during 2013-2020. The annual average PM2.5 concentration decreases from 61.03 μg/m3 to 30.17 μg/m3, with an average decrease rate of 51.57%. Significant spatial autocorrelation exists among PM2.5 concentrations of ports. The result of the geographically and temporally weighted regression (GTWR) model shows significant spatiotemporal heterogeneity in the effects of meteorological and socioeconomic factors on PM2.5 concentrations. The effects of boundary layer height on PM2.5 concentrations are found to be negative in most ports, with a stronger effect found in the Pearl River Delta, Yangtze River Delta and some ports of the Bohai Rim Area. The total precipitation shows negative effects on PM2.5 concentrations, with the strongest effect found in ports of the Southeast Coast. The effects of surface pressure on PM2.5 concentrations are positive, with stronger effects found in Beibu Gulf Port and Zhanjiang Port. The effects of wind speed on PM2.5 concentrations generally increase from south to north. Cargo throughput shows strong and positive effects on PM2.5 concentrations in ports of Bohai Rim Area; the positive effects found in Beibu Gulf Port increased from 2013 to 2018 and decreased since 2019. The positive effects of GDP and nighttime light on PM2.5 concentrations gradually decrease and turn negative from south to north. Understandings obtained from this study can potentially support the prevention and control of air pollution in China's coastal ports.

Heavy vehicles' non-exhaust exhibits competitive contribution to PM2.5 compared with exhaust in port and nearby areas

Heavy port transportation networks are increasingly considered as significant contributors of PM2.5 pollution compared to vessels in recent decades. In addition, evidence points to the non-exhaust emission of port traffic as the real driver. This study linked PM2.5 concentrations to varied locations and traffic fleet characteristics in port area through filter sampling. The coupled emission ratio-positive matrix factorisation (ER-PMF) method resolves source factors by avoiding direct overlap from collinear sources. In the port central and entrance areas, freight delivery activity emissions including vehicle exhaust and non-exhaust particles, as well as induced road dust resuspension, accounted for nearly half of the total contribution (42.5%-49.9%). In particular, the contribution of non-exhaust from denser traffic with high proportion of trucks was competitive and equivalent to 52.3% of that from exhaust. Backward trajectory statistical models further interpreted the notably larger-scale coverage of non-exhaust emissions in the port's central area. The distribution of PM2.5 were interpolated within the scope of the port and nearby urban areas, displaying the potential contribution of non-exhaust within 1.15 μg/m3-4.68 μg/m3, slightly higher than the urban detections reported nearby. This study may provide useful insights into the increasing percentage of non-exhaust from trucks in ports and nearby urban areas and facilitate supplementary data collection on Euro-VII type-approval limit settings.

Assessing the impact of COVID-19 on air pollutant emissions from vessels in Lianyungang Port

The COVID-19 has had a particularly significant impact on the shipping industry. Using AIS data, a "bottom-up" method was adopted to investigate whether the removal of port-imposed prevention regulations would affect ship activity and ship emissions in Lianyungang Port. The study discovered that, except for passenger ships, the total number of other ships has increased significantly, with tugs, tankers/chemical vessels, ROROs and work boats ranking among the top four. After the regulations were removed, the average normal cruising time per vessel increased from 12.23 to 20.05 h, an increase of 63.94 %, while the average operating time per vessel during slow cruising, maneuvering and hotelling decreased. Meanwhile, the total emissions of air pollutants from vessels have increased by >60 %. Relevant departments need to pay more attention to NOx and develop feasible policies to reduce emissions from especially cargo vessels, tankers and chemical vessels.

Spatiotemporal variations of NO2 and its driving factors in the coastal ports of China

Nitrogen Dioxide (NO₂) is one of the major air pollutants in coastal ports of China. Understanding the spatiotemporal varying effects of driving factors of NO₂ is vital for the implementation of differentiated air pollution control measures for different port areas. Based on the Ozone Monitoring Instrument (OMI) satellite data, we adopted a Geographically and Temporally Weighted Regression (GTWR) model to explore the influences of meteorological and socioeconomic factors on the NO₂ Vertical Column Concentrations (VCDs) in coastal ports of China from 2015 to 2021. The results indicate that NO₂ VCD in most ports has decreased since 2016 and the ports with serious NO₂ pollution are mainly distributed in northern China. The associations between NO₂ VCD levels and their drivers exhibit obvious spatiotemporal heterogeneity. Higher wind speed and relative humidity are more helpful to alleviate NO₂ pollution in ports of the Bohai Rim and the Pearl River Delta. Cargo throughput has more closely associated with NO₂ pollution in Beibu Gulf in recent years, yet there is no significant association found for Shanghai ports. The positive relationship between transportation emissions and NO₂ VCD is more significant in southern ports. This work provides some implications for the formulation of targeted emission reduction policies for different ports along the Chinese coast.