Search

Air pollution poses a grave threat to human health and everyday life. Accurate air-quality prediction plays a crucial role in effectively preventing and controlling air pollution. A multi-graph spatial-temporal attention network is proposed to predict the air quality in a given area by analyzing the interconnections between stations and the individual characteristics of each station. Firstly, this paper constructs multi-scale spatial-temporal graphs from spatial and temporal perspectives to effectively capture the interconnections between stations, thereby comprehensively understanding the spatial-temporal relationships among them. Secondly, incorporating the nonlinear temporal correlation of station data, this paper proposes a temporal multi-graph attention-fusion module to integrate information from both neighboring stations and the station itself. Finally, predictions are made using a spatial-temporal graph network. The experiments in this paper were based on air-quality data from Beijing and Tianjin, and the following experimental results were obtained. (1) The proposed model outperforms the baselines significantly in both single-step and multi-step prediction tasks. (2) The ablation study confirms that the graph constructed in this paper contributes to improving the performance of the model. (3) Comparing the performance of attention components, the proposed attention mechanism exhibits better performance than other attention mechanisms. [ABSTRACT FROM AUTHOR]

The profound impacts of severe air pollution on human health, ecological balance, and economic stability are undeniable. Precise air quality forecasting stands as a crucial necessity, enabling governmental bodies and vulnerable communities to proactively take essential measures to reduce exposure to detrimental pollutants. Previous research has primarily focused on predicting air quality using only time-series data. However, the importance of remote-sensing image data has received limited attention. This paper proposes a new multi-modal deep-learning model, Res-GCN, which integrates high spatial resolution remote-sensing images and time-series air quality data from multiple stations to forecast future air quality. Res-GCN employs two deep-learning networks, one utilizing the residual network to extract hidden visual information from remote-sensing images, and another using a dynamic spatio-temporal graph convolution network to capture spatio-temporal information from time-series data. By extracting features from two different modalities, improved predictive performance can be achieved. To demonstrate the effectiveness of the proposed model, experiments were conducted on two real-world datasets. The results show that the Res-GCN model effectively extracts multi-modal features, significantly enhancing the accuracy of multi-step predictions. Compared to the best-performing baseline model, the multi-step prediction's mean absolute error, root mean square error, and mean absolute percentage error increased by approximately 6%, 7%, and 7%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, a vehicle track coupling dynamic model including bearing outer ring defects is built, the time history of the axle‐box vibration acceleration and the time history of the bearing roller‐outer raceway contact load under the condition of random track irregularity on the Beijing‐Tianjin line are obtained by simulation calculation. The results show that when the outer ring defect of the bearing occurs, the axle box will generate high‐frequency vibration at the resonance peak in the vertical and lateral directions. When the defect on the bearing outer ring is in the small width of 1 mm, the roller only imposes one impact when passing through the defect area. However, when the width exceeds 3 mm, the large defect causes the roller to impose a double impact on the lateral direction of the axle box, due to changes in bearing clearance in the passing‐through process. When the running speed of the train is about 250 km h−1, the width of bearing outer ring defects needs to be limited to within 1 mm, to minimize a series of problems such as structural fatigue caused by the increased bearing roller‐outer raceway contact load caused by bearing outer ring defects. [ABSTRACT FROM AUTHOR]

Currently, ozone pollution is one of the key environmental concerns, and to provide more effective strategies for ozone control, this paper proposes the use of the Geostationary Environmental Monitoring Spectrometer (GEMS) in conjunction with MAX-DOAS for observations and ozone sensitivity analysis. Compared to traditional polar-orbiting satellites, GEMS, launched by South Korea in 2019, offers superior spatiotemporal resolution. However, there is a lack of ground validation for GEMS data related to ozone and its precursors. In this study, we conducted validation in the Jing-Jin-Ji (Beijing-Tianjin-Hebei) region using two typical MAX-DOAS sites and the China National Environmental Monitoring Center (CNEMC) sites, confirming the accuracy of GEMS data. Analysis of the seasonal horizontal distribution results from GEMS and vertical distribution results from MAX-DOAS in 2022 reveals that the concentrations of NO 2 , HCHO, O 3 , and ozone sensitivity not only display seasonality and regional variations but also exhibit distinct characteristics at different altitudes and times, influenced by local climatic conditions, human activities, and topography. When formulating ozone control policies, it becomes imperative to consider factors such as time, regional characteristics, and seasonality. Comparisons between daily results from TROPOMI and GEMS indicate that polar-orbiting satellites may overlook high-pollution periods within a single day, and their measurements may not provide a comprehensive representation of an entire day's data. Consequently, relying solely on polar-orbiting satellite data for shaping ozone prevention and control policies may inadvertently encourage ozone formation during specific time periods, rendering these policies ineffective. Therefore, leveraging GEMS is essential for the development of comprehensive, around-the-clock ozone control policies. Finally, we used monitoring data from Beijing on October 6, 2022, to illustrate how the combination of GEMS and MAX-DOAS enables three-dimensional monitoring of pollutant transport processes on an hourly scale. [Display omitted] • Validation of the accuracy of ozone and its precursor data from GEMS. • Analysis of hourly ozone sensitivity level distribution using GEMS. • Limitations of polar orbit satellites in O 3 sensitivity analysis compared to GEMS. • Observation of the transport of pollutants combining GEMS and MAX-DOAS. [ABSTRACT FROM AUTHOR]