Typical Station Research Articles

Optimal redesign of a salinity monitoring network in Barataria Basin, Louisiana, USA using discrete entropy theory

We use discrete entropy theory and the MaxT model to optimize a continuous salinity monitoring network in a coastal Louisiana estuary (71 stations, 5 station types). Four station types represent marsh zones based on plant tolerance to salinity: fresh, intermediate, brackish, and saline. The fifth station type include stations in open water spanning the entire estuarine salinity gradient. A dry year (2012) with reduced freshwater inputs, and a wet year (2019) were chosen to test the robustness of the model. Our analysis showed that thirty-one stations formed the core network for both water years, with an additional 12 (2012) and 14 (2019) stations, unique for each year, needed to capture the optimal information for salinity in all five habitats. Fourteen stations could be eliminated with minimal loss of information regardless of whether the estuary was under drought or excess freshwater conditions. The Nash-Sutcliffe coefficient (ENs), coefficient of determination (R2) and the relative error (RE) showed good to excellent agreement between salinity measured by the original network and the modeled salinity of the modified network. Discrete entropy theory and MaxT proved effective in identifying redundancies in information sufficient to allow a 20% reduction of stations. Considering the highly variable nature of salinity within an estuary over short- and long-term temporal scales within a particular geographic location and across the entire estuary, this result was unexpected. Further reductions in stations (and corresponding savings in resources and costs) will require approaches not focused on replicating the exact information content from station to station but rather on measuring those salinity patterns and thresholds that shape biotic resource response in an estuary and possibly a reformulation of monitoring objectives. Monitoring objectives should include sampling for parameters (e.g., suspended sediments and nutrients) that don't require continuous data and are less costly to sustain yet provide equally critical information for understanding coastal wetland habitat sustainability and restoration.

Air pollution assessment in Seoul, South Korea, using an updated daily air quality index

The variability of daily air quality index DAQx* was analyzed for types of air quality monitoring stations (AQMSs) in Seoul, South Korea, from 2018 to 2021. Daily maximum 1-h means of O3 and NO2 and daily 24-h means of PM10 and PM2.5 from 42 AQMSs were used to calculate the DAQx*. The frequencies of DAQx* values in DAQx* classes 3 (satisfactory) and 4 (sufficient) dominated for all station types, followed by DAQx* class 5 (poor). The variability of DAQx* values within station types mostly corresponded approximately to one DAQx* class, with mean frequencies of 82% for roadside, 81% for urban, and 72% for background stations. Lower air pollution levels on weekends than weekdays were shown for roadside stations by frequencies of DAQx* values in classes 3 (11% higher) and 4 (12% lower) during summer. NO2 was the air pollutant that annually most frequently formed DAQx* at roadside (48%) and urban (32%) stations, while O3 was the dominant pollutant (38%) at background stations. In winter, PM10 was the most common contributor to the DAQx* (at least 47%) at all station types. The dominant air pollutants in summer were NO2 at roadside stations (72%) and O3 at urban (63%) and background (68%) stations. Air quality improvement during a stronger social distancing period in 2020 due to the COVID-19 pandemic was evidenced by higher frequencies in DAQx* class 3 (up to 26%) but lower frequencies in DAQx* class 4 (up to 24%) than that during the reference period, especially for the roadside stations.

DATA MANAGEMENT FROM MOBILE METEOROLOGICAL STATIONS FOR GENERAL AVIATION AND STATE INTEGRATED RESCUE SYSTEM

The article deals with the problem of obtaining objective meteorological information for general aviation, which also includes the aviation component of the Integrated Rescue System of the Slovak Republic. The article aims to present a possible solution to the insufficient meteorological coverage of various parts of Slovakia, which would be inexpensive, and easy to install, with the possibility of subsequent sharing of data for the needs of the decision-making process in the environment of crisis management in emergencies, and at the same time would provide relevant data in normal aviation practice. The article identifies the specific needs of general aviation meteorological assurance based on the prevailing mode of flying in this segment of aviation. Based on this analysis, the article's authors describe the meteorological system used for educational purposes at the Aviation Faculty of the Technical University in Košice and propose a system for processing and further managing meteorological data obtained from this type of meteorological station. At the same time, the article mentions data-flow management, which ensures the sharing of data with other airspace users, which adds socio-economic benefits to the entire system in the form of increasing the level of flight safety and more efficient planning of flight routes. The article also deals with the case of providing crisis management, and metrological information from critical places, namely the operational deployment of mobile meteorological devices in areas with a declared emergency.

Modeling interactions between the Montreal subway and other urban transportation modes at the station level

Subway systems are an example of how underground space can contribute to developing more sustainable cities. Their use can be encouraged by integrating other urban transportation modes to provide easy access to the stations, thus facilitating intermodal connectivity. However, few studies have addressed data and modeling issues with multiple modes. This gap, mainly due to the lack of appropriate methods, explains why relationships between traditional and emerging modes remain poorly understood; there is still debate about whether they are complementary or competitive. This paper investigates this question by examining interactions between three alternative modes (bikesharing, free-floating carsharing and taxi) and the Montreal (Quebec, Canada) subway over two months. To this end, several operational passive datasets are merged. A two-level growth model, including both fixed and random effects, is then developed based on time series of daily numbers of boardings at subway stations. This longitudinal model quantifies the effect of various variables (calendar, weather, socio-demographic and economic, network connectivity, land use and built environment attributes) on each station use. The correlations between subway boardings and alternative mode destinations are also measured to detect potential intermodal relations. Finally, a further categorical analysis is conducted by period and station type to specify these interactions in time and space. Results reveal that alternative modes tend to complement the subway in the network periphery (as possible access mode to the subway stations), but may compete with the subway in areas closer to the city center. Such findings could help policymakers determine the location of the mobility services to enhance first-mile subway access, as well as the best mode integration around subway stations in planning strategies.

How to Measure the Impact of Walking Accessibility of Suburban Rail Station Catchment Areas on the Commercial Premium Benefits of Joint Development

As the primary solution to the issue of high passenger traffic in urban areas, rail transit has a significant impact on the structural form of cities and regional development. Additionally, it has varying degrees of a premium effect on land value around stations. Current research on the factors influencing the premium effect of rail transit station areas mainly focuses on the macro level of the station area circle, with more attention given to the premium caused by distance and functional differences. Most research objects are typically urban center lines or stations. However, this study focuses on the core area of the station and concentrates on the impact of the construction of integrated station–city facilities on the choice of pedestrian routes and the enhancement of pedestrian accessibility. It also explores whether this enhancement is associated with the premium benefits of ancillary commercial development. To achieve this goal, this paper integrates models from several related studies to conduct a comprehensive assessment. Firstly, it uses a spatial panel econometric model to improve the classical characteristic price method model. It then combines the ideas and models of the cost–benefit analysis method, taking the Odakyu Odawara Line of the Japanese suburban railroad as an example. This analysis explores the mechanism and factors influencing the rent premium of commercial facilities in the suburban rail station area and systematically assesses the combined station–city facilities. The study evaluates the social benefits (enhanced walkability) and economic value (premium value added from commercial facilities) of the combined station–city facilities systematically. The results of the study show that (1) the premium benefits of suburban railroad station area commercial facilities are significantly related to the type of station–city combination facilities, combination mode, and walking time and weakly related to the location factor. Additionally, (2) the results of the cost–benefit valuation analysis based on the Ebina Station verify that a reasonable design of station–city combination facilities can effectively enhance the proximity of commercial facilities to the station and improve the walking accessibility, thus promoting the premium benefits. The study demonstrates that a reasonable design of the combined station and city facilities can effectively enhance the proximity of commercial facilities to the station and improve pedestrian accessibility, promoting premium benefits, which can quickly feed the construction cost of the station and achieve positive revenue in the short term. Therefore, the results of the study provide a quantitative reference for the planning and design of suburban stations.

Classification and Development Potential Evaluation of Urban Metro Station Areas Based on Extended Node-Place Model-- A case study of Nanjing Metro Line 1

In the process of changing from the extensive mode to the compact mode of the urban space development in China, metro has solved the problem of high-capacity and rapid transportation in cities. The planning of metro stations needs to be investigated in the context of station types in the process of the urban development. In the research, combined with the development examples of stations and surrounding areas along Nanjing Subway Line 1, the factors such as the classification of station types, the current development potential assessment and so on were investigated based on the extended "node-place" model. And then the scientific and reasonable optimization and adjustment strategies for stations and surrounding areas were proposed, which provides reference for the subsequent planning strategies and development and construction of metro stations and surrounding areas.

A Hybrid Deep Learning Model for Multi-Station Classification and Passenger Flow Prediction

Multiple station passenger flow prediction is crucial but challenging for intelligent transportation systems. Recently, deep learning models have been widely applied in multi-station passenger flow prediction. However, flows at the same station in different periods, or different stations in the same period, always present different characteristics. These indicate that globally extracting spatio-temporal features for multi-station passenger flow prediction may only be powerful enough to achieve the excepted performance for some stations. Therefore, a novel two-step multi-station passenger flow prediction model is proposed. First, an unsupervised clustering method for station classification using pure passenger flow is proposed based on the Transformer encoder and K-Means. Two novel evaluation metrics are introduced to verify the effectiveness of the classification results. Then, based on the classification results, a passenger flow prediction model is proposed for every type of station. Residual network (ResNet) and graph convolution network (GCN) are applied for spatial feature extraction, and attention long short-term memory network (AttLSTM) is used for temporal feature extraction. Integrating results for every type of station creates a prediction model for all stations in the network. Experiments are conducted on two real-world ridership datasets. The proposed model performs better than unclassified results in multi-station passenger flow prediction.

Identifying metro station types based on transfer purposes: An application of bike‐sharing data in Xiamen, China

AbstractWith the networking of urban rail transit and the large‐scale development of bike‐sharing, metro and bike‐sharing connection has become the preferred way of daily travel for residents of Xiamen. Current studies mainly identify metro station types based on node and place orientation, lacking behaviour‐based investigation. To fill this gap, this study aims to explore the classification of metro stations based on transfer purposes by combining bike‐sharing and point of interest data in Xiamen, using buffer analysis, kernel density estimation, and DBSCAN clustering algorithm comprehensively. The results indicate the following. (1) Distinct transfer purposes have significant agglomeration characteristics and present poly‐centric spatial pattern, an authentic portrayal of Xiamen's land use function. (2) The heterogeneity of connection flow between different transfer purposes and metro stations is apparent. The distribution of flow and flow direction within the same transfer purpose is also in non‐equilibrium. (3) Based on traffic connection analysis, metro stations are divided into seven types: transportation hub, employment‐oriented, residence‐oriented, job‐housing balance, school‐oriented, traffic‐tourism integration, and business connection types. The obtained results assist in improving the transportation connection environment, perfecting urban land use planning, and enhancing low‐carbon and green travel.

Pay cycles and gasoline price: When low-cost and independent stations take advantage of the needy

This paper analyses the daily price behaviour of different types of gasoline stations in the presence of potential temporary demand shocks caused by an increased availability of disposable income, generated by the payment of a subsidy to a specific part of the population (the unemployed). Using 2015–2016 Spanish data on daily fuel prices and a difference-in-difference approach, we show that independent and low-cost gasoline stations take advantage of the neediest consumers. We find that their prices increase on the day the unemployed receive the government subsidy, while, on the same day, major branded companies decrease their prices. This phenomenon underlines the effect of payment cycles on consumer choices and their economic impact. The paper fills an important gap in the knowledge of how gasoline stations strategically exploit the income patterns of low-income motorists. The findings are also relevant for antitrust and for industry regulators, who generally focus on the activities of major branded gasoline stations, giving less emphasis to the activities of other operators, which also cover significant market shares.

Irrigation mitigates the heat impacts on photosynthesis during grain filling in maize

Elevating soil water content (SWC) through irrigation was one of the simple mitigation measures to improve crop resilience to heat stress. The response of leaf function, such as photosynthetic capacity based on chlorophyll fluorescence during the mitigation, has received limited attention, especially in field conditions. A two-year field experiment with three treatments (control treatment (CK), high-temperature treatment (H), and high-temperature together with elevating SWC treatment (HW)) was carried out during grain filling with two maize hybrids at a typical station in North China Plain. Averagely, the net photosynthetic rate (Pn) was improved by 20%, and the canopy temperature decreased by 1–3°C in HW compared with in H in both years. Furthermore, the higher SWC in HW significantly improved the actual photosynthetic rate (Phi2), linear electron flow (LEF), variable fluorescence (Fv), and the maximal potential quantum efficiency (Fv/Fm) for both hybrids. Meanwhile, different responses in chlorophyll fluorescence between hybrids were also observed. The higher SWC in HW significantly improved thylakoid proton conductivity (gH+) and the maximal fluorescence (Fm) for the hybrid ZD958. For the hybrid XY335, the proton conductivity of chloroplast ATP synthase (vH+) and the minimal fluorescence (Fo) was increased by the SWC. The structural equation model (SEM) further showed that SWC had significantly positive relationships with Pn, LEF, and Fv/Fm. The elevating SWC alleviated heat stress with the delayed leaf senescence to prolong the effective period of photosynthesis and enhanced leaf photosynthetic capacity by improving Phi2, LEF, Fv, and Fv/Fm. This research demonstrates that elevating SWC through enhancing leaf photosynthesis during grain filling would be an important mitigation strategy for adapting to the warming climate in maize production.

EFFECT OF ABATTOIR WASTE ON THE PHYSICO-CHEMICAL AND FAECAL COLIFORM LOAD OF SURFACE AND UNDERGROUND WATER BODIES IN UGHELLI, DELTA STATE

This study aimed to evaluate the effects of effluent from the Ogheneweta abattoir on the physico-chemical and faecal coliform load of surface and underground water surrounding the abattoir. The study compared the water quality parameters with the guidelines provided by the Federal Ministry of Environment (FMENV) and the World Health Organization (WHO). The research involved the determination of various factors, including physico-chemical characteristics, microbial activity, and spatial and seasonal variations of water. Four sampling stations were selected for the study, with two focusing on groundwater impact and the other two on surface water impact. Differences between the two types of stations were also analyzed. Field sampling was conducted over a nine-month period, and water quality parameters such as temperature, pH, dissolved oxygen, turbidity, biochemical oxygen demand, and faecal coliform load were measured. Standard methods and instruments were utilized for sample collection and analysis, following established water analysis procedures. Statistical analysis was performed using a paired sample T-test (P<0.05). The results indicated that water temperature ranged from 25.56oC to 27.78oC, pH from 6.52 to 7.11, total dissolved solids (TDS) from 10.67mg/l to 210.78mg/l, electrical conductivity (EC) from 20.95mg/l to 426.05mg/l, dissolved oxygen (DO) from 4.17mg/l to 4.72mg/l, turbidity from 1.95mg/l to 9.67mg/l, and biochemical oxygen demand (BOD) from 1.33mg/l to 1.74mg/l. Faecal coliform counts in underground and surface water samples ranged from 2.00 to 2.22MPN/100L and 2.67 to 7.33MPN/100L, respectively. The study findings revealed that the abattoir activities had a negative impact on the quality of both surface and underground water within the Ogheneweta abattoir area. While most physico-chemical and microbial parameters adhered to FMENV and WHO guidelines, the concentrations of turbidity in surface water and faecal coliform in both surface and underground water exceeded the acceptable limits. Moreover, the study showed distinct seasonal variations in physico-chemical parameters, with higher values recorded for pH, TDS, and turbidity during the rainy season, and lower values observed for conductivity. Based on the results, it is recommended that a groundwater monitoring program be implemented to assess the water quality status of wells near abattoirs, ensuring the protection of local residents’ health. Prompt intervention measures, including the establishment of effluent treatment facilities, are essential for effective waste management at abattoirs in Ughelli.

Acoustic comfort at Kyiv metro stations

Kyiv Metro was opened in 1960 and became the first metro system in Ukraine. From then until the beginning of the 21st century it was developing without considering the acoustic comfort of its passengers and employees. Increased levels of noise and vibration in public transport are mostly ignored, although they are certainly recognized as the reasons for increasing the harmfulness of work for metro employees. The present report analyzes noise levels at metro stations depending on their design features. There are several main types of stations in the Kyiv metro: deep-lying, shallow-lying, as well as above-ground stations. For all types of underground stations, there are options both with and without sound-absorbing finishes. Also, during the construction of the newest stations of the Kyiv metro, vibration isolation systems were used for the construction of the permanent way were used. Within this study, sound pressure levels were measured on the platform at stations of various types. These measurements made it possible to establish a significant influence of the shape of the station vestibule, the presence of sound-absorbing finishes in it, as well as the vibration isolation of the permanent way, on the objective and subjective parameters of acoustic comfort for passengers and employees of the subway.

Analyzing the Occupied Space of Passengers with Reduced Mobility in Metro Station Platforms: An Experimental Approach Using a Tracking System

The objective of this study is to analyze the occupied space of passengers with reduced mobility when boarding or alighting a train through an experimental approach based on a virtual tracking tool system to obtain their exact position. The designed experiments considered a train and its adjacent platform, in which 21 volunteers were recruited, 3 with reduced mobility. The results indicated that passengers with reduced mobility required up to 80% more space, compared to a passenger without reduced mobility, when waiting to board the train. The passenger who occupied the largest space was the one with a pram, reaching 1.70 m2/passenger, represented as a polygon. In addition, when passengers started to walk, the space used increased due to limb movement. In the alighting process, passengers with reduced mobility used almost twice the space required for the boarding process due to the relatively larger platform space occupied as each passenger alights and walks away, whereas when boarding, each passenger has less space to share with the other people waiting for the train to arrive or for the doors to open. These results could help practitioners improve the design of the platform or implement control measures, such as adding waiting areas for those passengers with reduced mobility. Further research is needed regarding other types of stations and density situations.

A Mixed-Integer Linear Programming Model for the Station Capacity Allocation Problem of a Star-Tree Pipe Network

The optimization of the layout of the surface gathering and transportation pipe network in the oil and gas field can effectively reduce the total investment in the pipe network. Currently, based on the constraints of fixed station capacity in the star-tree pipe network topology, hierarchical optimization strategies are often used to optimize the pipe network layout. Aiming at the overall optimization of the layout of the star-tree ground gathering and transportation pipe network, this paper constructs a special mixed-integer linear programming (MILP) mathematical model considering the station capacity allocation problem, which can simultaneously obtain the optimal pipe network topology, pipe connection relationship, station location and quantity, station type, central station [central processing plant (CPP)] location and investment of each part. Numerical analysis of gas fields of different scales is used to discuss the influence of station capacity allocation and different station capacity combinations on the optimization of pipe network layout. The optimization effect of star-tree and star-star pipe network layout is compared and analyzed. The results not only prove the correctness and effectiveness of the model and algorithm proposed in this paper but also reduce the total investment of the pipe network. It can be seen that the optimization scheme has guiding significance for the surface engineering construction of the oil and gas fields.

Common snowdrop as a climate change bioindicator in Czechia

The phenological response to climate change differs among species. We examined the beginning of flowering of the common snowdrop (Galanthus nivalis) in connection with meteorological variables in Czechia in the period 1923-2021. The long-term series were analyzed from phenological and meteorological stations of the Czech Hydrometeorological Institute (CHMI). Temporal and spatial evaluation (using Geographic Information System) in timing of beginning of flowering (BBCH 61) of G. nivalis was investigated under urban and rural settings. Furthermore, the detailed analysis of selected meteorological variables to onset of G. nivalis flowering was performed. Moreover, the trends (using Mann-Kendall test) and Pearson's correlation coefficients between phenological phase and meteorological variable were calculated. The main finding of this study was that the trend of the beginning of flowering of the common snowdrop during the studied period (1923-2021) is negative, and it varies in urban and rural environments. The results showed most significant acceleration of the beginning of flowering of G. nivalis by - 0.20dayyear-1 in urban area and by - 0.11dayyear-1 in rural area. Above that, a major turning point occurred between 1987 and 1988 (both, in phenological observations and meteorological variables), and the variability of the beginning of flowering is significantly higher in the second period 1988-2021. On top of, the study proved that the beginning of flowering of G. nivalis closely correlated with number of days with snow cover above 1cm (December-March) at both types of stations (urban and rural), and with mean air temperature in February, maximum air temperature in January, and minimum air temperature in March. The Mann-Kendall test showed a reduction in the number of days with snow cover above 1cm (December-March) during 99years period at Klatovy station (a long-term time series) by - 0.06dayyear-1, i.e., by - 5.94days per the whole period. Conversely, air temperatures increase (maximum and minimum air temperature by 0.03°Cyear-1 (2.97°C per the whole period) and average air temperature by 0.02°Cyear-1 (1.98°C per the whole period)). Thus, our results indicate significant changes in the beginning of flowering of G. nivalis in Czechia as a consequence of climate change.

Newcomb–Benford Law as a generic flag for changes in the derivation of long-term solar terrestrial physics timeseries

Abstract The Newcomb–Benford Law (NBL) prescribes the probability distribution of the first digit of variables which explore a broad range under conditions including aggregation. Long-term space weather relevant observations and indices necessarily incorporate changes in the contributing number and types of observing instrumentation over time and we find that this can be detected solely by comparison with the NBL. It detects when upstream solar wind magnetic field high resolution OMNI interplanetary magnetic field incorporated new data from the WIND and Advanced Composition Explorer spacecraft after 1995. NBL comparison can detect underlying changes in the geomagnetic auroral electrojet index (activity-dependent background subtraction) and the SuperMAG electrojet index (different station types) that select individual stations showing the largest deflection, but not where station data are averaged, as in the SuperMAG ring-current index. As composite indices become more widespread across the geosciences, the NBL may provide a generic, data processing-independent flag indicating changes in the constituent raw data, calibration, or sampling method.

The whole story: Rumors and science communication in the aftermath of 2012 Emilia seismic sequence

Controversies that stir the public debate on geological matters usually revolve around a few specific aspects, including the actual trigger of geological phenomena (i.e., natural vs. anthropogenic), their predictability, and the trustworthiness of the experts who provide information and advice on the phenomena. A typical example of such difficulties is the case of the 2012 Emilia, Italy, seismic sequence which struck an area of relatively moderate seismic hazard. In that period, geophysical prospecting was planned to assess the potential of a reservoir for gas storage, near the town of Rivara. The low frequency of important seismic events in the area, associated with the ongoing industrial planning prompted widespread rumors of an anthropogenic origin of the 2012 earthquakes. Controversy also arose about the actual size of the seismic events: earthquakes magnitude can be computed with different methods, and its value depends on the type, number, and geographical distribution of the available seismic stations. As a result, different institutions commonly release different estimates of the earthquake magnitude, casting doubts on the reliability of each estimate. Since 2012, public concern has also been caused by the repeated occurrence of unusual phenomena in the area, such as ground heating or bubbling well waters. Popular belief tends to establish a causal link between particular phenomena and seismic activity, reinforcing the false conviction that seismicity could be predicted. In this work we present and discuss some of the activities that INGV pursued through the years to contrast rumors and disseminate correct scientific information. In the aftermath of the 2012 seismic sequence, INGV worked in collaboration with the National Department of Civil Protection, the local administrations, the University Network of seismic engineering, the Regional Healthcare System and local volunteer organizations. The organization of public meetings, the collection and analysis of widespread rumors and the creation of ad hoc outreach materials all contributed to reinforce the mutual trust between our research institute and the local population.

Engine room thermal density specials in heating systems shutdow process

THE PURPOSE. Consider the effect of heating system turning off process on the engine room thermal density in a high-voltage city sewage pumping station. Determine how the heating system shutdown affects to the considered room thermal regimes with unchanged requirements for the indoor air microclimate thermal and moisture parameters. Do a numerical experiment which simulates the stationary thermal regime of engine room and taking into account the main technological process in this room of a high-voltage city sewage pumpingstation. Perform adaptation of thermal regime developed model to simulate the heating system turning off process. Describe the distribution of heat losses in the engine room while maintaining a constant air temperature. METHODS. When solving the task, author has used the method of calculating the engine room design stationary mode.RESULTS. Researcher describes the relevance of the topic, considers the specials of the change in the engine room thermal density when the heating system is turned of and other factors. Author has presented the results of the thermal excesses calculation for different numbers of operating pumps and changes in wastewater temperature.CONCLUSION. The turning off process of the heating system reduces the thermal density of the engine room by an average of 0.3 - 0.4 W/m3. This method of energy saving helps to reduce the consumption of thermal energy and could be used in this part of sewage pumping station. The economical effect of proposed energy saving measurement will be in economical index reducing. It will be 890 000 rubles saving per year for this type of sewage pumping station in designed mode.

A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network

Short-term prediction of urban air quality is critical to pollution management and public health. However, existing studies have failed to make full use of the spatiotemporal correlations or topological relationships among air quality monitoring networks (AQMN), and hence exhibit low precision in regional prediction tasks. With this consideration, we proposed a novel deep learning-based hybrid model of Res-GCN-BiLSTM combining the residual neural network (ResNet), graph convolutional network (GCN), and bidirectional long short-term memory (BiLSTM), for predicting short-term regional NO2 and O3 concentrations. Auto-correlation analysis and cluster analysis were first utilized to reveal the inherent temporal and spatial properties respectively. They demonstrated that there existed temporal daily periodicity and spatial similarity in AQMN. Then the identified spatiotemporal properties were sufficiently leveraged, and monitoring network topological information, as well as auxiliary pollutants and meteorology were also adaptively integrated into the model. The hourly observed data from 51 air quality monitoring stations and meteorological data in Shanghai were employed to evaluate it. Results show that the Res-GCN-BiLSTM model was better adapted to the pollutant characteristics and improved the prediction accuracy, with nearly 11% and 17% improvements in mean absolute error for NO2 and O3, respectively compared to the best performing baseline model. Among the three types of monitoring stations, traffic monitoring stations performed the best for O3, but the worst for NO2, mainly due to the impacts of intensive traffic emissions and the titration reaction. These findings illustrate that the hybrid architecture is more suitable for regional pollutant concentration.

Toward dynamic regulation of bidirectional automatic fare gates: A macro-to-micro simulation approach

While bidirectional automatic fare gates (BAFGs) serve as important tools for mitigating the congestion of passengers in subway stations, most of BAFGs function merely as single-directional automatic fare gates (AFGs) in most cities of China and other countries. This paper proposes a pioneering work on the dynamic regulation problem of BAFGs. We build a macro-to-micro model which simulates the movement of passengers in stations from both the macroscopic and microscopic perspectives. The system dynamics based macromodel simulates the macroscopic movement of passengers in stations, while the social force based micromodel simulates the microscopic movement of passengers. Benefitting from the negative feedback regulation mechanism of the system dynamics, we adjust different number of BAFGs according to the congestion extent of the passenger flow on the platform in the macromodel, and change the pedestrian flowline in the micromodel to ensure that there is no new conflict produced by the regulation scheme. We conduct case studies on Dawanglu station and Jiangtai station, Beijing, China, and propose optimized configurations and dynamic regulation scheme of BAFGs accordingly. The simulation results show that the macro-to-micro model not only significantly improves both the BAFGs’ efficiency and the passengers’ efficiency, but also exhibits a high generalization ability towards different types of subway stations. Our study benefits the subway operation and management, and is conducive to sustainable urban development.