Stations In Beijing Research Articles

Beyond half-mile circle: Measuring the impact of subway expansion on home-based travels in Beijing, China

Subways play an important role in supporting travel needs, yet whether the benefits of subway expansion can justify the substantial investments remains a much-debated question. Existing studies have arbitrarily defined the catchment area of a subway station using walking distance and have disproportionately focused on commuting trips, potentially underestimating broader subway effects. To address these limitations, this study employed the distance-band approach to accurately define the treatment area of subway stations while incorporating both local and network effects. Based on longitudinal mobile signaling data, we used the difference-in-differences approach to estimate the average treatment effects of 32 new subway stations on different types of home-based travels in Beijing, China. We found that the opening of new subway stations has led to significant increases in subway usage, trip duration, and trip distance within a 2000-metre radius, and that commuting trips have been more affected than home-based non-commuting trips, except during the COVID-19 pandemic. Moreover, the new subway stations also enhanced the connectivity of the city-wide network, influencing the travel behavior of residents in the vicinity of existing subway stations. We further found that subway expansion is particularly beneficial for women, younger residents, and residents of low-rent neighborhoods. According to these findings, planning new subway stations in Beijing and other densely populated megacities requires an integrated approach that considers the relationships between the existing transport network and diverse travel demand.

Evaluation of GNSS-TEC Data-Driven IRI-2016 Model for Electron Density

The ionosphere is one of the important error sources that affect the communication of radio signals. The international reference ionosphere (IRI) model is a commonly used model to describe ionospheric parameters. The driving parameter IG12 of the IRI-2016 model was optimally updated based on GNSS-TEC data from 2015 and 2019. The electron density profiles and NmF2 calculated by the IRI-2016 model (upda-IRI-2016) driven by the updated IG12 value (IG-up) were evaluated for their accuracy using ionosonde observations and COSMIC inversion data. The experiments show that both the electron density profiles and NmF2 calculated by upda-IRI-2016 driven by IG-up show significant optimization effects, compared to the IRI-2016 model driven by IG12. For electron density, the precision improvement (PI) for both MAE and RMSE at the Beijing station exceed 31.2% in January 2015 and 16.0% in January 2019. While the PI of MAE and RMSE at the Wuhan station, which is located at a lower latitude, both exceed 32.5% in January 2015, both exceed 42.1% in January 2019, which is significantly higher than that of the Beijing station. In 2015, the PI of MAE and RMSE compared with COSMIC are both higher than 20%. For NmF2, the PI is greater for low solar activity years and low latitude stations, with the Wuhan station showing a PI of more than 11.7% in January 2019 compared to January 2015. The PI compared to COSMIC was higher than 17.2% in 2015.

Enhanced Air Quality Prediction through Spatio-temporal Feature Sxtraction and Fusion: A Self-tuning Hybrid Approach with GCN and GRU

Accurate prediction of air quality change is essential for air pollution control and human daily mobility. Due to the strong spatial and temporal correlation of air quality changes, existing air quality prediction methods often face the problem of low prediction accuracy due to insufficient extraction of spatio-temporal features. In this paper, we proposed a self-tuning spatio-temporal neural network (ST2NN) to enhance air quality prediction. ST2NN model consisted of four modules. First, ST2NN model constructed a temporal feature extraction module and a spatial feature extraction module based on gated recurrent unit (GRU) and graph convolutional neural network (GCN), respectively, and the two feature extraction modules adopted a parallel structure, which could effectively extract the spatio-temporal features in data. Additionally, ST2NN model constructed a feature fusion module based on gating mechanism to delineate the contribution of spatio-temporal features to the predicted values. Further, ST2NN model constructed a Hyperband hyperparameter optimization module based on Hyperband optimization algorithm to automatically adjust the network hyperparameters. The structure of ST2NN model endowed it with excellent spatio-temporal feature extraction and parameter adaptability. ST2NN model was evaluated and compared with existing models, including convolutional long short-term memory neural network (ConvLSTM), GRU, combined convolutional neural network and long short-term memory neural network (CNN-LSTM), and GCN-LSTM for air quality index (AQI) prediction using data from twelve monitoring stations in Beijing, China. Across all four evaluation indexes, ST2NN model outperformed the comparative models, improving prediction accuracy by 0.51%-10.18% (measured using R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document}). From the experimental results, it can be seen that ST2NN model constructed from the perspective of spatio-temporal feature extraction has better prediction performance compared with the existing air quality prediction model, which provides a new method for air quality prediction and has certain application value.

Prediction of PM2.5 Concentration Based on Deep Learning, Multi-Objective Optimization, and Ensemble Forecast

Accurate and stable prediction of atmospheric PM2.5 concentrations is crucial for air pollution prevention and control. Existing studies usually rely on a single model or use a single evaluation criterion in multi-model ensemble weighted forecasts, neglecting the dual needs for accuracy and stability in PM2.5 forecast. In this study, a novel ensemble forecast model is proposed that overcomes these drawbacks by simultaneously taking into account both forecast accuracy and stability. Specifically, four advanced deep learning models—Long Short-Term Memory Network (LSTM), Graph Convolutional Network (GCN), Transformer, and Graph Sample and Aggregation Network (GraphSAGE)—are firstly introduced. And then, two combined models are constructed as predictors, namely LSTM–GCN and Transformer–GraphSAGE. Finally, a combined weighting strategy is adopted to assign weights to these two combined models using a multi-objective optimization algorithm (MOO), so as to carry out more accurate and stable predictions. The experiments are conducted on the dataset from 36 air quality monitoring stations in Beijing, and results show that the proposed model achieves more accurate and stable predictions than other benchmark models. It is hoped that this proposed ensemble forecast model will provide effective support for PM2.5 pollution forecast and early warning in the future.

Analysis of the Development Status and Industrial Policies of the Hydrogen Energy Industry in Zhangjiagang City

China is currently building hydrogen refueling stations in Beijing, Shanghai, and Zhengzhou. Moreover, there are currently numerous medium-sized hydrogen refueling stations under construction with a capacity of over 400KG/D. From planning, design, construction to operation, hydrogen stations with long-term operational capabilities are required to analyze and develop the system, ensuring the scientific nature of technology and the economic efficiency of operation. The core facilities of the hydrogen refueling station are mainly gas storage tanks. Air compressors and various control systems. At present, the existing hydrogen production stations and core facilities under construction mainly adopt the form of "import+domestic products", basically establishing the conditions for national production. But it is necessary to strengthen the implementation of current standards, the establishment of inspection instruments, and supervision and management.

Urban heat island analysis based on high resolution measurement data: A case study in Beijing

Urban heat island (UHI) is a widely concerned urban climate which impacts billions of residents worldwide. Nevertheless, inadequate rigorous air temperature (Tair) measurement has become an obstacle to UHI research and mitigation, especially in megacities like Beijing. In this study, we applied a 1-km hourly Tair dataset interpolated from records of 521 stations in Beijing. The dataset enables us to analyze UHI patterns on a block scale and the impacts of landscapes combined with the local climate zones (LCZ) scheme. Our results indicate that: (1) Tair and its temporal variation in each LCZ vary significantly, which are highly relevant to their morphology and thermal-radiative properties. (2) LCZ 1 and LCZ 2 have the highest nocturnal UHI intensities (UHII). Discrepancies among LCZs also cause various temporal variations in their UHII. (3) The spatial pattern of LCZs affects regional temperature. Area ratio and aggregation extent of LCZ 1&2 show significant positive correlations with regional temperature, while LCZ A&D&G have the opposite regularity. (4) Distinct mitigation strategies are put forward for each subarea in Beijing with various endowments of population and the LCZ structure. The study provides insight into Beijing UHI and plausible mitigation advice in megacities like Beijing.

An adaptive adjacency matrix-based graph convolutional recurrent network for air quality prediction

In recent years, air pollution has become increasingly serious and poses a great threat to human health. Timely and accurate air quality prediction is crucial for air pollution early warning and control. Although data-driven air quality prediction methods are promising, there are still challenges in studying spatial–temporal correlations of air pollutants to design effective predictors. To address this issue, a novel model called adaptive adjacency matrix-based graph convolutional recurrent network (AAMGCRN) is proposed in this study. The model inputs Point of Interest (POI) data and meteorological data into a fully connected neural network to learn the weights of the adjacency matrix thereby constructing the self-ringing adjacency matrix and passes the pollutant data with this matrix as input to the Graph Convolutional Network (GCN) unit. Then, the GCN unit is embedded into LSTM units to learn spatio-temporal dependencies. Furthermore, temporal features are extracted using Long Short-Term Memory network (LSTM). Finally, the outputs of these two components are merged and air quality predictions are generated through a hidden layer. To evaluate the performance of the model, we conducted multi-step predictions for the hourly concentration of PM2.5, PM10 and O3 at Fangshan, Tiantan and Dongsi monitoring stations in Beijing. The experimental results show that our method achieves better predicted effects compared with other baseline models based on deep learning. In general, we designed a novel air quality prediction method and effectively addressed the shortcomings of existing studies in learning the spatio-temporal correlations of air pollutants. This method can provide more accurate air quality predictions and is expected to provide support for public health protection and government environmental decision-making.

Analyzing Evapotranspiration in Greenhouses: A Lysimeter-Based Calculation and Evaluation Approach

The absence of accurate measurement or calculation techniques for crop water requirements in greenhouses frequently results in over- or under-irrigation. In order to find a better method, this study analyzed the accuracy, data consistency and practicability of the Penman–Monteith (PM), Hargreaves–Samani (HS), Pan Evaporation (PAN), and Artificial Neural Network (ANN) models. Model-calculated crop evapotranspiration (ETC) was compared with lysimeter-measured crop evapotranspiration (ETC) in the National Precision Agriculture Demonstration Station in Beijing, China. The results showed that the actual ETC over the entire experimental period was 176.67 mm. The ETC calculated with the PM, HS, PAN, and ANN model were 146.07 mm, 189.45 mm, 197.03 mm, and 174.7 mm, respectively, which were different from the actual value by −17.32%, 7.23%, 11.52%, and −1.12%, respectively. The order of the calculation accuracy for the four models is as follows: ANN model > PAN model > PM model > HS model. By comprehensively evaluating the statistical indicators of each model, the ANN model was found to have a significantly higher calculation accuracy compared to the other three models. Therefore, the ANN model is recommended for estimating ETC under greenhouse conditions. The PM and PAN models can also be used after improvement.

Case study of performance assessment of overlapping shield tunnels with a small curve radius

AbstractDue to the network planning of subways and their surrounding structures, increasingly more overlapping shields with a small curve radius have been constructed. A newly constructed upper tunnel partly overlaps a lower one, leading to the extremely complex uplift of the lower tunnel caused by the construction of a new tunnel. Based on the shield‐driven project that runs from the Qinghe Xiaoyingqiao Station to the Qinghe Station in Beijing, which adopts the reinforcement measures of interlayer soil grouting and steel supports on site, in this study, the uplift pattern of the lower tunnel and the stress characteristics of steel supports were investigated through numerical simulations and on‐site monitoring. The study results show that among all tunnel segments, the first segment of the shield witnesses a maximum uplift displacement that increases with the horizontal space between tunnels. On using either interlayer soil grouting or steel‐ring bracing reinforcement, the uplift of the tunnel lining exceeds the control value; by contrast, when these two measures are jointly applied, the uplift of the tunnel lining does not exceed a maximum value of 4.87 mm, which can satisfy the requirements of deformation control. Under these two joint measures, the soil strength between two stacked shield tunnels can be enhanced and the uplift deformation can be restricted with the interlayer soil grouting. Also, the segmental deformation and overall stability of the existing tunnel can be controlled with the temporary steel supports. The deformation of circumferential supports and segments is closely related to each other, and the segmental uplift is controlled by H‐shaped steel supports. With the increase in the horizontal space between twin shields, the effect of the construction would gradually weaken, accompanied by a gradual reduction of the stresses of steel supports. These findings provide a valuable reference for the engineering design and safe construction of overlapping shield tunnels with a small curve radius.

Heterogeneous impacts of local traffic congestion on local air pollution within a city: Utilizing taxi trajectory data

This study estimates the causal effects of traffic congestion on air quality in local areas within a city, highlighting the spatial and temporal variation in local traffic, local air pollution, and health risks to residents due to local pollutant exposure. We employ a large-scale taxi driving trajectory data to construct measures of traffic congestion in local areas surrounding air quality monitoring stations in Beijing, on an hourly basis. The station-by-hour panel data enables the estimation of both contemporaneous and lagged marginal effects of local traffic on local air pollution. We find that local traffic congestion increases concentrations of NO2 and CO contemporaneously, but concentrations of PM2.5 and PM10 in a 2-h lagged manner. The magnitude and significance of the estimates vary with local traffic and pollution conditions, implying heterogeneous marginal effects on local air pollution of local traffic across locations, hours of the day, months and seasons. These results stress the importance of designing traffic policies that are both spatially and temporally fine-grained to attain efficiency and equity.

Spatiotemporal informer: A new approach based on spatiotemporal embedding and attention for air quality forecasting

Accurate prediction of air pollution is essential for public health protection. Air quality, however, is difficult to predict due to the complex dynamics, and its accurate forecast still remains a challenge. This study suggests a spatiotemporal Informer model, which uses a new spatiotemporal embedding and spatiotemporal attention, to improve AQI forecast accuracy. In the first phase of the proposed forecast mechanism, the input data is transformed by the spatiotemporal embedding. Next, the spatiotemporal attention is applied to extract spatiotemporal features from the embedded data. The final forecast is obtained based on the attention tensors. In the proposed forecast model, the input is a 3-dimensional data that consists of air quality data (AQI, PM2.5, O3, SO2, NO2, CO) and geographic information, and the output is a multi-positional, multi-temporal data that shows the AQI forecast result of all the monitoring stations in the study area. The proposed forecast model was evaluated by air quality data of 34 monitoring stations in Beijing, China. Experiments showed that the proposed forecast model could provide highly accurate AQI forecast: the average of MAPE values for from 1 h to 20 h ahead forecast was 11.61%, and it was much smaller than other models. Moreover, the proposed model provided a highly accurate and stable forecast even at the extreme points. These results demonstrated that the proposed spatiotemporal embedding and attention techniques could sufficiently capture the spatiotemporal correlation characteristics of air quality data, and that the proposed spatiotemporal Informer could be successfully applied for air quality forecasting.

ANALYZING LAND USE TYPES’ EFFECTS ON LST USING THE GWR MODEL AND CASE STUDIES IN BEIJING

The development of urbanization and the transformation of green lands into impermeable land increase temperature and create urban heat islands (UHIs). Our observations with remote sensing instruments of Landsat platforms show considerable changes in land use types in Beijing city with the shrinking of green lands, expansion of built environments, and a slight increase in the temperature during the recent four decades. Using remote sensing instruments of Landsat platforms and registered data from two meteorological stations in Beijing, this study finds the relationship between land surface temperature (LST) and the increasing conversion of cultivated lands into built-up areas. This article presents innovative research that shows the mutual correlation well and recommends revisions in the land use policies for better weather. The geographically weighted regression model (GWR) with a Gaussian weighting kernel function analyzes the impact of various urban land use types on the LST and the increase UHIs. In Beijing city, green lands show fewer standard deviations (SD) in the average temperatures equal to 0.109, while the industrial spaces exhibit a high SD equal to 0.212. The outcomes of this paper contribute to finding optimal land use policies everywhere in the world with the increasing urbanization through simulating its model for a more comfortable life.

Electric Vehicle Charging Transaction Model Based on Alliance Blockchain

With the increasing demand for electric vehicle (EV) charging, there are cases of complicated trading between EV users and charging operators or electrical utilities. This paper proposes a new trading model based on consortium blockchain. Firstly, mutual trust interconnected transaction networks and channels between charging operators are established. The PBFT consensus algorithm is used to verify EV charging transactions, and smart contracts are used to complete the process. In this model, charging station nodes of each company can verify transactions, the interconnection and independent management of charging transactions are realized, users’ charging methods are enriched, and the flexibility of charging services is improved. Finally, this paper uses hyperledger fabric to build an experimental environment. The feasibility of the above method is verified with an actual distribution scenario of some charging stations in Beijing.

Evaluation of emergency evacuation capacity of urban metro stations based on combined weights and TOPSIS-GRA method in intuitive fuzzy environment

Research on emergency evacuations of urban metro stations has become a hot topic in public security applications in recent years. This paper proposes a comprehensive framework for evaluating the emergency evacuation capacity of metro stations. An evaluation indicator system with 16 indicators of human, equipment, environmental, and management factors is established. A triangular intuitionistic fuzzy number (TIFN) approach is used to collect indicator data to express the uncertainty of the language variables and ensure that the data is closer to reality. Subsequently, a combination of the TIFN and the decision-making trial and evaluation laboratory (TIFN-DEMATEL) and the entropy weight method (EWM) are used to combine the weights using game theory to ensure the weights is more scientific and reasonable. Grey relational analysis (GRA) is integrated with the technique for order preference by similarity to an ideal solution (TOPSIS) to improve the ranking results and evaluate metro station emergency evacuation capacity. A case study of eight metro stations in Beijing is conducted to validate the evaluation framework. Sensitivity analysis and comparative analysis demonstrate the reliability and robustness of the proposed method. Finally, the specific measures to improve the emergency evacuation capacity are given.

Deep learning methods for atmospheric PM2.5 prediction: A comparative study of transformer and CNN-LSTM-attention

A transformer-based method was firstly developed to predict the hourly PM2.5 concentration at 12 monitoring stations in Beijing. Convolutional neural network-long short-term memory-attention mechanism (CNN-LSTM-Attention) model were introduced to compare with Transformer model. Experiments on historical long time series data and future prediction were conducted to evaluate the model performance and generalization ability over a long period of time. The four metrics, namely, the explained variance score (EVS), R2, mean absolute error (MAE), and mean square error (MSE), were selected to evaluate the models. The results revealed that the EVS, MAE, MSE, and R2 values of Transformer model were 12%, 9%, 6%, and 30% higher than those of the CNN-LSTM-Attention model, respectively. The forecast results revealed that the Transformer model outperformed the CNN-LSTM-Attention model in terms of the goodness-of-fit R2 (94.4% vs. 83.6%). Transformer model can capture short-term pollution changes affected by abruptly changing meteorological conditions and long-term trends with significant seasonal changes, especially in autumn and winter when the pollution situation is more complex. Transformer model has obvious advantages in overcoming the interdependence problem of the influencing factors in long sequences, providing a new method for the long-term prediction of air quality.

Effect of short-term exposure to ambient air pollutants on non-accidental mortality in emergency department visits: a time-series study.

Exposure to air pollution has been linked to an increased risk of premature mortality. However, the acute effects of air pollution on the risk of non-accidental mortality have not been extensively researched in developing countries, and the findings thus far have been inconsistent. Therefore, this study aimed to examine the association between short-term exposure to six pollutants (PM2.5, PM10, SO2, NO2, O3, and CO) and non-accidental mortality in Beijing, China. Daily data on non-accidental deaths were gathered from 1 January 2017 to 31 December 2018. Air pollution data for the same period were collected from 35 fixed-site air quality monitoring stations in Beijing. Generalized additive models (GAM) based on Poisson regression were used to investigate the association between non-accidental mortality in emergency department visits and the daily average levels of air pollutants. There were 8,676 non-accidental deaths recorded during 2017-2018. After sensitivity analysis, short-term exposure to air pollutants, particularly gaseous pollutants, was linked to non-accidental mortality. Specifically, for every 10 μg/m3 increase (5 μg/m3 in SO2, 0.5 mg/m3 in CO) of SO2 (lag 04), NO2 (lag 04), O3 (lag 05), and CO (lag 04), the relative risk (RR) values were 1.054 (95% CI: 1.009, 1.100), 1.038 (95% CI: 1.013, 1.063), 1.032 (95% CI: 1.011, 1.054), and 1.034 (95% CI: 1.004, 1.066), respectively. In terms of causes of death, short-term exposure to NO2, SO2, and O3 increased the risk of circulatory mortality. Further stratified analysis revealed that the stronger associations were presented in females for O3 while in males for CO. People aged 65 and over were strongly associated with ambient air pollution. Our study showed that ambient air pollutants were associated with non-accidental mortality. Our findings suggested that efforts to control gaseous pollution should be stepped up, and vulnerable groups should be the focus of health protection education.

A Charging Guidance Optimization Model for Electric Vehicle Travel by Considering Multi-Dimensional Preferences of Users

The dual-carbon strategy advocates a green, environmentally friendly, and low-carbon lifestyle. In the field of transportation, electric vehicles (EVs) have been regarded as an effective solution to reduce carbon emissions and to conserve energy. Developing a reasonable charging guidance scheme for users is a feasible way to solve problems, such as the range anxiety of EV users, and has a great application value for the promotion of EVs in the future. In practical situations, how to develop charging induction schemes for users that better meet their needs according to the type of user and their multi-dimensional preferences is the focus of this paper. To this end, this study utilized charging behavioral data to investigate the multi-dimensional charging preference of users based on the collaborative filtering algorithm. Then, a multi-objective optimization model was established based on the preference degree of each charging station and the integrated travel cost. An NSGA-III framework was used to design the algorithm to solve the proposed model. The algorithm was tested using simulation experiments that were designed based on the road network and charging stations in Beijing. The final result is an experimental analysis of the weight matrices for the three different preferences of minimum energy consumption cost, minimum time cost, and minimum fee cost, which yields a difference of about 4.4% between the optimal energy consumption cost and the maximum energy cost, about 2.9% between the optimal time cost and the maximum time cost, and about 10% between the optimal fee cost and the maximum fee cost under these three different preferences, respectively. The proposed multi-objective optimization model is able to provide users with reliable charging station selection by incorporating their personalized charging preference characteristics and charge guidance schemes.

Real-Time Water Level Monitoring Based on GNSS Dual-Antenna Attitude Measurement

Real-time and high-precision water level monitoring is crucial for the fields of hydrology, hydraulic engineering, and disaster prevention and control. The most prevalent method for measuring water level is through the use of water level gauges, which can be costly and have limited coverage. In recent years, Global Navigation Satellite System Reflectometry (GNSS-R) technology has emerged as a promising approach for water level monitoring due to its low cost and high coverage. However, a limitation of current GNSS-R technology is the extended time required to record signals, which hinders its potential for real-time application. This paper introduces a novel real-time water level monitoring method based on GNSS dual-antenna attitude measurement and develops a model to invert water level based on baseline vector. This method uses double-difference observations to eliminate errors caused by various factors, such as satellite and receiver clock, and ionospheric and tropospheric delay. To avoid the impact of detecting and correcting cycle slips during real-time operations, a single-epoch calculation method is introduced. In order to verify the stability and reliability of our method, field tests were carried out at Dongshahe Station in Beijing. We obtained water level data with a time resolution of 1 Hz through field experiments. Experimental data collected from 12 May to 8 June 2022 and from 4 July to 8 August 2022 showed good agreement with on-site water gauge measurements, with root mean square errors of 2.77 cm and 2.54 cm, respectively. Experimental results demonstrate that this method can achieve high-precision, high-temporal-resolution water level monitoring.

Research on short-term forecasting method of photovoltaic power generation based on clustering SO-GRU method

In order to enhance the stability of the power grid and increase the ability of the power grid to absorb photovoltaic energy, while enriching the prediction model of photovoltaic power generation, improve the precision reading of the prediction model. This paper proposes a short-term forecasting model of photovoltaic power generation based on K-means++clustering- Snake Optimizer algorithm (SO) - Gate Recurrent Unit(GRU). First, Pearson correlation coefficient analysis is used to screen out variables that are not related to the actual output of power generation.Then, select historical data with similar weather fluctuation degree as the training sample through K-means++clustering, use SO algorithm to optimize the parameters of GRU network, and use the optimized GRU network to predict photovoltaic power generation, Finally, through the simulation of a photovoltaic power station in Beijing, the results show that the prediction model proposed in this paper has improved the prediction accuracy compared with other traditional prediction models when the weather is almost no fluctuation, the weather has some fluctuations and the weather fluctuation is very severe. This research can provide reference for energy storage research of integrated energy system.

Multi-site, multi-pollutant atmospheric data analysis using Riemannian geometry

We demonstrate the benefits of using Riemannian geometry in the analysis of multi-site, multi-pollutant atmospheric monitoring data. Our approach uses covariance matrices to encode spatio-temporal variability and correlations of multiple pollutants at different sites and times. A key property of covariance matrices is that they lie on a Riemannian manifold and one can exploit this property to facilitate dimensionality reduction, outlier detection, and spatial interpolation. Specifically, the transformation of data using Reimannian geometry provides a better data surface for interpolation and assessment of outliers compared to traditional data analysis tools that assume Euclidean geometry. We demonstrate the utility of using Riemannian geometry by analyzing a full year of atmospheric monitoring data collected from 34 monitoring stations in Beijing, China.