Visualization of uncertainty in air quality ensemble forecasts

2021 ◽  
Author(s):  
Angelika Heil ◽  
Augustin Colette
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Mobile Apps ◽  
Predictive Performance ◽  
User Preferences ◽  
Ensemble Forecasts ◽  
The Public ◽  
Pollution Levels ◽  
Wide Range

<p>Air quality forecasts help decision-makers to respond to air pollution episodes and to improve air quality management. In recent years, the public increasingly uses mobile apps to check forecasted air pollution levels and then adjusts outdoor activities accordingly. For Europe, state-of-the-art daily air quality forecasts are provided by the regional Copernicus Atmosphere Monitoring System (CAMS). The system integrates forecasts from 9 individual models. This ensemble approach not only achieves better predictive performance compared to a single model, but also allows a better quantification of forecast uncertainty. How to best communicate this uncertainty to a broad audience is by no means a trivial task, but yet essential to maintain trust in the forecasts.</p><p>We developed innovative visualizations to convey CAMS forecast uncertainties in time series and maps. The development is strongly user-driven and involves iterative consultation with a wide range of expert and non-expert users. We investigate the feasibility of different bivariate techniques to communicate the ensemble's best estimate and its uncertainty in a single map. We explore user preferences for a variety of time-series graphs, including boxplots, violinplots, and fancharts. Whilst preferences are largely driven by the data and visualization literacy of the users, we identify some generally valid best practices in terms of graph types, choices of colors and labels, and accompanying textual explanations. Finally, we present our candidate designs for the public display of air quality forecasts on the regional CAMS webpage.</p>

scholarly journals Embedded Generative Air Pollution Model with Variational Autoencoder and Environmental Factor Effect in Ulaanbaatar City

Atmosphere ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 71
Author(s):  
Bulgansaikhan Baldorj ◽  
Munkherdene Tsagaan ◽  
Lodoysamba Sereeter ◽  
Amanjol Bulkhbai
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Environmental Factors ◽  
Influencing Factors ◽  
Quality Measurement ◽  
Temporal Distribution ◽  
Range Data ◽  
Pollution Levels ◽  
Variational Autoencoder ◽  
Wide Range

Air pollution is one of the most pressing modern-day issues in cities around the world. However, most cities have adopted air quality measurement devices that only measure the past pollution levels without paying attention to the influencing factors. To obtain preliminary pollution information with regard to environmental factors, we developed a variational autoencoder and feedforward neural network-based embedded generative model to examine the relationship between air quality and the effects of environmental factors. In the model, actual SO2, NO2, PM2.5, PM10, and CO measurements from 2016 to 2020 were used, which were assembled from 15 differently located ground monitoring stations in Ulaanbaatar city. A wide range of weather and fuel measurements were used as the data for the influencing factors, and were collected over the same period as the air pollution data were recorded. The prediction results concerned all measurement stations, and the results were visualized as a spatial–temporal distribution of pollution and the performance of individual stations. A cross-validated R2 was used to estimate the entire pollution distribution through the regions as SO2: 0.81, PM2.5: 0.76, PM10: 0.89, and CO: 0.83. Pearson’s chi-squared tests were used for assessing each measurement station, and the contingency tables represent a high correlation between the actual and model results. The model can be applied to perform specific analysis of the interdependencies between pollution and environmental factors, and the performance of the model improves with long-range data.

scholarly journals Visualization of Correlation for Air Pollution Time Series using TAQMN Data

2019 ◽  
Vol 8 (3) ◽  
pp. 7922-7927
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Particulate Matter ◽  
Pearson Correlation ◽  
Fine Particulate Matter ◽  
Correlation Method ◽  
Well Being ◽  
Pollution Levels ◽  
Fine Particulate ◽  
Pm2.5 Concentration

In Taiwan country Annan, Chiayi, Giran, and Puzi cities are facing a serious fine particulate matter (PM2.5) issue. To date the impressive advance has been made toward understanding the PM2.5 issue, counting special temporal characterization, driving variables and well-being impacted. However, notable research as has been done on the interaction of the content between the selected cities of Taiwan country for particulate matter (PM2.5) concentration. In this paper, we purposed a visualization technique based on this principle of the visualization, cross-correlation method and also the time-series concentration with particulate matter (PM2.5) for different cities in Taiwan. The visualization also shows that the correlation between the different meteorological factors as well as the different air pollution pollutants for particular cities in Taiwan. This visualization approach helps to determine the concentration of the air pollution levels in different cities and also determine the Pearson correlation, r values of selected cities are Annan, Puzi, Giran, and Wugu.

scholarly journals Communicating air pollution-related health risks to the public: An application of the Air Quality Health Index in Shanghai, China

2013 ◽  
Vol 51 ◽  
pp. 168-173 ◽  
Author(s):  
Renjie Chen ◽  
Xi Wang ◽  
Xia Meng ◽  
Jing Hua ◽  
Zhijun Zhou ◽  
...  
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Health Risks ◽  
Health Index ◽  
The Public ◽  
Quality Health ◽  
Air Quality Health Index

NESTED HIGH-RESOLUTION NOx AND PM SIMULATIONS OVER ZÜRICH

2021 ◽  
Author(s):  
Ivo Suter ◽  
Lukas Emmenegger ◽  
Dominik Brunner
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Boundary Conditions ◽  
Meteorological Conditions ◽  
Model Systems ◽  
Multi Scale ◽  
Wide Range ◽  
The Impact ◽  
The City ◽  
Concentration Levels

<p>Reducing air pollution, which is the world's largest single environmental health risk, demands better-informed air quality policies. Consequently, multi-scale air quality models are being developed with the goal to resolve cities. One of the major challenges in such model systems is to accurately represent all large- and regional-scale processes that may critically determine the background concentration levels over a given city. This is particularly true for longer-lived species such as aerosols, for which background levels often dominate the concentration levels, even within the city. Furthermore, the heterogeneous local emissions, and complex dispersion in the city have to be considered carefully.</p><p>In this study, the impact of processes across a wide range of scales on background concentrations over Switzerland and the city of Zurich was modelled by performing one year of nested European and Swiss national COSMO-ART simulations to obtain adequate boundary conditions for gas-phase chemical, aerosol and meteorological conditions for city-resolving simulations. The regional climate chemistry model COSMO-ART (Vogel et al. 2009) was used in a 1-way coupled mode. The outer, European, domain, which was driven by chemical boundary conditions from the global MOZART model, had a 6.6 km horizontal resolution and the inner, Swiss, domain one of 2.2 km. For the city scale, a catalogue of more than 1000 mesoscale flow patterns with 100 m resolution was created with the model GRAMM, based on a discrete set of atmospheric stabilities, wind speeds and directions, accounting for the influence of land-use and topography. Finally, the flow around buildings was solved with the CFD model GRAL forced at the boundaries by GRAMM. Subsequently, Lagrangian dispersion simulations for a set of air pollutants and emission sectors (traffic, industry, ...) based on extremely detailed building and emission data was performed in GRAL. The result of this nested procedure is a library of 3-dimensional air pollution maps representative of hourly situations in Zurich (Berchet et al. 2017). From these pre-computed situations, time-series and concentration maps can be obtained by selecting situations according to observed or modelled meteorological conditions.</p><p>The results were compared to measurements from air quality monitoring network stations. Modelled concentrations of NO<sub>x</sub> and PM compared well to measurements across multiple locations, provided background conditions were considered carefully. The nested multi-scale modelling system COSMO-ART/GRAMM/GRAL can adequately reproduce local air quality and help understanding the relative contributions of local versus distant emissions, as well as fill the space between precise point measurements from monitoring sites. This information is useful for research, policy-making, and epidemiological studies particularly under the assumption that exceedingly high concentrations become more and more localised phenomenon in the future.</p>

Air quality management using genetic algorithm based heuristic fuzzy time series model

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lalit Bhagat ◽  
Gunjan Goyal ◽  
Dinesh C.S. Bisht ◽  
Mangey Ram ◽  
Yigit Kazancoglu
Keyword(s):  
Genetic Algorithm ◽  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Quality Management ◽  
Fuzzy Time Series ◽  
Selection Algorithm ◽  
Content Type ◽  
Proposed Model ◽  
Adaptive Time

PurposeThe purpose of this paper is to provide a better method for quality management to maintain an essential level of quality in different fields like product quality, service quality, air quality, etc.Design/methodology/approachIn this paper, a hybrid adaptive time-variant fuzzy time series (FTS) model with genetic algorithm (GA) has been applied to predict the air pollution index. Fuzzification of data is optimized by GAs. Heuristic value selection algorithm is used for selecting the window size. Two algorithms are proposed for forecasting. First algorithm is used in training phase to compute forecasted values according to the heuristic value selection algorithm. Thus, obtained sequence of heuristics is used for second algorithm in which forecasted values are selected with the help of defined rules.FindingsThe proposed model is able to predict AQI more accurately when an appropriate heuristic value is chosen for the FTS model. It is tested and evaluated on real time air pollution data of two popular tourism cities of India. In the experimental results, it is observed that the proposed model performs better than the existing models.Practical implicationsThe management and prediction of air quality have become essential in our day-to-day life because air quality affects not only the health of human beings but also the health of monuments. This research predicts the air quality index (AQI) of a place.Originality/valueThe proposed method is an improved version of the adaptive time-variant FTS model. Further, a nature-inspired algorithm has been integrated for the selection and optimization of fuzzy intervals.

A Big Data Test-bed for Analyzing Data Generated by an Air Pollution Sensor Network

2016 ◽  
Vol 13 (4) ◽  
pp. 19-35 ◽  
Author(s):  
Lídice García Ríos ◽  
José Alberto Incera Diéguez
Keyword(s):  
Air Pollution ◽  
Big Data ◽  
Sensor Networks ◽  
Internet Of Things ◽  
Sensor Network ◽  
Proof Of Concept ◽  
Test Bed ◽  
Pollution Levels ◽  
Wide Range ◽  
Military Applications

Sensor networks have perceived an extraordinary growth in the last few years. From niche industrial and military applications, they are currently deployed in a wide range of settings as sensors are becoming smaller, cheaper and easier to use. Sensor networks are a key player in the so-called Internet of Things, generating exponentially increasing amounts of data. Nonetheless, there are very few documented works that tackle the challenges related with the collection, manipulation and exploitation of the data generated by these networks. This paper presents a proposal for integrating Big Data tools (in rest and in motion) for gathering, storage and analysis of data generated by a sensor network that monitors air pollution levels in a city. The authors provide a proof of concept that combines Hadoop and Storm for data processing, storage and analysis, and Arduino-based kits for constructing their sensor prototypes.

scholarly journals Understanding Public Response to Air Quality Using Tweet Analysis

2019 ◽  
Vol 5 (3) ◽  
pp. 205630511986765
Author(s):  
Supraja Gurajala ◽  
Suresh Dhaniyala ◽  
Jeanna N. Matthews
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Machine Learning Algorithms ◽  
Mitigation Measures ◽  
Quality Data ◽  
Public Health Issue ◽  
New Delhi ◽  
Public Response ◽  
Pollution Levels ◽  
Adverse Health Effects

Poor air quality is recognized as a major risk factor for human health globally. Critical to addressing this important public-health issue is the effective dissemination of air quality data, information about adverse health effects, and the necessary mitigation measures. However, recent studies have shown that even when public get data on air quality and understand its importance, people do not necessarily take actions to protect their health or exhibit pro-environmental behaviors to address the problem. Most existing studies on public attitude and response to air quality are based on offline studies, with a limited number of survey participants and over a limited number of geographical locations. For a larger survey size and a wider set of locations, we collected Twitter data for a period of nearly 2 years and analyzed these data for three major cities: Paris, London, and New Delhi. We identify the three hashtags in each city that best correlate the frequency of tweets with local air quality. Using tweets with these hashtags, we determined that people’s response to air quality across all three cities was nearly identical when considering relative changes in air pollution. Using machine-learning algorithms, we determined that health concerns dominated public response when air quality degraded, with the strongest increase in concern being in New Delhi, where pollution levels are the highest among the three cities studied. The public call for political solutions when air quality worsens is consistent with similar findings with offline surveys in other cities. We also conducted an unsupervised learning analysis to extract topics from tweets in Delhi and studied their evolution over time and with changing air quality. Our analysis helped extract relevant words or features associated with different air quality–related topics such as air pollution policy and health. Also, the topic modeling analysis revealed niche topics associated with sporadic air quality events, such as fireworks during festivals and the air quality impact on an outdoor sport event. Our approach shows that a tweet-based analysis can enable social scientists to probe and survey public response to events such as air quality in a timely fashion and help policy makers respond appropriately.

A Discussion on recent research in air pollution - Plume rise estimates for electric generating stations

1969 ◽  
Vol 265 (1161) ◽  
pp. 221-243 ◽  
Keyword(s):  
Air Pollution ◽  
Pollution Control ◽  
Full Scale ◽  
Plume Rise ◽  
Air Pollution Control ◽  
Operational Conditions ◽  
The Public ◽  
Wide Range ◽  
Tennessee Valley ◽  
Comprehensive Study

The Tennessee Valley Authority, under sponsorship of the Public Health Service, National Air Pollution Control Administration, initiated a comprehensive study titled ‘ Full scale study of plume rise at large electric generating stations’ in 1963. The variability of plant sizes, stack heights, and stack configurations accommodated full scale assessment of plume rise over a wide range of meteorological and operational conditions.

scholarly journals Evidence on the Impact of Winter Heating Policy on Air Pollution and Its Dynamic Changes in North China

2019 ◽  
Vol 11 (10) ◽  
pp. 2728 ◽  
Author(s):  
Shulin Wang ◽  
Yongtao Li ◽  
Mahfuzul Haque
Keyword(s):  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Central Government ◽  
Northern China ◽  
Policy Changes ◽  
Dynamic Changes ◽  
The Public ◽  
Local Residents ◽  
The Impact

Environmental pollution, especially air pollution, is an alarming issue for the public, which is extensively debated among academic scholars. During the winter heating season, “smog” has become somewhat a normal phenomenon to local residents’ livelihood in northern China. Based on the daily air pollution data of regional cities in China from 2014 to 2016, and using a regression discontinuity design (RDD), the study finds that winter heating makes the air quality worse in the northern part of China. With the start of the winter heating, it increases the Air Quality Index (AQI) by 10.4%, particulate matter smaller than 10 μm (PM10) by 9.77%, particulate matter smaller than 2.5 μm (PM2.5) by 17.25%, CO by 9.84%, NO2 by 5.23%, and SO2 by 17.1%. Furthermore, dynamic changes demonstrate that air quality has gradually improved due to a series of heating policy changes implemented by the central government in recent years. Specifically, from 2014 to 2016, major indicators measuring the air pollution decrease dramatically, such as AQI by 92.36%, PM10 by 91.24%, PM2.5 by 84.06%, CO by 70.97%, NO2 by 52.76%, and SO2 by 17.15%.

scholarly journals A tale of four cities: A semantic analysis comparing the newspaper coverage of air pollution in Hong Kong, London, Pittsburgh, and Tianjin from 2014 to 2017

2019 ◽  
Vol 41 (1) ◽  
pp. 37-52
Author(s):  
Tongxin Sun ◽  
Bu Zhong
Keyword(s):  
Air Pollution ◽  
Hong Kong ◽  
Air Quality ◽  
Real Time ◽  
Semantic Analysis ◽  
Newspaper Coverage ◽  
Word Count ◽  
The Public ◽  
Computer Aided ◽  
Linguistic Inquiry

A computer-aided semantic analysis (using Linguistic Inquiry and Word Count [LIWC]) examined how newspaper coverage of air pollution from 2014 to 2017 may affect the public agenda in four cities—Hong Kong, London, Pittsburgh, and Tianjin. Results show that after controlling for the real-time air quality, the agenda-setting effect was found in Hong Kong, London, and Pittsburgh, but not Tianjin. Tianjin’s reports also contained more future-framed words but fewer present-framed words than other cities.

Sign in / Sign up

Export Citation Format

Share Document