Abstract
Several metropolis in Asia are high pollutant concentration regions and urban population in these regions frequently experience events of extremely poor levels of air quality. We believe such extreme events can be suitably modeled using extreme value distributions. We developed a sensing system to sense the urban air quality data, built probability distribution-based forecast models using extreme value theory and determined the best fit distribution in this work. Gumbel, Weibull and Frechet distributions were evaluated. The goodness of fit was determined using index of agreement and the coefficient of determination. The best-fit distribution is used to compute return periods and exceeding probabilities of air pollution peaks. The effective performance of the forecast model is then validated using mean absolute deviation (MAD), mean squared error (MSE), mean percentage error (MPE), root mean squared error (RMSE) and mean absolute percentage error (MAPE).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alyousifi Y, Masseran N, Ibrahim K (2018) Modeling the stochastic dependence of air pollution index data. Stoch Environ Res Risk Assess 32:1603. https://doi.org/10.1007/s00477-017-1443-7
Apergis N, Ozturk I (2015) Testing environmental Kuznets curve hypothesis in Asian countries. Ecol Ind 52:16–22. https://doi.org/10.1016/j.ecolind.2014.11.026
Barthwal A, Acharya D (2021) An IoT based sensing system for modeling and forecasting urban air quality. Wirel Pers Commun 116:3503–3526. https://doi.org/10.1007/s11277-020-07862-6
Beretta S (2021) More than 25 years of extreme value statistics for defects: fundamentals, historical developments, recent applications. Int J Fatigue 151:106407. https://doi.org/10.1016/j.ijfatigue.2021.106407
Central Pollution Control Board, India, 2018 [Online]. https://cpcb.nic.in/AQI_Bulletin.php
Chang J, Tseng C (2017) Analysis of correlation between secondary PM2.5 and factory pollution sources by using ANN and the correlation coefficient. IEEE Access 5:22812–22822. https://doi.org/10.1109/ACCESS.2017.2765337
Chukwudum QC, Nadarajah S (2021) Bivariate extreme value analysis of rainfall and temperature in Nigeria. Environ Model Assess. https://doi.org/10.1007/s10666-021-09781-7
Cichowicz R, Wielgosiński G, Fetter W (2017) Dispersion of atmospheric air pollution in summer and winter season. Environ Monit Assess 189(12):605. https://doi.org/10.1007/s10661-017-6319-2
Dyvak M, Darmorost I, Kasatkina N et al (2018) Correlation analysis traffic intensity of the motor vehicles and the air pollution by their harmful emissions. In: 2018 14th international conference on advanced trends in radio-elecrtronics, telecommunications and computer engineering (TCSET), Lviv-Slavske, pp 855–858
Einmahl J, He Y (2021) Extreme value estimation for heterogeneous data. J Bus Econ Stat. https://doi.org/10.1080/07350015.2021.2008408
Ercelebi SG, Toros H (2009) Extreme value analysis of Istanbul air pollution data. Clean: Soil, Air, Water 37(2):122–131. https://doi.org/10.1002/clen.200800041
Guo H, Sahu SK, Kota SH, Zhang H (2019) Characterization and health risks of criteria air pollutants in Delhi. Chemosphere 225:27–34. https://doi.org/10.1016/j.chemosphere.2019.02.154
Hama S, Kumar P, Harrison R et al (2020) Four-year assessment of ambient particulate matter and trace gases in the Delhi-NCR region of India. Sustain Cities Soc 54:102003. https://doi.org/10.1016/j.scs.2019.102003.6
Hasenfratz D, Saukh O, Thiele L (2012) On-the-fly calibration of low-cost gas sensors. In: Picco GP, Heinzelman W (eds) Wireless sensor networks, EWSN 2012, lecture notes in computer science 7158. Springer, Berlin
Hu K, Rehman A, Bhrugubanda H et al (2017) HazeEst: machine learning based metropolitan air pollution estimation from fixed and mobile sensors. IEEE Sens J 17(11):3517–3525. https://doi.org/10.1109/JSEN.2017.2690975
Karaca F, Alagha O (2005) Statistical characterization of atmospheric PM10 and PM2.5 concentrations at a non-impacted suburban site of Istanbul, Turkey. Chemosphere 59:1183–1190. https://doi.org/10.1016/j.chemosphere.2004.11.062
Kim J, Chu C, Shin S (2014) ISSAQ: an integrated sensing systems for real-time indoor air quality monitoring. IEEE Sens J 14(12):4230–4244. https://doi.org/10.1109/JSEN.2014.2359832
Li L, Yan D, Xu S et al (2017) Characteristics and source distribution of air pollution in winter in Qingdao, eastern China. Environ Pollut 224:44–53. https://doi.org/10.1016/j.envpol.2016.12.037
Martins L, Wikuats C, Capucim M et al (2017) Extreme value analysis of air pollution data and their comparison between two large urban regions of South America. Weather Clim Extremes 18:44–54. https://doi.org/10.1016/j.wace.2017.10.004
Masseran N (2021) Power-law behaviors of the duration size of unhealthy air pollution events. Stoch Environ Res Risk Assess 35:1499–1508. https://doi.org/10.1007/s00477-021-01978-2
Nebenzal A, Fishbain B (2018) Long-term forecasting of nitrogen dioxide ambient levels in metropolitan areas using the discrete-time Markov model. Environ Model Softw 107:175–185. https://doi.org/10.1016/j.envsoft.2018.06.001
Neisi A, Vosoughi M, Shirmardi M et al (2018) Concentration of air pollutants as toxic matter in urban and rural areas of Ahvaz. Toxin Rev 37(3):243–250. https://doi.org/10.1080/15569543.2017.1337796
Ozonur D, Pobocikova I, de Souza A (2021) Statistical analysis of monthly rainfall in Central West Brazil using probability distributions. Model Earth Syst Environ 7:1979–1989. https://doi.org/10.1007/s40808-020-00954-z
Pandey A, Brauer M, Cropper M (2021) Health and economic impact of air pollution in the states of India: the Global Burden of Disease Study 2019. Lancet Planet Health 5(1):e25–e38. https://doi.org/10.1016/S2542-5196(20)30298-9
Patel K, Bhandari S, Gani S et al (2021) Sources and dynamics of submicron aerosol during the autumn onset of the air pollution season in Delhi, India. ACS Earth Space Chem 5(1):118–128. https://doi.org/10.1021/acsearthspacechem.0c00340
Sharma P, Khare M, Chakrabarti S (2019) Application of extreme value theory for predicting violations of air quality standards for an urban road intersection. Transp Res Part D Transp Environ 4:201–216. https://doi.org/10.1016/S1361-9209(99)00006-1
Singh A, Oli N (2021) Development of vulnerability framework for assessing the air pollution-related health impacts in four districts of Delhi, India. Curr Sci 120(6):1092. https://doi.org/10.18520/cs/v120/i6/1092-1098
Souza A, Aristone F, Fernandes W et al (2020) Analysis of ozone concentrations using probability distributions. Ozone Sci Eng 42(6):539–550. https://doi.org/10.1080/01919512.2020.1736987
Wang Q (2019) Multifractal characterization of air polluted time series in China. Phys A Stat Mech Appl 514:167–180. https://doi.org/10.1016/j.physa.2018.09.065
Wang Y, Chen G (2017) Efficient data gathering and estimation for metropolitan air quality monitoring by using vehicular sensor networks. IEEE Trans Veh Technol 66(8):7234–7248. https://doi.org/10.1109/TVT.2017.2655084
Wang X, Mauzerall D (2004) Characterizing distributions of surface ozone and its impact on grain production in China, Japan and South Korea: 1990 and 2020. Atmos Environ 38:4383–4402. https://doi.org/10.1016/j.atmosenv.2004.03.067
Williams G, Schäfer B, Beck C (2020) Superstatistical approach to air pollution statistics. Phys Rev Res 2(1):013019. https://doi.org/10.1103/PhysRevResearch.2.013019
Yap B, Sim C (2011) Comparisons of various types of normality tests. J Stat Comput Simul 81(12):2141–2155. https://doi.org/10.1080/00949655.2010.520163
Zhu J, Sun C, Li V (2017) An Extended spatio-temporal granger causality model for air quality estimation with heterogeneous urban big data. IEEE Trans Big Data 3(3):307–319. https://doi.org/10.1109/TBDATA.2017.2651898
Funding
This research did not receive any grant or funding from funding agencies in the public, commercial, or not-for-profit sectors.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors confirm that there is no conflict of interest or competing interest to declare for this publication.
Employment
The authors are employed in academic capacity, only with DIT University, Dehradun.
Research involving human participants and/or animals
No human or animal participants were involved/used in the present work.
Informed consent
Not applicable (no human or animal participants were involved in the research).
Financial/non-financial interests
The authors declare that they have no financial/non-financial interests with the publication of the research.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Barthwal, A., Acharya, D. Performance analysis of sensing-based extreme value models for urban air pollution peaks. Model. Earth Syst. Environ. 8, 4149–4163 (2022). https://doi.org/10.1007/s40808-022-01349-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-022-01349-y