Nevşehir İli Hava Kalitesinin Markov Zinciri ile Tahmini

Year 2021, , 1707 - 1723, 31.10.2021

Emine Baştürk , Alper Alver

https://doi.org/10.29130/dubited.885779

Abstract

Bu makalede Nevşehir İlinde µg m-3 seviyesinde bulunan PM10, SO2, CO, NO2 ve O3 gibi temel hava kirletici parametreleri 01.08.2019-19.11.2020 tarihleri arasında izlenilmiş ve bu parametrelere bağlı olarak Hava Kalite İndeksi (HKİ) değerleri hesaplanmıştır. Nevşehir İli HKİ değerleri iyi ve hassas dereceler arasında değişkenlik göstermektedir. HKİ izleme verileri kullanılarak Küçük Ölçekli ve Ayrık Zamanlı Markov Zinciri Modelleri eğitilmiş ve 20.11.2020-20.12.2020 tarihlerini kapsayan yeni verilerle doğrulamaları yapılmıştır. Yapılan bu çalışmada Nevşehir İli HKİ değerleri, Küçük Ölçekli ve Ayrık Zamanlı Markov zincir modelleri ile sırasıyla 0,887 ve 0,982 oranında başarıyla tahmin edilmiştir. Nevşehir İli hava kalitesine bağlı olarak daha az değişken duruma sahip olan Ayrık-Zamanlı Markov Zinciri Modeli hem eğitimde hem de kontrolünde kullanılan HKİ verilerini tahmin etmede daha başarılı bulunmuştur. Sonuç olarak Markov Zinciri modellerinin farklı hava koşullarını tahmin etmede başarılı bir yöntem olarak kullanılabileceği belirlenmiştir.

Keywords

Hava kirliliği,, Hava kalite indeksi,, Markov zinciri,, Model,, Tahmin, Nevşehir

Thanks

Yapılan bu çalışmada yazımında manen destek veren değerli iş arkadaşlarımıza ve hocalarımıza teşekkür ederiz.

Prediction of Nevşehir Province Air Quality with Markov Chain

Abstract

In this article, basic air pollutant parameters such as PM10, SO2, CO, NO2, and O3 at µg m-3 level in Nevşehir Province were monitored between 01.08.2019-19.11.2020 and Air Quality Index (AQI) values were calculated depending on these parameters. Nevşehir Province AQI values vary between good and sensitive degrees. While monitoring data were used in the training of the models, the data calculated between 20.11.2020-20.12.2020 and not used in the training of the models were also used in the checking. In this study, Nevşehir Province AQI values were successfully predicted using small-scale and discrete-time Markov Chain Models at 0.887 and 0.982, respectively. The discrete-time Markov Chain Model, which has less variable status depending on the air quality of Nevşehir Province, has been found to be more successful in predicting the AQI data used both in training and checking. As a result, it has been revealed that Markov Chain models can be used as a successful method to predict different weather conditions.

Keywords

Air pollution, Air quality index, Markov Chain, Model, Nevşehir, Forecast

References

• [1] L. Yang, M. Li, W. Li, Y. Jiang, and Z. Qiang, “Bench-and pilot-scale studies on the removal of pesticides from water by VUV/UV process,” Chemical Engineering Journal, vol. 342, pp. 155-162, 2018.
• [2] Y. J. Wu and J.-C. Chen, “A structured method for smart city project selection,” International Journal of Information Management, pp. 101981, 2019.
• [3] World Health Organization, “WHO Air quality guidelines for particulate matter, ozone, nitrogen dioxide and sulfur dioxide: global update 2005: summary of risk assessment, Geneva, Switzerland, WHO/SDE/PHE/OEH/06.02, 2006.
• [4] Y.-Y. Lee, Y.-K. Hsieh, G.-P. Chang-Chien, and W. Wang, “Characterization of the air quality index in southwestern Taiwan,” Aerosol and Air Quality Research, vol. 19, no. 4, pp. 749-785, 2019.
• [5] K. N. Andersen, J. A. Nielsen, and S. Kim, “Use, cost, and digital divide in online public health care: lessons from Denmark,” Transforming Government: People, Process and Policy, pp. 197-211, 2019.
• [6] J. P. S Sidhu, W. Ahmed, W. Gernjak, R. Aryal, D. McCarthy, A. Palmer, P. Kolotelo, and S. Toze, “Sewage pollution in urban stormwater runoff as evident from the widespread presence of multiple microbial and chemical source tracking markers,” Science of the Total Environment, vol. 463, pp. 488-496, 2013.
• [7] U.S. Environmental Protection Agency, “A guide to air quality and your health,” New York, USA, EPA-456/F-14-002, 2009.
• [8] C. Zhu, R. Fan, J. Sun, M. Luo, and Y. Zhang, “Exploring the fluctuant transmission characteristics of Air Quality Index based on time series network model,” Ecological Indicators, vol. 108, pp. 105681, 2020.
• [9] X. Yang, Z. Zhang, Z. Zhang, L. Sun, C. Xu, and L. Yu, “A long-term prediction model of Beijing haze episodes using time series analysis,” Computational Intelligence and Neuroscience, vol. 2016, 2016.
• [10] P. Hajek and V. Olej, “Predicting common air quality index-the case of czech microregions,” Aerosol and Air Quality Research, vol. 15, no. 2, pp. 544-555, 2015.
• [11] Y. Qi and S. Ishak, “A Hidden Markov Model for short term prediction of traffic conditions on freeways,” Transportation Research Part C: Emerging Technologies, vol. 43, pp. 95-111, 2014.
• [12] J. R. Crusoe and K. Ahlin, “Users’ activities for using open goandrnment data–a process framework,” Transforming Goandrnment: People, Process and Policy, pp. 213-236, 2019.
• [13] S. Elgharbi, M. Esghir, O. Ibrihich, A. Abarda, S. El Hajji, and S. Elbernoussi, “Grey-Markov Model for the prediction of the electricity production and consumption,” in International Conference on Big Data and Networks Technologies, Leuven, Belgium: Springer, 2019, pp. 206-219.
• [14] R. P. Sen, “Markov versus non-markov processes,” in Operations Research: Applications And Algorithms, Eastern Economy Ed., New Delhi: PHI Learning Private Limited, 2012, vol. 3.
• [15] C. Chatfield, “Statistical inference regarding Markov chain models,” Journal of the Royal Statistical Society: Series C (Applied Statistics), vol. 22, no. 1, pp. 7-20, 1973.
• [16] K. Y. Chan and L. Jian, “Identification of significant factors for air pollution leandls using a neural network based knowledge discoandry system,” Neurocomputing, vol. 99, pp. 564-569, 2013.
• [17] N. Güler and Ö. G. İşçi, “The regional prediction model of PM10 concentrations for Turkey,” Atmospheric Research, vol. 180, pp. 64-77, 2016.
• [18] B. T. Ong, K. Sugiura, and K. Zettsu, “Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM 2.5,” Neural Computing and Applications, vol. 27, no. 6, pp. 1553-1566, 2016.
• [19] N. Suhaimi, N. A. Ghazali, M. Y. Nasir, M. I. Z. Mokhtar, and N. A. Ramli, “Markov Chain Monte Carlo method for handling missing data in air quality datasets,” Malaysian Journal of Analytical Sciences, vol. 21, no. 3, pp. 552-559, 2017.
• [20] L. Luo, F. Zhang, W. Zhang, L. Sun, C. Li, D. Huang, and B. Wang, “Markov chain-based acute effect estimation of air pollution on elder asthma hospitalization,” Journal of Healthcare Engineering, vol. 2017, 2017.
• [21] Á. Gómez-Losada, “Clustering air monitoring stations according to background and ambient pollution using hidden Markov models and multidimensional scaling,” Data Science, pp. 123-132, 2017.
• [22] A. Nebenzal and B. Fishbain, “Long-term forecasting of nitrogen dioxide ambient leandls in metropolitan areas using the discrete-time Markov model,” Environmental Modelling & Software, vol. 107, pp. 175-185, 2018.
• [23] M. Nicas, “Markov modeling of contaminant concentrations in indoor air,” AIHAJ-American Industrial Hygiene Association, vol. 61, no. 4, pp. 484-491, 2000.
• [24] A. Plaia and M. Ruggieri, “Air quality indices: a review,” Reviews in Environmental Science and Bio/Technology, vol. 10, no. 2, pp. 165-179, 2011.
• [25] M. H. Chi, “The long-run behavior of Markov chains,” Linear Algebra And Its Applications, no. 244, pp. 111-121, 1996.
• [26] C. M. Grinstead and J. L. Snell, Grinstead and Snell's Introduction to Probability: The CHANCE Project, USA: American Mathematical Society, 2006.
• [27] H. J. Fernando, M. C. Mammarella, G. Grandoni, P. Fedele, R. Di Marco, R. Dimitrova, and P. Hyde, “Forecasting PM10 in metropolitan areas: Efficacy of neural networks,” Environmental Pollution, vol. 163, pp. 62-67, 2012.
• [28] S. M. Ross, Introduction To Probability Models, 11th ed., USA: Elsevier Academic Press, 2014.
• [29] N. J. Vickers, “Animal communication: when i’m calling you, will you answer too?,” Current Biology, vol. 27, no. 14, pp. R713-R715, 2017.
• [30] A. D. Sahin and Z. Sen, “First-order Markov chain approach to wind speed modelling,” Journal of Wind Engineering and Industrial Aerodynamics, vol. 89, no. 3-4, pp. 263-269, 2001.
• [31] E. R. Rodrigues, M. H. Tarumoto, and G. Tzintzun, “Application of a non-homogeneous Markov chain with seasonal transition probabilities to ozone data,” Journal of Applied Statistics, vol. 46, no. 3, pp. 395-415, 2019.
• [32] L. Hoyos, P. Lara, E. Ortiz, R. L. Bracho, and J. González, “Evaluation of air pollution control policies in Mexico City using finite Markov chain observation model,” Revista de Matemática: Teoría y Aplicaciones, vol. 16, no. 2, pp. 255-266, 2009.
• [33] S. A. Kalogirou, “Artificial neural networks in renewable energy systems applications: a review,” Renewable and Sustainable Energy Reviews, vol. 5, no. 4, pp. 373-401, 2001.
• [34] R. Liu and Y. Ge, “Smart home system design based on Internet of Things,” in 12th International Conference on Computer Science and Education (ICCSE), 2017, pp. 444-448.
• [35] T. C. Çevre and Şehircilik Bakanlığı. (2021, 23 Nisan). Hava kalitesi izleme sistemi [Çevrimiçi]. Erişim: https://sim.csb.gov.tr/Home/HKI?baslik=HAVZA%20%C4%B0ZLEME%20S%C4%B0STEM%C4%B0
• [36] Ü. A. Şahin vd., “Temporal variations of atmospheric black carbon and its relation to other pollutants and meteorological factors at an urban traffic site in Istanbul,” Atmospheric Pollution Research, vol. 11, no. 7, pp. 1051-1062, 2020.
• [37] M. Krzyzanowski and A. Cohen, “Update of WHO air quality guidelines,” Air Quality, Atmosphere & Health, vol. 1, no. 1, pp. 7-13, 2008.
• [38] A. Dolar ve H. T. K. Saraç, “Türkiye’nin doğu ı̇llerindeki hava kalitesinin PM10 yönüyle ı̇ncelenmesi,” Iğdır Üniandrsitesi Fen Bilimleri Enstitüsü Dergisi, c. 5, no. 4, ss. 25-32, 2015.
• [39] W. Wang, K. Cui, R. Zhao, L.-T. Hsieh, and W.-J. Lee, “Characterization of the air quality index for Wuhu and Bengbu cities, China,” Aerosol and Air Quality Research, vol. 18, no. 5, pp. 1198-1220, 2018.
• [40] J.-C. Chen and Y. J. Wu, “Discrete-time Markov chain for prediction of air quality index,” Journal of Ambient Intelligence and Humanized Computing, pp. 1-10, 2020.
• [41] World Health Organization, Air Quality Guidelines: Global Update 2005: Particulate Matter, Ozone, Nitrogen Dioxide, And Sulfur Dioxide, Copenhagen, Denmark: World Health Organization Regional Office for Europe, 2006.
• [42] I. Suryati, H. Khair, and D. Gusrianti, “Analysis of air quality index distribution of PM10 and O3 concentrations in ambient air of Medan City, Indonesia,” Journal of Physical Science, vol. 29, pp. 37-48, 2018.