HAVA KALİTESİ PARAMETRELERİNİN TAHMİNİ VE MEKANSAL DAĞILIMI İÇİN MAKİNE ÖĞRENMESİ YÖNTEMLERİNİN KULLANILMASI

Yıl 2020, Cilt: 9 Sayı: 1, 37 - 47, 30.01.2020

Yeşim Dokuz , Aslı Bozdağ , Begüm Gökçek

https://doi.org/10.28948/ngumuh.654092

Cited By: 5

Öz

Hava kirliliği, nüfus ve endüstrileşmenin artması ile birlikte günümüzde küresel boyutta yaşanan sorunlardan biri haline gelmiştir. Bu nedenle hava kirletici parametreler düzenli aralıklarla ölçülmeli ve ölçüm sonuçları değerlendirilerek gerekli tedbirler alınmalıdır. Hava kirliliğinin önlenmesi amacıyla kirletici parametreler bir model kapsamında değerlendirilmesi gerekmektedir. Son zamanlarda günümüzde hava kirliliğine yönelik objektif ve daha hassas sonuçların elde edilmesi için yapay zeka teknolojilerine ait makine öğrenmesi algoritmalarından yararlanılarak elde edilen çalışmalar yapılmaktadır. Bu çalışmada, öncelikli olarak hava kirletici parametrelerin özellikleri, çevreye olan etkileri ve bu parametrelerin tahmin edilmesi ve izlenmesinin gerekliliği açıklanmıştır. Ardından bu parametrelerin değerlendirilmesinde uygulanan makine öğrenmesi yöntemlerinin neler olduğu; hangi parametrelerin kullanıldığı, kullanım amaçları, kısıtlılıkları ve elde edilen doğruluk düzeyleri açısından incelenerek kullanılan yöntemlere ve çalışma prensiplerine ilişkin detaylı bilgi verilmiştir. Bu çalışma, hava kalitesinin iyileştirilerek sürdürülebilir bir çevrenin elde edilmesinde hangi parametreler hangi yöntem kullanılarak nasıl bir analiz ile incelenmeli sorusuna ilişkin seçim karmaşasının çözümlenmesine yönelik gelecek çalışmalara bir fikir sunmaktadır.

Anahtar Kelimeler

hava kirletici parametre, makine öğrenmesi, mekansal dağılım, yapay zeka, tahmin modellemesi

Kaynakça

• [1] Y. A. Ayturan, “Derin Öğrenme İle Havadaki Partikül Madde Konsantrasyonu Tahmini”, KTO Karatay Üniversitesi Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, Konya, 2019.
• [2] S. Yeongkwon, A. R. Osornio-Vargas, M. S. O'Neill, P. Hystade, J. L. Texcalac-Sangrador, P. Ohman-Strickland, Q. Menga, S. Schwander, “Land use regression models to assess air pollution exposure in Mexico City using finer spatial and temporal input parameters”, Science of the Total Environment 639, 40–48, 2018.
• [3] H. Chu, J. Wei, W. Wu, “Streamflow prediction using LASSO-FCM-DBN approach based on hydrometeorological condition classification”, Journal of Hydrology, https://doi.org/10.1016/j.jhydrol.2019.124253.
• [4] G. Xua, X. Ren, K. Xiong, L. Li, X. Bi, Q. Wu, “Analysis of the driving factors of PM2.5 concentration in the air: A case study of the Yangtze River Delta, China”, Ecological Indicators 110, 105889, 2020.
• [5] S. Zhu, X. Lian, H. Liu, J. Hu, Y. Wang, J. Che, “Daily air quality index forecasting with hybrid models: A case in China”, Environmental Pollution 231, 1232-1244, 2017.
• [6] S. Zhu, X. Lian, L. Wei, J. Che, X. Shena, L. Yang, X. Qiu, X. Liu, W. Gao, X. Ren, J. Li, “PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors”, Atmospheric Environment 183, 20–32, 2018.
• [7] W. Fan, F. Si, S. Ren, C. Yu, Y. Cui, P. Wang, “Integration of continuous restricted Boltzmann machine and SVR in NOx emissions prediction of a tangential firing boiler”, Chemometrics and Intelligent Laboratory Systems 195, 103870, 2019.
• [8] J. Murillo-Escobara, J.P. Sepulveda-Suescun, M.A. Correa, D. Orrego-Metaute, “Forecasting concentrations of air pollutants using support vector regression improved with particle swarm optimization: Case study in Aburrá Valley, Colombia”, Urban Climate 29, 100473, 2019.
• [9] H. Sun, D. Gui, B. Yan, Y. Liu, W. Liao, Y. Zhu, C. Lu, N. Zhao, “Assessing the potential of random forest method for estimating solar radiation using air pollution index”, Energy Conversion and Management 119, 121–129, 2016.
• [10] Rubal, D. Kumar, “Evolving Differential evolution method with random forest for prediction of Air Pollution” , Procedia Computer Science 132, 824–833, 2018.
• [11] J. A. Kaminska, “The use of random forests in modelling short-term air pollution effects based on traffic and meteorological conditions: A case study in Wrocław”, Journal of Environmental Management 217, 164-174, 2018.
• [12] Y. Wang, Y. Du, J. Wang, T. Li, “Calibration of a low-cost PM2.5 monitor using a random forest model”, Environment International 133, 105161, 2019.
• [13] Y. Fan, L. Hou, K. X. Yan, “On the density estimation of air pollution in Beijing”, Economics Letters 163, 110–113, 2018.
• [14] C. Wen, S. Liu, X. Yao, L. Penga, X. Li, Y. Hua, T. Chi, “A novel spatiotemporal convolutional long short-term neural network for air pollution prediction”, Science of the Total Environment 654, 1091–1099, 2019.
• [15] E. Espositoa, S. De Vitoa, M. Salvatoa, V. Brightb, R.L. Jonesb, O. Popoola, “Dynamic neural network architectures for on field stochasticcalibration of indicative low cost air quality sensing systems”, Sensors and Actuators B 231, 701–713, 2016.
• [16] Q. Song, M. R. Zhao, X. H. Zhou, Y. Xue, Y. J. Zheng, “Predicting gastrointestinal infection morbidity based on environmental pollutants: Deep learning versus traditional models”, Ecological Indicators 82, 76–81, 2017.
• [17] J. Ma, Y. Ding, J. C.P. Cheng, F. Jiang, Y. Tan, V. J.L. Gan, Z. Wan, “Identification of high impact factors of air quality on a national scale using big data and machine learning techniques”, Journal of Cleaner Production, https://doi.org/10.1016/j.jclepro.2019.118955.
• [18] Y. Zhou, F. J. Chang, L. C. Chang, I-F. Kao, Y. S. Wang, “Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts”, Journal of Cleaner Production, 209, 134-145, 2019.
• [19] Y. Park, B. Kwon, J. Heo, X. Hu, Y. Liu, T. Moon, “Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks”, Environmental Pollution, https://doi.org/10.1016/j.envpol.2019.113395
• [20] Y. Qi, Q. Li, H. Karimiana, D. Liu, “A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory”, Science of the Total Environment, 664, 1–10, 2019.
• [21] N. Dong, J. F. Chang, A. G. Wu, Z. K. Gao, “A novel convolutional neural network framework based solar irradiance prediction method”, Electrical Power and Energy Systems, 114, 105411, 2020.
• [22] A. Sayeed, Y. Choi, E. Eslami, Y. Lops, A. Roy, J. Jung, “Using a deep convolutional neural network to predict 2017 ozone concentrations, 24 hours in advance”, Neural Networks,121, 396–408, 2020.
• [23] R. Feng, H. Zheng, H. Gao, A. Zhang, C. Huang, J. Zhang, K. Luo, J. Fan, “Recurrent Neural Network and random forest for analysis and accurate forecast of atmospheric pollutants: A case study in Hangzhou, China”, Journal of Cleaner Production, 231, 1005-1015, 2019.
• [24] Z. Liu, C. J. Sullivan, “Prediction of weather induced background radiation fluctuation with recurrent neural networks”, Radiation Physics and Chemistry, 155, 275–280, 2019.
• [25] H.S. Peavy, D.R. Rowe, G. Tchobanoglous, Mcgraw, "Environmental Engineering", Hill Inc., Singapore, 1985.
• [26] T. Godish, “Air Quality 4 Edition”, Lewis Publishers, A CRC Press Company, p 32-185,2004.
• [27] EC,Cleaner air fol all, http://ec.europa.eu/environment/air/cleaner_air/ , (April, 2017)
• [28] G. E. Fan, M. Qıu, H. Hu, H. Tıan, L. Wang, X. Xu, G. Weı, X. “Ambient Levels Associated With Reduced Risk of Initial Outpatient Visits For Tuberculosis: A Population Based Time Series Analysis”, Environmental Pollution, 28, 408-415, 2017.
• [29] A. Barbulescu, L. Barbes, “Mathematical Modeling Of Sulfur Dioxide Concentration in The Western Part Of Romania”, Journal of Environmental Management, 204 Part 3, 825-830, 2017.
• [30] D. Grano, “Clean Air Act requirements: Effect on Emissions of NO, from stationary sources. In: Ozkan, U.S., Agarwal, SK. And Marcelin, G. (Eds.), Reduction of Nitrogen Oxide Emissions, ACS Symposium Series 587”, American Chemical Society, Washington, DC, pp. 14-31, 1995.
• [31] Tosun, E., “Türkiye’nin 2009-2016 Yılları Arasındaki Hava Kalitesi Verilerinin Değerlendirilmesi”, Hacettepe Üniversitesi Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, Ankara, 2017.
• [32] A. Müezzinoğlu, “Hava Kirliliği ve Kontrolünün Esasları, Dokuz Eylül Yayınları, İzmir, 2005.
• [33] M. Türkeş, U. M. Sümer, G. Çetiner, “Küresel İklim Değişikliği Ve Olası Etkileri”, Çevre Bakanlığı, Birleşmiş Milletler İklim Değişikliği Çerçeve Sözleşmesi Seminer Notları, 7-24, Çkök Gn. Md., Ankara, 2000.
• [34] R. Tibshirani, "Regression shrinkage and selection via the lasso", Journal of the Royal Statistical Society: Series B (Methodological), 58(1): 267-288, 1996.
• [35] V. N. Vapnik, “The Nature of Statistical Learning Theory”, Springer Science & Business Media, 1st Edition, 1995
• [36] H. Drucker, C.J. Burges, L. Kaufman, A.J. Smola, V. Vapnik, “Support vector regression machines”, Advances in Neural Information Processing Systems (pp. 155-161), 1997.
• [37] L. Breiman, “Random forests”, Machine Learning, 45(1): 5-32, 2001.
• [38] Z. Yao, L.R. Walter. "A regression-based K nearest neighbor algorithm for gene function prediction from heterogeneous data", BMC Bioinformatics, 7(1): 1-11, 2006.
• [39] Y. Bengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning, 2(1): 1-127, 2009.
• [40] D.E. Rumelhart, G.E. Hinton, R.J. Williams, “Learning representations by back-propagating errors”, Nature, 323, 533–536, 1986.
• [41] S. Hochreiter, J. Schmidhuber, “Long Short-Term Memory”, Neural Computation, 9(8): 1735-1780, 1997.
• [42] I. Goodfellow, Y. Bengio, A. Courville, “Deep Learning”, MIT Press, p. 326, 2016.
• [43] J. Ma, J.C.P. Cheng, C. Lin, Y. Tan, ve J. Zhang, “Improving air quality prediction accuracy at larger temporal resolutions using deep learning and transfer learning techniques”. Atmospheric Environment, 214, 2019.
• [44] Ertürk, A., Ekdal, A., Gurel, M., Yuceil, K., ve Tanik, A. “Use of mathematical models to estimate the effect of nutrient loadings on small streams”. Fresen. Environ. Bull. 13(11b), 1361-1370, 2004.
• [45] Ataol, M. “Burdur Gölü’nde seviye değişimleri”, Coğrafi Bilimler Dergisi. 8(1), 77-92, 2010.
• [46] Liu, H., Wang, L., Yang, J., Nakagoshi, N., Liang C., Wang, W. ve Lv, Y. “Predictive modeling of the potential naturel vegetation pattern in Northeast China. Ecological Research”. 24, 1313-1321, 2009.
• [47] Ozkan, K. ve Senturk, Ö. “The applicatıon of group discrimination techniques to predict the potential distribution of turpentine tree”. In Proceedings of International Scientific Conference People Buildings and Environment, 7-9 October, Lednice, Czech Republic, 728-736, 2012.
• [48] Javadian, M., Shamskooshki, H. ve Momeni, M. "Application of sustainable urban development in environmental suitability analysis of educational land use by using AHP and GIS in Tehran”, Procedia Engineering, 21, 72-80, 2011.
• [49] Malczewski, J. “GIS-based land-use suitability analysis: a critical overview”, Progress in planning, Elsevier, 62-65, 2004.
• [50] Tamas, W., Notton, G., Paoli, C., Nivet, M-L. ve Voyant, C. “Hybridization of Air Quality Frecasting Models Using Machine Learning and Clustering: An Orginal Approach to Detect Pollutant Peaks, Aerosol and Air Qaulity Research, 16, 405-416, 2016.
• [51] Rybarczyk, Y. ve Zalakeviciute, R., “Machine Learning Approach to Forecasting Urban Pollution”. IEEE Ecuador Technical Chapter Meetings, 2016.
• [52] Zhan, Y., Luo, Y., Deng, X., Chen, H., Grieneisen, M. L., Shen, X., Zhu, L. ve Zhang, M. “Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm. Atmospheric Environment, 155, 129-139, 2017.
• [53] Deters, J. K., Zalakeviciute, R., Gonzalez, M. ve Rybarczyk, Y.”Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters”. Journal of Electrical and Computer Engineering, Makale ID 5106045, 14, 2017
• [54] García Nieto, P.J., Sánchez Lasheras, F., García-Gonzalo, E. ve de Cos Juez, F.J. “PM10 concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM,MLP, VARMA and ARIMA: A case study”. Science of the Total Environment, 621,753–761, 2018.
• [55] Huang, C-J., ve Kuo, P-H. “A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities”, Sensors, 18 (2220), 2018.
• [56] Chen, G., Li, S., Knibbs, L.D., Hamm, N.A.S., Cao, W., Li, T., Guo, J., Ren, H., Abramson, M.J. ve Guo, Y. “A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information”. Science of the Total Environment, 636, 52–60, 2018.
• [57] Xu, Y., Chak, Ho, H., Wong, M.S., Deng, C., Shi, Y., Chan, T-C. ve Knudby, A. “Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of groundlevel PM2.5. Environmental Pollution, 242, 1417- 1426, 2018.
• [58] Chen, S., Mihara, K. ve Wen, “Time series prediction of CO2, TVOC and HCHO based on machine learning at different sampling points”. Building and Environment, 146, 238–246, 2018.
• [59] Requia, W.J., Coull, B. A. ve Koutrakis, P. “Evaluation of predictive capabilities of ordinary geostatistical interpolation, hybrid interpolation, and machine learning methods for estimating PM2.5 constituents over space”. Environmental Research, 175, 421–433, 2019.
• [60] Suleiman, A., Tight, M.R. ve Quinn, A.D. “Applying machine learning methods in managing urban concentrations of traffic-related particulate matter (PM10 and PM2.5)”. Atmospheric Pollution Research, 10, 134–144, 2019.
• [61] Lim, C.C., Kim, H., Ruzmyn Vilcassim, M.J., Thurston, G.D., Gordon, T., Chen, L-C., Lee, K., Heimbinder, M. ve Kim, S-Y. “Mapping urban air quality using mobile sampling with low-cost sensors and machine learning in Seoul, South Korea”. Environment International, 131, 105022,2019.
• [62] Zhong, J., Zhang, X. ve Wang, Y. “Relatively weak meteorological feedback effect on PM2.5 mass change in Winter 2017/18 in the Beijing area: Observational evidence and machine-learning estimations”. Science of the Total Environment, 664, 140–147, 2019.
• [63] Li, X. ve Zhang, X. “Predicting ground-level PM2.5 concentrations in the Beijing-Tianjin-Hebei region: A hybrid remote sensing and machine learning”. Approach. Environmental Pollution, 249, 735-749, 2019.
• [64] Liu, J., Weng, F. ve Li, Z. “Satellite-based PM2.5 estimation directly from reflectance at the top of the atmosphere using a machine learning algorithm”. Atmospheric Environment 208, 113–122, 2019.
• [65] Irmak, M. E. ve Aydilek, İ.B. “Hava Kalite İndeksinin Tahmin Başarısının Artırılması için Topluluk Regresyon Algoritmalarının Kullanılması”. Academic Platform Journal of Engineering and Science 7-3, 507-514, 2019.