بهبود دقت برآورد غلظت ازن در سطح زمین با استفاده از محصولات ماهوارهای و یادگیری ماشین | ||
| نشریه سنجش از دور و GIS ایران | ||
| مقاله 2، دوره 15، شماره 4 - شماره پیاپی 60، 1402، صفحه 17-30 اصل مقاله (3.5 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.48308/gisj.2022.102758 | ||
| نویسندگان | ||
| رسول آتشی دلیگانی1؛ مینا مرادی زاده* 2؛ بهنام تشیع3 | ||
| 1دانشجوی کارشناسی ارشد، مهندسی نقشهبرداریـ گرایش سنجش از دور، دانشکدة عمران و حملونقل، دانشگاه اصفهان، اصفهان، ایران | ||
| 2استادیار گروه مهندسی نقشهبرداری، دانشکدة عمران و حملونقل، دانشگاه اصفهان، اصفهان، ایران | ||
| 3استادیار گروه مهندسی نقشهبرداری، دانشکدة عمران و حملونقل، دانشگاه اصفهان، اصفهلن، ایران | ||
| چکیده | ||
| ازن نزدیک به سطح زمین یکی از آلایندههای بسیار خطرناک است که تأثیرات زیانبار درخور توجهی در سلامت ساکنان مناطق شهری دارد. هدف از این مطالعه شناسایی عوامل مؤثر در غلظت ازن و مدلسازی تغییرات آن، با استفاده از دادههای ماهوارهای و روشهای گوناگون یادگیری ماشین در شهر تهران است. بدینمنظور دادههای غلظت آلایندهها، دادههای هواشناسی و دمای سطح خاک، طی بازة زمانی بین سالهای 2015 تا 2021، بهکار رفت. پساز محاسبة همبستگی بین غلظت ازن و پارامترهای مستقل، طی پنج حالت متفاوت، با پارامترهای ورودی و روش یادگیری متفاوت و بهکارگیری پالایش دادهها، غلظت ازن مدلسازی شد. در حالت اول و دوم، مدلسازی با استفاده از دادههای غلظت آلایندهها و دادههای هواشناسی با روش رگرسیون خطی چندمتغیره انجام شد. تنها تفاوت این دو حالت، پالایش دادههای ورودی بهشیوة WTEST در روش دوم است. در حالت سوم، دمای سطح خاک به دادههای ورودی افزوده شد و در حالت چهارم و پنجم، بهترتیب مدلسازی ازن با استفاده از شبکة عصبی چندلایهای و شبکة عصبی بازگشتی انجام شد. مقایسة این حالتها نشان داد که مدلسازیهای مراحل اول تا پنجم، بهترتیب با ضریب تعیین تعدیلشدة 5/0، 64/0، 69/0، 74/0 و 8/0 توانایی بازیابی غلظت ازن را داشتهاند. همچنین مشخص شد در بین آلایندههای گوناگون، مونوکسید نیتروژن، دیاکسید نیتروژن، نیتراکس و از میان دادههای هواشناسی دما، رطوبت و سرعت باد بیشترین تأثیر را در غلظت ازن دارند. افزودن دمای سطح خاک به دادههای ورودی نیز افزایش پنجدرصدی دقت را در برآورد غلظت ازن، بههمراه داشت. | ||
| کلیدواژهها | ||
| غلظت ازن؛ یادگیری ماشین؛ رگرسیون خطی چندمتغیره؛ شبکة عصبی بازگشتی؛ آلایندة جوّی | ||
| عنوان مقاله [English] | ||
| Improving the Accuracy of Ground Surface Ozone Concentration Estimation Using Satellite Products and Machine Learning | ||
| نویسندگان [English] | ||
| Rasoul Atashi Deligani1؛ Mina Moradizadeh2؛ Behnam Tashayo3 | ||
| 1M.Sc. Student, Dep. of Geomatics, Faculty of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran | ||
| 2Assistant Prof., Dep. of Geomatics, Faculty of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran | ||
| 3Assistant Prof., Dep. of Geomatics, Faculty of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran | ||
| چکیده [English] | ||
| Ground surface ozone is one of the most dangerous pollutants that has significant harmful effects on the residents of urban areas. The purpose of this study is to identify the factors affecting ozone concentration and modeling its changes using satellite data and different machine learning methods in Tehran. For this purpose, pollutant concentration and meteorological data were used along with the satellite product of land surface temperature (LST) in the period from 2015 to 2021. After calculating the correlation between ozone concentration and independent parameters, ozone concentration modeling was done in five different modes in terms of input parameters and learning method and applying data refinement. In the first and second mode, modeling was done using pollutant concentration and meteorological data through multivariate linear regression method. The only difference between these two modes is the filtering of the input data using the WTEST method in the second mode. In the third mode, the LST product was added to the input data, and in the fourth and fifth mode, ozone modeling was done using multilayer neural network and recurrent neural network, respectively. The comparison of the five modes showed that the modeling of the first to fifth stages with adjusted coefficient of determination of 0.5, 0.64, 0.69, 0.74 and 0.8 were able to recover the ozone concentration, respectively. It was also found that among different pollutants, nitrogen monoxide, nitrogen dioxide and nitrox have the greatest impact on ozone concentration, just as temperature, humidity and wind speed are the most influential among meteorological data. Although the use of WTEST statistics led to the identification and elimination of inconsistencies and errors in the observations of pollution measurement stations, the neural network learning method showed better performance in modeling than multivariate regression due to its less sensitivity to noise. As a notable result, adding the LST product to the input data brought a 5% increase in accuracy in estimating ozone concentration. | ||
| کلیدواژهها [English] | ||
| Ozone concentration, Machine learning, Multivariate linear regression, Recurrent neural network, Atmospheric pollutant | ||
| مراجع | ||
|
Abdul-Wahab, S.A., Bakheit, C.S. & Al-Alawi, S.M., 2005, Principal Component and Multiple Regression Analysis in Modelling of Ground-Level Ozone and Factors Affecting Its Concentrations, Environmental Modelling & Software, 20(10), PP. 1263-1271. https://doi.org/ 10.1016/j.envsoft.2004.09.001 Abdullah, S., Nasir, N.H.A., Ismail, M., Ahmed, A.N. & Jarkoni, M.N.K., 2019, Development of Ozone Prediction Model in Urban Area, International Journal of Innovative Technology and Exploring Engineering, 8(10), PP. 2263-2267. https://doi.org/ 10.35940/ijitee.J1127.0881019 Ahamad, F., Latif, M.T., Tang, R., Juneng, L., Dominick, D. & Juahir, H., 2014, Variation of Surface Ozone Exceedance around Klang Valley, Malaysia. Atmospheric Research, 139, PP. 116-127. https://doi.org/ 10.1016/j.atmosres.2014.01.003 Ahmadi, M.M. & Mahmoudi, P., 2013, Analysis of Tehran Air Pollution Data in Recent Decade (2000-2009), IJHE, 6(1), PP. 33-44. Asl, F.B., Leili, M., Vaziri, Y., Arian, S.S., Cristaldi, A., Conti, G.O. & Ferrante, M., 2018, Health Impacts Quantification of Ambient Air Pollutants Using AirQ Model Approach in Hamadan, Iran, Environmental Research, 161, PP. 114-121. https://doi.org/ 10.1016/j.envres.2017.10.050 Barrero, M., Grimalt, J.O. & Cantón, L., 2006, Prediction of Daily Ozone Concentration Maxima in the Urban Atmosphere, Chemometrics and Intelligent Laboratory Systems, 80(1), PP. 67-76. https://doi.org/ 10.1016/j.chemolab.2005.07.003
Biancofiore, F., Verdecchia, M., Di Carlo, P., Tomassetti, B., Aruffo, E., Busilacchio, M., Bianco, S., Di Tommaso, S. & Colangeli, C., 2015, Analysis of Surface Ozone Using a Recurrent Neural Network, Science of the Total Environment, 514, PP. 379-387. https://doi.org/10.1016/j.scitotenv.2015.01.106 Booker, F., Muntifering, R., McGrath, M., Burkey, K., Decoteau, D., Fiscus, E., Manning, W., Krupa, S., Chappelka, A. & Grantz, D., 2009, The Ozone Component of Global Change: Potential Effects on Agricultural and Horticultural Plant Yield, Product Quality and Interactions with Invasive Species, Journal of Integrative Plant Biology, 51(4), PP. 337-351. https://doi.org/10.1111/j.1744-7909.2008.00805.x Draxler, R.R., 2000, Meteorological Factors of Ozone Predictability at Houston, Texas, Journal of the Air & Waste Management Association, 50(2), PP. 259-271. https://doi.org/10.1080/10473289.2000.10463999 Gvozdić, V., Kovač-Andrić, E. & Brana, J., 2011, Influence of Meteorological Factors NO 2, SO 2, CO and PM 10 on the Concentration of O 3 in the Urban Atmosphere of Eastern Croatia, Environmental Modeling & Assessment, 16(5), PP. 491-501. https://doi.org/ 10.1007/s10666-011-9256-4 Hastie, T., Tibshirani, R., Friedman, J.H. & Friedman, J.H., 2009, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Vol. 2), Springer. Hollaway, M.J., Arnold, S., Challinor, A.J. & Emberson, L., 2012, Intercontinental Trans-Boundary Contributions to Ozone-Induced Crop Yield Losses in the Northern Hemisphere, Biogeosciences, 9(1), PP. 271-292. https://doi.org/ 10.5194/bg-9-271-2012, 2012. Huang, Y., Yang, Z. & Gao, Z., 2019, Contributions of Indoor and Outdoor Sources to Ozone in Residential Buildings in Nanjing, International Journal of Environmental Research and Public Health, 16(14), P. 2587. https://doi.org/ 10.3390/ijerph16142587 Ito, K., De Leon, S.F. & Lippmann, M., 2005, Associations between Ozone and Daily Mortality: Analysis and Meta-Analysis, Epidemiology, 16(4), PP. 446-457. https://doi.org/10.1097/01.ede.0000165821.90114.7f Javanbakht Amiri, S. & Khatami, S.H., 2012, The Study of the Correlation between Air Quality Index Pollution and Meteorological Parameters in Tehran with Regression Analysis Approach, Human and Environment, 10(34), PP. 15-28. Kampa, M. & Castanas, E., 2008, Human Health Effects of Air Pollution, Environmental Pollution, 151(2), PP. 362-367. https://doi.org/ 10.1016/j.envpol.2007.06.012 Li, X. & Rappenglück, B., 2014, A WRF–CMAQ Study on Spring Time Vertical Ozone Structure in Southeast Texas, Atmospheric Environment, 97, PP. 363-385. https://doi.org/10.1016/j.atmosenv.2014.08.036 Moustris, K., Nastos, P., Larissi, I. & Paliatsos, A., 2012, Application of Multiple Linear Regression Models and Artificial Neural Networks on the Surface Ozone Forecast in the Greater Athens Area, Greece, Advances in Meteorology, 2012. https://doi.org/ 10.1155/2012/894714 Özbay, B., 2012, Modeling the Effects of Meteorological Factors on SO2 and PM10 Concentrations with Statistical Approaches, Clean–Soil, Air, Water, 40(6), PP. 571-577. https://doi.org/ 10.1002/clen.201100356 Pak, U., Kim, C., Ryu, U., Sok, K. & Pak, S., 2018, A Hybrid Model Based on Convolutional Neural Networks and Long Short-Term Memory for Ozone Concentration Prediction, Air Quality, Atmosphere & Health, 11(8), PP. 883-895. https://doi.org/ 10.1007/s11869-018-0585-1 Reeves, C.E., Penkett, S.A., Bauguitte, S., Law, K.S., Evans, M.J., Bandy, B.J., Monks, P.S., Edwards, G.D., Phillips, G. & Barjat, H., 2002, Potential for Photochemical Ozone Formation in the Troposphere over the North Atlantic as Derived from Aircraft Observations during ACSOE, Journal of Geophysical Research: Atmospheres, 107(D23), ACH 14-11-ACH 14-14. https://doi.org/ 10.1029/2002JD002415 Ren, X., Mi, Z. & Georgopoulos, P.G., 2020, Comparison of Machine Learning and Land Use Regression for fine Scale Spatiotemporal Estimation of Ambient Air Pollution: Modeling Ozone Concentrations across the Contiguous United States, Environment International, 142, P. 105827. https://doi.org/10.1016/j.envint.2020.105827 Shan, W., Yin, Y., Lu, H. & Liang, S., 2009, A Meteorological Analysis of Ozone Episodes Using HYSPLIT Model and Surface Data, Atmospheric Research, 4(93), PP. 767-776. DOI: 10.1016/j.atmosres.2009.03.007 Sotoudeheian, S. & Arhami, M., 2014, Estimating Ground-Level PM 10 Using Satellite Remote Sensing and Ground-Based Meteorological Measurements over Tehran, Journal of Environmental Health Science and Engineering, 12(1), PP. 1-13. https://doi.org/ 10.1186/s40201-014-0122-6 Sousa, S., Martins, F.G., Alvim-Ferraz, M. & Pereira, M.C., 2007, Multiple Linear Regression and Artificial Neural Networks Based on Principal Components to Predict Ozone Concentrations, Environmental Modelling & Software, 22(1), PP. 97-103. https://doi.org/10.1016/j.envsoft.2005.12.002 Spellman, G., 1999, An Application of Artificial Neural Networks to the Prediction of Surface Ozone Concentrations in the United Kingdom, Applied Geography, 19(2), PP. 123-136. https://doi.org/10.1016/S0143-6228(98)00039-3 Sullivan, J.T., Rabenhorst, S.D., Dreessen, J., McGee, T.J., Delgado, R., Twigg, L. & Sumnicht, G., 2017, Lidar Observations Revealing Transport of O3 in the Presence of a Nocturnal Low-Level Jet: Regional Implications for “Next-Day” Pollution, Atmospheric Environment, 158, PP. 160-171. https://doi.org/ 10.1016/j.atmosenv.2017.03.039 Susaya, J., Kim, K.-H., Shon, Z.-H. & Brown, R.J., 2013, Demonstration of Long-Term Increases in Tropospheric O3 Levels: Causes and Potential Impacts, Chemosphere, 92(11), PP. 1520-1528. https://doi.org/10.1016/j.chemosphere.2013.04.017 Ul-Saufie, A.Z., Yahaya, A.S., Ramli, N.A., Rosaida, N. & Hamid, H.A., 2013, Future Daily PM10 Concentrations Prediction by Combining Regression Models and Feedforward Backpropagation Models with Principle Component Analysis (PCA), Atmospheric Environment, 77, PP. 621-630. https://doi.org/ 10.1016/j.atmosenv.2013.05.017 Vingarzan, R., 2004, A Review of Surface Ozone Background Levels and Trends, Atmospheric Environment, 38(21), PP. 3431-3442. https://doi.org/10.1016/j.atmosenv.2004.03.030 Xiang, S., Liu, J., Tao, W., Yi, K., Xu, J., Hu, X., Liu, H., Wang, Y., Zhang, Y., Yang, H., Hu, J., Wan, Y., Wang, X., Ma, J., Wang, X., Tao, S., 2020, Control of both PM2.5 and O3 in Beijing-Tianjin-Hebei and the surrounding areas, Atmospheric Environment, 224, 117259. https://doi.org/ 10.1016/j.atmosenv.2020.117259
| ||
|
آمار تعداد مشاهده مقاله: 6,008 تعداد دریافت فایل اصل مقاله: 3,247 |
||