تحلیل تطبیقی غلظت دیاکسیدگوگرد (SO2) در هوای آزاد با دادههای ماهوارهای توسط الگوریتمهای یادگیری ماشین - یک مطالعه موردی
محورهای موضوعی : منابع طبیعی و مدیریت زیست محیطی
ثمین رحیم زاده
1
,
مهدی قنبرزاده لک
2
*
,
آرزو سلیمانی
3
1 - دانشجوی کارشناسی ارشد مهندسی عمران-محیطزیست، دانشکده فنی و مهندسی، دانشگاه ارومیه، ایران
2 - دانشیار گروه مهندسی عمران، دانشکده فنی و مهندسی دانشگاه ارومیه، ایران
3 - دانش آموخته دکتری محیط زیست-آلودگی های محیط زیست، دانشکده منابع طبیعی و محیط زیست.دانشگاه ملایر، ملایر، ایران
کلید واژه: آلودگی هوای آزاد, SO2, Sentinel-5P, الگوریتم یادگیری ماشین, ارومیه, پارامترهای هواشناسی,
چکیده مقاله :
آلودگی هوا بهعنوان یکی از معضلات اصلی زیستمحیطی، تأثیرات منفی جدی بر سلامت عمومی و کیفیت زندگی دارد. دیاکسیدگوگرد، یکی از آلایندههای معیار کیفیت هوای آزاد، علاوه بر ایجاد اثرات زیانبار بر سلامت انسان، نقش مهمی در شکلگیری پدیدههای جهانی همچون بارشهای اسیدی دارد. پژوهش حاضر باهدف پایش و تحلیل غلظت دیاکسیدگوگرد در شهر ارومیه، از دادههای برگرفته از سنجنده تروپومی از ماهوارهای سنتینل 5-پی و دادههای زمینی، در ترکیب با الگوریتمهای یادگیری ماشین، بهره برده است. دادهها در بازه زمانی 1398 تا 1402 جمعآوری و پس از پیشپردازش، با استفاده از شاخصهای ضریب تعیین و ریشه میانگین مربعات خطا تحلیل شدند. نتایج نشان داد که ادغام دادههای زمینی و ماهوارهای، همراه با پارامترهای هواشناسی شامل دمای هوا، رطوبت نسبی، میزان تبخیر و تعرق، دمای تر، میزان ابرناکی و فشار هوا در ارتفاع ایستگاه، عملکرد مدلها را بهطور قابلتوجهی بهبود بخشیده است. الگوریتم XGBoost با مقادیر R² برابر 89/0 و RMSE معادل 57/0، بهعنوان بهترین مدل شناسایی شد. تحلیلهای بدون در نظر گرفتن پارامترهای هواشناسی، کاهش چشمگیر دقت مدلها را نشان داد، که اهمیت این پارامترها را تأیید میکند. دادههای ماهوارهای قابلیت ایفای نقش کلیدی در پوشش شکافهای اطلاعاتی ناشی از محدودیتهای ایستگاههای زمینی را دارند. همچنین، ترکیب فناوریهای نوین و دادههای محیطی میتواند به شناسایی دقیقتر آلایندهها و بهبود کیفیت هوا کمک کرده و بهعنوان الگویی برای سایر شهرهای ایران و کشورهای درحالتوسعه مطرح شود.
Air pollution, as one of the main environmental challenges, has significant adverse effects on public health and quality of life. Sulfur dioxide (SO₂), one of the criteria pollutants of ambient air quality, not only causes harmful impacts on human health but also plays a vital role in global phenomena such as acid rain. This study aims to monitor and analyze SO₂ concentrations in Urmia city using data from the TROPOMI sensor onboard the Sentinel-5P satellite, combined with ground-level data and machine learning algorithms. Data were collected during the period 2019 to 2023, preprocessed, and analyzed using performance indicators such as the coefficient of determination (R²) and root mean square error (RMSE). The results revealed that integrating ground-based and satellite data, alongside meteorological parameters such as air temperature, relative humidity, evapotranspiration, wet-bulb temperature, cloud cover, and atmospheric pressure at station height, significantly improved the performance of the models. The XGBoost algorithm, with R² of 0.89 and RMSE of 0.57, was identified as the best-performing model. Analyses excluding meteorological parameters showed a substantial decrease in model accuracy, underscoring the importance of these variables. Satellite data demonstrated their potential to play a key role in bridging information gaps caused by the limitations of ground-based stations. Moreover, combining modern technologies with environmental data can contribute to more precise pollutant identification, improve air quality, and serve as a model for other cities in Iran and developing countries.
1- Ahmady-Birgani, H., Ravan, P., Yao, Z., & Afrasinei, G. M. (2022, May). Newly-Born Sand Dunes of Lake Urmia: Assessing Migration Rate and Morphodynamic Changes Using Remote Sensing Techniques and Field Studies. In EGU General Assembly Conference Abstracts (pp. EGU22-12041). https://doi.org/10.5194/egusphere-egu22-12041
2- Aneja, V. P., Agarwal, A., Roelle, P. A., Phillips, S. B., Tong, Q., Watkins, N., & Yablonsky, R. (2001). Measurements and analysis of criteria pollutants in New Delhi, India. Environment International, 27(1), 35-42. https://doi.org/10.1016/S0160-4120(01)00051-4
3- Anggraini, T. S., Irie, H., Sakti, A. D., & Wikantika, K. (2024). Machine learning-based global air quality index development using remote sensing and ground-based stations. Environmental Advances, 15, 100456. https://doi.org/10.1016/j.envadv.2023.100456
4- Blanco, G., Barco, L., Innocenti, L., & Rossi, C. (2024). Urban Air Pollution Forecasting: a Machine Learning Approach leveraging Satellite Observations and Meteorological Forecasts. arXiv preprint arXiv:2405.19901. https://doi.org/10.48550/arXiv.2405.19901
5- Budach, L., Feuerpfeil, M., Ihde, N., Nathansen, A., Noack, N., Patzlaff, H., Harmouch, H., & Naumann, F. (2022). The effects of data quality on machine learning performance. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2207.14529
6- Cofano, A., Cigna, F., Santamaria Amato, L., Siciliani de Cumis, M., & Tapete, D. (2021). Exploiting Sentinel-5P TROPOMI and ground sensor data for the detection of volcanic SO2 plumes and activity in 2018–2021 at Stromboli, Italy. Sensors, 21(21), 6991. https://doi.org/10.3390/s21216991
7- Dastaran M, Jafari Sh, Moslemi H, Attarchi, S, Alavipanah, S. K. 2022. Monitoring Bakhtegan wetland using a time series of satellite data on the Google Earth Engine platform and predicting parameters with Facebook’s Prophet model. Journal of RS and GIS for Natural Resources, 13(4): 1-20. https://doi.org/10.30495/GIRS.2022.685454. (In Persian).
8- Dubovik, O., Schuster, G. L., Xu, F., Hu, Y., Bösch, H., Landgraf, J., & Li, Z. (2021). Grand challenges in satellite remote sensing Frontiers in Remote Sensing, 2, 619818. doi: 10.3389/frsen.2021.619818.
9- Fania, A., Monaco, A., Pantaleo, E., Maggipinto, T., Bellantuono, L., Cilli, R., ... & Bellotti, R. (2024). Estimation of Daily Ground Level Air Pollution in Italian Municipalities with Machine Learning Models Using Sentinel-5P and ERA5 Data. Remote Sensing, 16(7), 1206. https://doi.org/10.3390/rs16071206
10- Ghannadi, M. A., Shahri, M., & Moradi, A. (2022). Air pollution monitoring using Sentinel-5 (Case study: big industrial cities of Iran). Environmental Sciences, 20(2), 81-98. http://dx.doi.org/10.52547/envs.2022.1026. (In Persian).
11- Ghozikali, M. G., Heibati, B., Naddafi, K., Kloog, I., Conti, G. O., Polosa, R., & Ferrante, M. (2016). Evaluation of chronic obstructive pulmonary disease (COPD) attributed to atmospheric O3, NO2, and SO2 using Air Q Model (2011–2012 year). Environmental research, 144, 99-105. https://doi.org/10.1016/j.envres.2015.10.030
12- Halder, B., Ahmadianfar, I., Heddam, S., Mussa, Z. H., Goliatt, L., Tan, M. L., ... & Yaseen, Z. M. (2023). Machine learning-based country-level annual air pollutants exploration using Sentinel-5P and Google Earth Engine. Scientific Reports, 13(1), 7968. https://doi.org/10.1038/s41598-023-34774-9
13- Hassanzadeh, N., Hassanzadeh, R., Hosseinjanizadeh, M., & Honarmand, M. (2023). Evaluation of So2 and No2 concentration in the atmosphere of industrial areas using RS and GIS: Case study of Khatoonabad Copper Smelting Factory, Kerman, Iran. Scientific-Research Quarterly of Geographical Data (SEPEHR), 32(125), 7-27. https://doi.org/10.22131/SEPEHR.2023.559597.2896. (In Persian).
14- Jion, M. M. M. F., Jannat, J. N., Mia, M. Y., Ali, M. A., Islam, M. S., Ibrahim, S. M., ... & Islam, A. R. M. T. (2023). A critical review and prospect of NO2 and SO2 pollution over Asia: Hotspots, trends, and sources. Science of The Total Environment, 876, 162851. https://doi.org/10.1016/j.scitotenv.2023.162851
15- Kamarehie, B., Ghaderpoori, M., Jafari, A., Karami, M., Mohammadi, A., Azarshab, K., ... & Noorizadeh, N. (2017). Quantification of health effects related to SO2 and NO2 pollutants by using air quality model. Journal of Advances in Environmental Health Research, 5(1), 44-50. https://doi.org/10.22102/jaehr.2017.47757
16- Kampa, M., & Castanas, E. (2008). Human health effects of air pollution. Environmental pollution, 151(2), 362-367. doi:10.1016/j.envpol.2007.06.012
17- Kazemi Garajeh, M., Laneve, G., Rezaei, H., Sadeghnejad, M., Mohamadzadeh, N., & Salmani, B. (2023). Monitoring trends of CO, NO2, SO2, and O3 pollutants using time-series sentinel-5 images based on google earth engine. Pollutants, 3(2), 255-279. https://doi.org/10.3390/pollutants3020019
18- Kluyver, T., Ragan-Kelley, B., Pérez, F., Granger, B. E., & Bussonnier, M. (2016) Jupyter Notebooks as a Publishing Format for Reproducible Research. In Proceedings of the 20th International Conference on Electronic Publishing (pp. 87-90). doi:10.3233/978-1-61499-649-1-87
19- Krotkov, N. A., McLinden, C. A., Li, C., Lamsal, L. N., Celarier, E. A., Marchenko, S. V., ... & Streets, D. G. (2016). Aura OMI observations of regional SO 2 and NO 2 pollution changes from 2005 to 2015. Atmospheric Chemistry and Physics, 16(7), 4605-4629. doi:10.5194/acp-16-4605-2016
20- Lelieveld, J., Pozzer, A., Pöschl, U., Fnais, M., Haines, A., & Münzel, T. (2020). Loss of life expectancy from air pollution compared to other risk factors: a worldwide perspective. Cardiovascular research, 116(11), 1910-1917. https://doi.org/10.1093/cvr/cvaa073
21- Li, C., McLinden, C., Fioletov, V., Krotkov, N., Carn, S., Joiner, J., ... & Dickerson, R. R. (2017). India is overtaking China as the world’s largest emitter of anthropogenic sulfur dioxide. Scientific reports, 7(1), 14304. https://doi.org/10.1038/s41598-017-14639-8.
22- Lu, Z., Streets, D. G., De Foy, B., & Krotkov, N. A. (2013). Ozone Monitoring Instrument observations of interannual increases in SO2 emissions from Indian coal-fired power plants during 2005–2012. Environmental science & technology, 47(24), 13993-14000. dx.doi.org/10.1021/es4039648
23- Lu, Z., Streets, D. G., Zhang, Q., Wang, S., Carmichael, G. R., Cheng, Y. F., ... & Tan, Q. (2010). Sulfur dioxide emissions in China and sulfur trends in East Asia since 2000. Atmospheric chemistry and physics, 10(13), 6311-6331. doi:10.5194/acp-10-6311-2010
24- Mohammadian M, Morovati M, Omidipour R. Comparison of the effectiveness of machine learning methods in modeling fire-prone areas (Ilam Province, Darehshahr City). Journal of RS and GIS for Natural Resources, 15(1): 48-73. DOI: 10.30495/girs.2022.697864. (In Persian).
25- Mumtaz, R., Amin, A., Khan, M. A., Asif, M. D. A., Anwar, Z., & Bashir, M. J. (2023). Impact of Green Energy Transportation Systems on Urban Air Quality: A Predictive Analysis Using Spatiotemporal Deep Learning Techniques. Energies, 16(16), 6087. https://doi.org/10.3390/en16166087
26- Nouri, A., Ghanbarzadeh Lak, M., & Valizadeh, M. (2021). Prediction of PM2. 5 concentrations using principal component analysis and artificial neural network techniques: A case study: Urmia, Iran. Environmental Engineering Science, 38(2), 89-98. https://doi.org/10.1089/ees.2020.0089
27- Oğuz, K., & Pekin, M. A. (2024). Prediction of Air Pollution with Machine Learning Algorithms. Turkish Journal of Science and Technology, 19(1), 1-12. https://doi.org/10.55525/tjst.1224661
28- Qu, Y., An, J., He, Y., & Zheng, J. (2016). An overview of emissions of SO2 and NOx and the long-range transport of oxidized sulfur and nitrogen pollutants in East Asia. Journal of Environmental Sciences, 44, 13-25. https://doi.org/10.1016/j.jes.2015.08.028
29- Rahman, M. S., Azad, M. A. K., Hasanuzzaman, M., Salam, R., Islam, A. R. M. T., Rahman, M. M., & Hoque, M. M. M. (2021). How air quality and COVID-19 transmission change under different lockdown scenarios? A case from Dhaka city, Bangladesh. Science of The Total Environment, 762, 143161. https://doi.org/10.1016/j.scitotenv.2020.143161
30- Saieedifar Z, Khosroshahi M, Gohardust A, Ebrahimikhusfi Z, Lotfinasabasl S, Dargahian F. 2020. Investigation of the origin and spatial distribution of high dust concentrations and its synoptical analysis in Gavkhooni basin. Journal of RS and GIS for Natural Resources, 11(4): 47-64. http://dorl.net/dor/20.1001.1.26767082.1399.11.4.3.3. (In Persian).
31- Sameh, S., Zarzoura, F., & El-Mewafi, M. (2024). Spatio-temporal Analysis Mapping of Air Quality Monitoring in Cairo using Sentinel-5 satellite data and Google earth engine. Mansoura Engineering Journal, 49(1), 3. https://doi.org/10.58491/2735-4202.3122
32- Serbula, S. M., Milosavljevic, J. S., Kalinovic, J. V., Kalinovic, T. S., Radojevic, A. A., Trujic, T. L. A., & Tasic, V. M. (2021). Arsenic and SO2 hotspot in South-Eastern Europe: An overview of the air quality after the implementation of the flash smelting technology for copper production. Science of the Total Environment, 777, 14598. https://doi.org/10.1016/j.scitotenv.2021.145981
33- Soleimany, A., Grubliauskas, R., & Šerevičienė, V. (2021). Application of satellite data and GIS services for studying air pollutants in Lithuania (case study: Kaunas city). Air Qual Atmos Health 14: 411–429. https://doi.org/10.1007/s11869-020-00946-z
34- Talebifard, R., Shafiee, A., & Yeganeh, A. (2021). Spatial evaluation of the effect of land use parameters on air quality in urban areas, a case study: Tehran. Journal of Environmental Science Studies, 6(3), 3890-3899. (In Persian).
35- Wieczorek, B. (2023). Air Pollution Patterns Mapping of SO2, NO2, and CO Derived from TROPOMI over Central-East Europe. Remote Sensing, 15(6), 1565. https://doi.org/10.3390/rs15061565
36- Zhao, Y., Wang, S., Duan, L., Lei, Y., Cao, P., & Hao, J. (2008). Primary air pollutant emissions of coal-fired power plants in China: Current status and future prediction. Atmospheric Environment, 42(36), 8442-8452. https://doi.org/10.1016/j.atmosenv.2008.08.021