هواشناسی کشاورزی

هواشناسی کشاورزی

مدل‌سازی و پیش‌بینی آلودگی گرد و غبار با استفاده از داده‌های ماهواره‌ای و مدل‌های یادگیری ماشین (مطالعه موردی: اهواز)

نوع مقاله : مقاله پژوهشی

نویسندگان
علیرضا یوسفی کبریا 1
مهدی نادی 2
عبادت قنبری پرمهر 3
سان ژونگ چانگ 4
1 دانشجوی دکتری، گروه مهندسی آب، هواشناسی کشاورزی، دانشکده مهندسی زراعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ساری، ایران
2 گروه آبیاری ، دانشکده مهندسی زراعی ، دانشگاه علوم کشاورزی و منابع طبیعی ساری
3 استادیار، گروه سنجش از دور، دانشکده نقشه برداری، دانشگاه صنعتی نوشیروانی بابل، بابل، ایران
4 مرکز تحقیقات بین المللی داده‌های بزرگ برای اهداف توسعه پایدار، آکادمی علوم چین، پکن، چین
10.22125/agmj.2024.478677.1174
چکیده
آلودگی گرد و غبار یکی از چالش‌های زیست‌محیطی در مناطق خشک و نیمه‌خشک است که تأثیرات زیان‌بار آن بر سلامت عمومی، کشاورزی، منابع‌آبی و زیرساخت‌ها حائز اهمیت است. در این پژوهش به منظور پیش‌بینی آلودگی ریزگرد (PM10) شهر اهواز، از شاخص AOD ماهواره مودیس در بازه زمانی ۲۰۱۶ تا ۲۰۲۲ استفاده شد و چهار تکنیک یادگیری ماشین شامل XGBoost، SGB، LSTM و MLP به کار گرفته شد. برای این منظور ابتدا با استفاده از مدل HYSPLIT، مسیرهای ریزگرد ردیابی و فراوانی آن بررسی شد. سپس با استفاده از تصاویر تروکالر ماهواره، ایستگاه‌های مجازی در مسیر حرکت ریزگرد تعیین و از مقادیر AOD این نقاط به عنوان داده‌های ورودی به مدل‌های پیش‌بینی استفاده شد. نتایج نشان داد که همبستگی داده‌های شاخص AOD ماهواره‌ای با داده‌های واقعی PM10 در سال‌های 2021 و 2022 در حد 01/0 معنادار بوده و ضرایب تعیین به ترتیب 89/0 و 85/0 به دست آمد. بررسی نقشه‌های مسیریابی ریزگردها مشخص کرد که گرد و غبار از مبدأ کشور عراق به اهواز منتقل شده است. میانگین داده‌هایAOD از هشت ایستگاه مجازی در یک گام زمانی به عقب برای پیش‌بینی یک هفته ای استفاده شد. نتایج نشان داد که روش XGBoost با میانگین مطلق خطا 08/0 و ضریب تعیین 87/0 عملکرد بهتری نسبت به سایر مدل‌ها داشت. همچنین، مدل‌های SGB و LSTM به ترتیب در رتبه‌های بعدی و MLP کمترین دقت را داشته است. نتایج پیش‌بینی هفت روزه نشان داد که مدل‌های بوستینگ، به‌ویژه XGBoost، توانایی بالایی در درک نوسانات داده‌ها دارد. نتایج این پژوهش نشان می‌دهد که داده‌های ماهواره‌ای AOD و مدل‌های پیشرفته یادگیری ماشین ابزارهای مؤثری برای پیش‌بینی و مدیریت آلودگی گرد و غبار می‌باشد.
کلیدواژه‌ها
شاخص AOD
ردیابی ریزگرد
مدل HYSPLIT
XGBoost
موضوعات

عنوان مقاله English

Modeling and forecasting dust pollution using satellite data and machine learning techniques (A case study of Ahvaz)

نویسندگان English

Alireza Yousefi kebriya 1
mehdi nadi 2
Ebadat Ghanbariparmehr 3
Sun Zhongchang 4
1 1- Ph.D. Candidate, Department of Water Engineering and Agricultural Meteorology, Faculty of Agricultural Engineering, Sari Agricultural Sciences and Natural Resources University, Sari, Iran.
2 Water engineering dept. Faculty of agricultural engineering , Sari agricultural sciences and natural resources university
3 3- Assistant Professor, Department of Remote Sensing, Faculty of Surveying Engineering, Noshirvani Babol University of Technology, Babol, Iran.
4 International Research Center of Big Data for Sustainable Development Goals, 100094, Beijing, China
چکیده English

Dust pollution presents a significant environmental challenge in arid and semi-arid regions, adversely impacting public health, agriculture, water resources, and infrastructure. This study aimed to forecast PM10 dust pollution in Ahvaz by utilizing MODIS satellite AOD data collected from 2016 to 2022, alongside four machine learning techniques: XGBoost, SGB, LSTM, and MLP. Initially, the HYSPLIT model was employed to track dust paths and analyze their frequency. Subsequently, true color satellite images were used to identify virtual stations along these dust paths, and the AOD values at these locations served as input data for the forecasting models. The results indicated a significant correlation between the satellite AOD data and actual PM10 data for 2021 and 2022, at significance level of 0.01 and determination coefficients of 0.89 and 0.85, respectively. Dust tracking maps demonstrated that dust was being transported from Iraq to Ahvaz. Average AOD data from eight virtual stations, with a one-day lag, was used for weekly dust prediction. Model evaluation results revealed that XGBoost outperformed the other models, achieving a mean absolute error of 0.08 and a coefficient of determination of 0.87, followed by the SGB and LSTM models with almost same performance, while the MLP model showed the lowest accuracy. Predictions for the following seven days indicated that boosting models, particularly XGBoost, effectively captured data fluctuations. This research demonstrates that AOD satellite data, combined with advanced machine learning techniques, are valuable tools for forecasting and managing dust pollution.

کلیدواژه‌ها English

AOD index
Dust tracking
HYSPLIT model
XGBoost
Show Human Fingerprint on Global Air Quality – Release Materials. Retrieved from https://svs.gsfc.nasa.gov, accessed in 2015.##Ahmadnejad, S., Nadi, M.  Aghelpour, P. 2024. Numerical Estimation of Surface Soil Moisture by Machine Learning Algorithms in Different Climatic Types. Pure Appl. Geophysics. 181, 2149–2175. ##Alimahmoodi Sarab, S., Shataee Jouybari, S., Rashki, A. 2018. The estimate of dust concentration using weather variables: A case study of Ahvaz City. Journal of Natural Environment, 71(3), 385-397. ##Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., Muneer, A., Sumiea, E. H., Alqushaibi, A.,  Ragab, M. G. 2024. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University-Computer and Information Sciences, 36(5), 102068. ##Ansari Ghojghar, M., Araghinejad, Sh., Bazrafshan, J., Zahraie, B., Parsi, E. 2021. Evaluating the performance of GRU-LSTM hybrid model in predicting the dust storms events (Case study: Khuzestan Province in southwest of Iran). Iran-Water Resources Research, 17(1), 11-09. ##Arias-Pérez, R. D., Taborda, N. A., Gómez, D. M., Narvaez, J. F., Porras, J., Hernandez, J. C. 2020. Inflammatory effects of particulate matter air pollution. Environmental Science and Pollution Research, 27(34), 42390-42404. ##Asadifard, E., Masoudi, M. 2018. Status and prediction of carbon monoxide as an air pollutant in Ahvaz City, Iran. Caspian Journal of Environmental Sciences, 16(3), 203-213.##Benti, N. E., Chaka, M. D., Semie, A. G. 2023. Forecasting renewable energy generation with machine learning and deep learning: Current advances and future prospects. Sustainability, 15(9), 7087. ##Bolan, S., Padhye, L. P., Jasemizad, T., Govarthanan, M., Karmegam, N., Wijesekara, H., Amarasiri, D., Hou, D., Zhou, P., Biswal, B. K., Balasubramanian, R., Wang, H., Siddique, K. H. M., Rinklebe, J., Kirkham, M. B.,  Bolan, N. 2024. Impacts of climate change on the fate of contaminants through extreme weather events. Science of the Total Environment, 909, 168388. ##Faraji M, Nadi S, Shojaei D. Spatial-Temporal Prediction of PM2.5 Pollutants Using Deep Recurrent Networks: A Case Study of Tehran. JGST 2021; 10 (3), 13-26. ##Ganaie, M. A., Hu, M., Malik, A. K., Tanveer, M., Suganthan, P. N. 2022. Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115, 105151. ##Goudarzi, G., Hopke, P. K., Yazdani, M. 2021. Forecasting PM2.5 concentration using artificial neural network and its health effects in Ahvaz, Iran. Chemosphere, 283, 131285. ##Handschuh, J., Erbertseder, T., Baier, F. 2023. Systematic evaluation of four satellite AOD datasets for estimating PM2.5 using a random forest approach. Remote Sensing, 15(8), 2064. ##He, L., Wang, S., Liu, M., Chen, Z., Xu, J., Dong, Y. 2023. Transport and transformation of atmospheric metals in ecosystems: A review. Journal of Hazardous Materials Advances, 9, 100218. ##Isik, H., Akkan, T. 2024. Water quality assessment with artificial neural network models: Performance comparison between SMN, MLP and PS-ANN methodologies. Arabian Journal for Science and Engineering, 1-19. ##Karami, P., Eslaminezhad, S. A., Eftekhari, M., Boroumand, F., Akbari, M. 2023. Development of machine learning algorithms to predict urban air quality index (Study area: Tehran city). Journal of Geography and Environmental Hazards, 12(2), 165-186. ##Kaviani Rad, A., Shamshiri, R. R., Naghipour, A., Razmi, S.-O., Shariati, M., Golkar, F., Balasundram, S. K. 2022. Machine Learning for Determining Interactions between Air Pollutants and Environmental Parameters in Three Cities of Iran. Sustainability, 14(13), 8027. ##Khalili. A., Bazrafshan, J., Cheraghalizadeh, M. 2022. A Comparative study on climate maps of Iran in extended de Martonne classification and application of the method for world climate zoning. Journal of Agricultural Meteorology, 10(1), 3-16. ##Kujawska, J., Kulisz, M., Oleszczuk, P., Cel, W. 2022). Machine Learning Methods to Forecast the Concentration of PM10 in Lublin, Poland. Energies, 15(17), 6428. ##Kurnaz, G., Demir, A. S. 2022. Prediction of SO2 and PM10 air pollutants using a deep learning-based recurrent neural network: Case of industrial city Sakarya. Urban Climate, 41, 101051. ##Li, L., Herrera, M., Mukherjee, A., Zheng, G., Chen, C., Dhada, M., Brice, H., Parekh, A., Parlikad, A. K. 2025. Predictive alarm models for improving radio access network robustness. Expert Systems with Applications, 259, 125312. ##Mansouri Moghadam, S., Payandeh, K., Koushafar, A., Goosheh, M., Mohammadi Rouzbahani, M. 2024. Level of heavy metals and environmental pollution index in Ahvaz, Southwest Iran. Scientific Reports, 14(1), 14754. ##Nadi, M., Yousefi Kebriya, A. 2024. A Method for Correction of Tropical Rainfall Measuring Mission Satellite Temperature Network in Mazandaran Province. Iranica Journal of Energy and Environment (IJEE), 15(1), 100-110. ##Nadi, M., Jamei, M., Bazrafshan, J., Janatrostami, S. 2012. Evaluation of Different Methods for Interpolation of Mean Monthly and Annual Precipitation Data (Case Study: Khuzestan Province), Physical Geography Research, 44(4), 117-130. ##NASA (National Aeronautics and Space Administration), 2015. GMS: NASA Images ##NOAA Research. (2020). NOAA ESRL global monitoring laboratory: SURFRAD aerosol optical depth. ##Pourgholam-Amiji, M., Ansari Ghojghar, M., Ahmadaali, K. 2021. Prediction of Dust Storms in Khuzestan Province Using Artificial Neural Networks. Nivar, 45(114-115), 56-75. ##Pourgholam-Amiji, M., Ansari Ghojghar, M., Ahmadaali, K. 2021. Prediction of Dust Storms in Khuzestan Province Using Artificial Neural Networks. Nivar, 45(114-115), 56-75. ##Rolph, G., Stein, A., Stunder, B. 2017. Real-time environmental applications and display system: READY. Environmental Modelling Software, 95, 210–228. ##Rolph, G., Stein, A., Stunder, B. 2017. Real-time environmental applications and display system: READY. Environmental Modelling Software, 95, 210–228. ##Sadeghi Moghaddam, A., Khanke, H., Norozi, M., Fateh, S., Farrokhi, M. 2022. A critique of studies on the combined effect of dust storms and meteorological elements on cardiovascular, cerebrovascular, and respiratory diseases. Health in Emergencies and Disasters Quarterly, 8(1), 1–6. ##Sadeghi Moghaddam, A., Khanke, H., Norozi, M., Fateh, S., Farrokhi, M. 2022. A critique of studies on the combined effect of dust storms and meteorological elements on cardiovascular, cerebrovascular, and respiratory diseases. Health in Emergencies and Disasters Quarterly, 8(1), 1–6. ##safarian zengir V, zenali B, Jafari hasi Kennedy Y, jafarzadeh L. Investigation of dust and evaluation of its prediction in Ardebil province using ANFIS model. Journal of Spatial Analysis Environmental Hazards 2018; 5(2), 107-124. ##Safarian Zengir, V., Zenali, B., Jafari Hasi Kennedy, Y., Jafarzadeh, L. 2018. Investigation of dust and evaluation of its prediction in Ardebil province using ANFIS model. Journal of Spatial Analysis Environmental Hazards, 5(2), 107-124. ##Shaziayani, W. N., Ul-Saufie, A. Z., Mutalib, S., Mohamad Noor, N., Zainordin, N. S. 2022. Classification Prediction of PM10 Concentration Using a Tree-Based Machine Learning Approach. Atmosphere, 13(4), 538. ##Shaziayani, W. N., Ul-Saufie, A. Z., Mutalib, S., Mohamad Noor, N., Zainordin, N. S. 2022. Classification Prediction of PM10 Concentration Using a Tree-Based Machine Learning Approach. Atmosphere, 13(4), 538. ##Thangavel, P., Park, D., Lee, Y.-C. 2022. Recent insights into particulate matter (PM2.5)-mediated toxicity in humans: An overview. International Journal of Environmental Research and Public Health, 19(12), 7511. ##Thangavel, P., Park, D., Lee, Y.-C. 2022. Recent insights into particulate matter (PM2.5)-mediated toxicity in humans: An overview. International Journal of Environmental Research and Public Health, 19(12), 7511. ##Yadav, V., Yadav, A. K., Singh, V., Singh, T. 2024. Artificial neural network: An innovative approach in air pollutant prediction for environmental applications: A review. Results in Engineering, 22, 102305. ##Yadav, V., Yadav, A. K., Singh, V., Singh, T. 2024. Artificial neural network: An innovative approach in air pollutant prediction for environmental applications: A review. Results in Engineering, 22, 102305. ##Yousefi kebria, A., Nadi, M., Jamei, M. 2022. Investigation of Statistical and Geostatistical Methods in Preparing the Rainfall Map of Mazandaran Province. Journal of Watershed Management Research. 12(23), 212-223. ##Yousefi Kebria, A., Nadi, M., Jamei, M. 2021. Investigation of Statistical and Geostatistical Methods in Preparing the Rainfall Map of Mazandaran Province. Journal of Watershed Management Research, 12(23), 212-223. ##Yousefi Kebria, A., Nadi, M., Ghanbari Parmehr, E., Sun, Z. 2024. Correlation between the changing Shadegan wetland extent and dust emission using remote sensing techniques. Journal of Watershed Management Research, 15(1), 1-15.##Yousefi Kebria, A., Nadi, M., Ghanbari Parmehr, E., Sun, Z. 2024. Correlation between the changing Shadegan wetland extent and dust emission using remote sensing techniques. Journal of Watershed Management Research, 15(1), 1-15.##Yousefi Kebriya, A., Nadi, M. (2024). Examining Air Pollution Continuity in Tehran Province using Markov Chain Model. Iranica Journal of Energy and Environment, 15(2), 201-210. ##Yousefi Kebriya, A., Nadi, M. 2024. Examining Air Pollution Continuity in Tehran Province using Markov Chain Model. Iranica Journal of Energy and Environment, 15(2), 201-210. ##Yousefi Kebriya, A., Nadi, M., Ghanbari Parmehr, E. 2023. Estimation of ozone and nitrogen dioxide pollutants in Mazandaran Province using sentinel 5 satellite images. Iranica Journal of Energy and Environment, 16(1). ##Yousefi Kebriya, A., Nadi, M., Ghanbari Parmehr, E. 2023. Estimation of ozone and nitrogen dioxide pollutants in Mazandaran Province using Sentinel 5 satellite images. Iranica Journal of Energy and Environment, 16(1).##Yousefi Kebriya, A., Nadi, M., Jamei, M. 2022. Combining interpolation methods and precipitation products of TRMM satellite to increase the accuracy of rainfall maps in Mazandaran province. Water and Soil Conservation, 28(3), 49-70. ##Yousefi Kebriya, A., Nadi, M., Ghanbari Parmehr, E., Sun, Z. 2024. Assessment of some environmental stresses in the Shadegan Wetland: Analysis of satellite data, water quality indicators, and dust storm pathways. Iranica Journal of Energy and Environment, 16(2), 1-13. ##Yousefi Kebriya, A., Nadi, M., Ghanbari Parmehr, E., Sun, Z. 2024. Assessment of some environmental stresses in the Shadegan Wetland: Analysis of satellite data, water quality indicators, and dust storm pathways. Iranica Journal of Energy and Environment, 16(2), 1-13. ##Yousefi Kebriya, A., Nadi, M., Jamei, M. 2022. Combining interpolation methods and precipitation products of TRMM satellite to increase the accuracy of rainfall maps in Mazandaran province. Water and Soil Conservation, 28(3), 49-70. ##Zhao, B., Cao, X. 2025. CompNET: Boosting image recognition and writer identification via complementary neural network post-processing. Pattern Recognition, 157, 110880. ##Zhao, B., Cao, X. 2025. CompNET: Boosting image recognition and writer identification via complementary neural network post-processing. Pattern Recognition, 157, 110880.##