استفاده از الگوریتم های یادگیری مولد عمیق به منظور تخمین غلظت ذرات معلق در شهر تهران

در دهه‌های اخیر، سطح غلظت ذرات معلق در کلان‌شهر تهران افزایش‌ یافته است که این امر، مخاطرات فراوانی را برای محیط‌زیست و سلامت شهروندان به همراه داشته است. یکی از خطرناک‌ترین نوع آلودگی‌ها، آلودگی ذرات معلق کمتر از 2.5 میکرون (pm2.5) هست که مدل‌سازی، پایش و پیش‌بینی آن‌ را بسیار حیاتی می‌نماید. برآورد غلظت این ذرات در سطح شهر تهران به‌دلیل وجود منابع گوناگون آلودگی و کمبود ایستگاه‌های هواشناسی و عدم توزیع مناسب ا‌یستگاه‌ها موضوعی چالش‌برانگیز است. یکی از منابع جایگزین، استفاده از داده‌های به‌دست‌آمده از طریق تصاویر ماهواره‌ای شامل داده‌های ایروسل با توان تفکیک مکانی بالاست. بااین‌حال تخمین مقادیر آلودگی سطحی از روی داده‌های ایروسل ماهواره‌ای به‌سادگی امکان ‌پذیر نیست و نیازمند توسعه مدل‌های مناسب نظیر مدل‌های داده مبنا و استفاده از تکنیک‌های یادگیری ماشینی می‌باشد. در این راستا هدف این مقاله ایجاد یک مدل به‌منظور تخمین میزان غلظت ذرات معلق در سطح شهر تهران با استفاده از داده‌های حاصل از مدل‌های هواشناسی و داده‌های ایروسل به‌دست‌آمده از تصاویر ماهواره‌ای مودیس به کمک الگوریتم‌های یادگیری عمیق مولد هست. برای این منظور سه نوع شبکه یادگیری عمیق بر مبنای مدل‌های مولد یعنی شبکه خود رمزنگار عمیق، شبکه باور عمیق بولتزمن و شبکه مولد تخاصمی شرطی برای تخمین غلظت pm2.5 با استفاده از داده‌های زمینی و ماهواره‌ای جمع‌آوری‌شده، توسعه داده شد. سپس ارزیابی دقت مدل‌های ایجادشده توسط شبکه‌های مذکور بر روی ‌داده‌های تست انجام شد و عملکرد آن‌ها مورد بررسی و مقایسه قرار گرفت. ارزیابی دقت نشان داد که شبکه‌ خود رمزنگار ترکیب‌شده با مدل‌ بردار پشتیبان مبنا با همبستگی0.69 و دقت (rmse) 10.34 میکروگرم بر مترمکعب بالاترین کارایی را در مقایسه با سایر مدل‌ها به‌دست می‌دهد که می‌تواند به‌منظور مدل‌سازی میزان غلظت ذرات در سطح شهر تهران مورد استفاده قرار گیرد.

Using deep generative models to estimate PM2.5 concentration from satellite AOD data collected from Tehran, Iran

Extended Abstract IntroductionThe concentration of particulate matters has recently increased in the metropolitan area of Tehran resulting in many severe hazards for both the environment and citizens. Particulate matters (PM) with a diameter less than 2.5 microns (PM2.5) are considered to be one of the most dangerous types of pollution. Estimating the concentration of these particles in Tehran is challenging due to the existence of various sources of pollution and the lack of sufficient ground stations. Aerosol optical depth (AOD) data retrieved from satellite imagery can be an alternative. However, AOD are not easily convertible into surface pollution and requires the development of appropriate models such as those based on datadriven approaches and machine learning techniques. Thus, the present study seeks to create a model to estimate the concentration of PM2.5 in Tehran employing deep generative models and insitu measurements, meteorological data, and AOD data extracted from MODIS satellite imagery. Reviewed literature has proved the ability of deep learning techniques to solve regression and classification problems. Deep learning techniques are divided into various categories, one of which is based on the generative models seeking to reconstruct the input features. In this way, highlevel and efficient features can be employed to explore the relationship between PM2.5 and AOD. Thus, the present study has investigated the potential of deep generative models for estimating PM2.5 concentration from high resolution AOD data retrieved from satellite imagery.  Materials and Study AreaAs a metropolitan area suffering from air pollution particularly in winters, the capital city of Iran, Tehran was selected as the study area. PM2.5, the main source of pollution in Tehran, is mainly emitted from vehicles and especially old urban public transport fleet.Aerosol data collected by Aqua and Terra sensors of MODIS and retrieved by Multiangle Implementation of Atmospheric Correction (MAIAC) algorithm were used in the present study. Meteorological data were obtained from the global ECMWF climate model, and the concentration of PM2.5 was measured at air quality monitoring stations. Data were collected for a time interval of January 2013 to January 2020. MethodsThe present study has investigated the potential of deep generative models used to provide an estimate of PM2.5 concentration based on satellite AOD data. To reach such an aim, three types of deep generative neural networks, deep autoencoder (DAE), deep belief network (DBN) and conditional generative adversarial network (CGAN) were developed. Moreover, the performance of deep generative modes was compared with linear regression techniques as typical models used to explore the relation between PM2.5 and AOD data. Finally, the most accurate model for the generation of high resolution (1km) PM2.5 maps from AOD data was selected based on the performance of models. Results and Discussion   The accuracy of each developed model was evaluated using the test data and the obtained results were compared with results obtained from other basic linear regression models. Accuracy evaluation indicated that the developed deep autoencoder (DAE) combined with support vector regression led to the highest correlation (R2 = 0.69) and lowest RMSE (10.34) and MAE (7.95) and thus, can be potentially used for high resolution estimation of PM2.5 concentration. Next was the developed deep belief network which with a performance close to DAE demonstrated its potential capability to estimate PM2.5 concentration from satellite AOD data. The CGAN network acted less accurately in the estimation of PM2.5 concentration as compared to other deep generative models, but outperformed the linear regression algorithms on the test data. To sum up, findings indicated that deep generative models have outperformed classical linear regression techniques used for high resolution estimation of PM2.5 from satellite AOD data. Among the linear methods, the highest accuracy was achieved by the Lasso algorithm with an RSME of 12.14 and MAE of 9.46 on the test data which showed the significance of regularization for the improvement of performance in linear regression algorithms. Nevertheless, the accuracy of linear regression techniques was much lower than deep generative models. ConclusionFinally, DAE was selected as the best model for the estimation of PM2.5 concentration across the study area and high resolution maps of PM2.5 concentration were generated using the developed model. Investigating the daily PM2.5 maps generated for two days with different air quality conditions (clean and polluted) demonstrated the efficiency of the developed DAE for PM2.5 modeling.