دانشگاه علوم کشاورزی و منابع طبیعی گرگان

 آمار

تعداد نشریات14
تعداد شماره‌ها689
تعداد مقالات7,127
تعداد مشاهده مقاله11,356,882
تعداد دریافت فایل اصل مقاله10,289,952
Zoqi, Mohamad javad, Dehqanpour Aliaqa, Aliasghar, Rasouli, Seyed Javad, Mansouri Daneshvar, Mohammad Reza. (1404). Daily PM2.5 prediction and pollution episode detection using MLP neural networks across urban monitoring sites with varied land uses. , 14(1), 109-127. doi: 10.22069/ijerr.2026.23813.1528
Mohamad javad Zoqi; Aliasghar Dehqanpour Aliaqa; Seyed Javad Rasouli; Mohammad Reza Mansouri Daneshvar. "Daily PM2.5 prediction and pollution episode detection using MLP neural networks across urban monitoring sites with varied land uses". , 14, 1, 1404, 109-127. doi: 10.22069/ijerr.2026.23813.1528
Zoqi, Mohamad javad, Dehqanpour Aliaqa, Aliasghar, Rasouli, Seyed Javad, Mansouri Daneshvar, Mohammad Reza. (1404). 'Daily PM2.5 prediction and pollution episode detection using MLP neural networks across urban monitoring sites with varied land uses', , 14(1), pp. 109-127. doi: 10.22069/ijerr.2026.23813.1528
Zoqi, Mohamad javad, Dehqanpour Aliaqa, Aliasghar, Rasouli, Seyed Javad, Mansouri Daneshvar, Mohammad Reza. Daily PM2.5 prediction and pollution episode detection using MLP neural networks across urban monitoring sites with varied land uses. , 1404; 14(1): 109-127. doi: 10.22069/ijerr.2026.23813.1528

Daily PM2.5 prediction and pollution episode detection using MLP neural networks across urban monitoring sites with varied land uses

Environmental Resources Research
دوره 14، شماره 1، فروردین 2026، صفحه 109-127    اصل مقاله (1.08 M)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22069/ijerr.2026.23813.1528
نویسندگان
Mohamad javad Zoqi* 1؛ Aliasghar Dehqanpour Aliaqa2؛ Seyed Javad Rasouli2؛ Mohammad Reza Mansouri Daneshvar2
1Department of Civil Engineering, University of Birjand, Birjand, Iran
2Applied Climate and Weather Forecast Office, Iran Meteorological Organization, Atmospheric Science and Meteorological Research Center (ASMERC), Mashhad, Iran
چکیده
This research presents a data-driven approach for forecasting daily PM2.5 concentrations using a multilayer perceptron (MLP) neural network across three urban monitoring sites in Mashhad, Iran—Sajjad, Torogh, and Vila—each reflecting a unique land-use profile. The study utilized daily datasets collected from 2018 to 2023, and a dedicated MLP model was trained for each station. Various training algorithms were assessed to identify the most suitable configuration, with model complexity fine-tuned by adjusting the number of neurons in the hidden layer. Key input features included meteorological variables from the preceding day (such as wind speed, ambient temperature, precipitation, solar radiation, and relative humidity), the previous day's PM2.5 concentration, and calendar-based temporal factors. To improve the network’s predictive capability and prevent overfitting, data normalization and early stopping strategies were applied. The best predictive performance was recorded at the Sajjad station, where the model achieved an R2 value of 0.79 and an MAE of 6.77 µg/m3. While the Torogh station yielded moderate predictive accuracy, the Vila station exhibited weaker performance. The models demonstrated strong capability in identifying pollution episodes, with true positive rates between 66% and 74%, and a minimum false alarm rate of 0.18 at the Sajjad station. Spatial disparities in model performance were attributed to localized environmental and climatic factors, including terrain variation and emission source intensity. Overall, the findings confirm the potential of MLP-based models as practical tools for daily air quality prediction and support their integration into urban pollution alert systems. .
کلیدواژه‌ها
PM2.5 concentration forecasting؛ artificial neural networks؛ air pollution؛ urban monitoring station؛ meteorological data
آمار
تعداد مشاهده مقاله: 193
تعداد دریافت فایل اصل مقاله: 143


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب