KaydedilenlerDerginizi ekleyin

Dergiler / Atmospheric Pollution Research / 2019 / Cilt: 10 - Sayı: 3

Assessing PM2.5 concentrations in Tehran, Iran, from space using MAIAC, deep blue, and dark target AOD and machine learning algorithms

Seyed Omid NABAVI
Leopold HAIMBERGER
Esmail ABBASI
Sayfa
889–903
DOI
—
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

The inferior accuracy of estimation in the north and east of Tehran is also linked to lackingfeatures which could feed the transportation of PM2.5 from west to the east of the study area into MLAs.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:This study aims to explore the spatial estimation of fine particulate matter (PM2.5) using 10-km merged darktarget and deep blue (DB_DT) Aerosol Optical Depth (AOD) and 1-km Multi-Angle Implementation ofAtmospheric Correction (MAIAC) AOD over Tehran.
📊
Temel Bulgular & Veri:The ability of four Machine Learning Algorithms (MLAs) topredict PM2.5 concentrations is also investigated.
💡
Sonuç & Katkı:The inferior accuracy of estimation in the north and east of Tehran is also linked to lackingfeatures which could feed the transportation of PM2.5 from west to the east of the study area into MLAs.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Alan Parametreleri

Özet

This study aims to explore the spatial estimation of fine particulate matter (PM2.5) using 10-km merged darktarget and deep blue (DB_DT) Aerosol Optical Depth (AOD) and 1-km Multi-Angle Implementation ofAtmospheric Correction (MAIAC) AOD over Tehran. The ability of four Machine Learning Algorithms (MLAs) topredict PM2.5 concentrations is also investigated. Results show that the association of satellite AOD with surfacePM significantly increases after considering the contribution of relative humidity in PM mass concentration andnormalization of AOD to Planetary boundary layer height (PBLH). The examination of derived aerosol layerheight (ALH) from 159 Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) profilesshows that PBLH could successfully represent the top of aerosol-laden layers. Surprisingly, the highest correlationwas found between normalized 10-km DB_DT AOD and corrected PM2.5 measurements. Consequently,random forest (RF) fed by this AOD product has yielded the best performance (R2=0.68, RMSE=17.52 andMRE=27.46%). Importance analysis of variables reveals that DB_DT and meteorological fields are of highestand least importance among selected variables, respectively. The RF performance is less satisfactory duringsummer which is assumed to be caused by the omission of unknown features representing the formation ofsecondary aerosols. The inferior accuracy of estimation in the north and east of Tehran is also linked to lackingfeatures which could feed the transportation of PM2.5 from west to the east of the study area into MLAs.

🔖

Bu Makaleye Atıf Yap

NABAVI, S. O., HAIMBERGER, L., ABBASI, E. (2019). Assessing PM2.5 concentrations in Tehran, Iran, from space using MAIAC, deep blue, and dark target AOD and machine learning algorithms. Atmospheric Pollution Research, Cilt: 10 - Sayı: 3, 889–903. https://ajindex.com/articles/351363

Kaynakça (10)

  1. Adams, A.M., Prospero, J.M., Zhang, C., 2012. CALIPSO-derived three-dimensional structure of aerosol over the Atlantic Basin and adjacent continents. J. Clim. 25, 6862–6879.
  2. Amini, H., Taghavi-Shahri, S.M., Henderson, S.B., Naddafi, K., Nabizadeh, R., Yunesian, M., 2014. Land use regression models to estimate the annual and seasonal spatial variability of sulfur dioxide and particulate matter in Tehran, Iran. Sci. Total Environ. 488, 343–353.
  3. Arhami, M., Hosseini, V., Shahne, M.Z., Bigdeli, M., Lai, A., Schauer, J.J., 2017. Seasonal trends, chemical speciation and source apportionment of fine PM in Tehran. Atmos. Environ. 153, 70–82.
  4. Asgharpour, S., Zanjani, H., Taleghani, G., 2013. Impact of urbanization on population changes in metropolitan area of Tehran, Iran. In: Proceedings of the 3rd International Geography Symposium-GEOMED Symposium Proceedings. Atash, F., 2007. The deterioration of urban environments in developing countries: mitigating the air pollution crisis in Tehran, Iran. Cities 24, 399–409.
  5. Bayat, R., Torkian, A., Najafi, M., Askariyeh, M.H., Arhami, M., 2012. Source apportionment of Tehran's air pollution by emissions inventory. In: International Emission Inventory Conference of EPA. EPA Tampa, FL, USA, pp. 13–16.
  6. Bilal, M., Nazeer, M., Qiu, Z., Ding, X., Wei, J., 2018. Global validation of MODIS C6 and C6. 1 merged aerosol products over diverse vegetated surfaces. Remote Sens. 10, 475. Breiman, L., 2001. Random forests. Mach. Learn. 45, 5–32.
  7. Bruns, E.A., El Haddad, I., Slowik, J.G., Kilic, D., Klein, F., Baltensperger, U., Prévôt, A.S., 2016. Identification of significant precursor gases of secondary organic aerosols from residential wood combustion. Sci. Rep. 6, 27881. Chan, K.M., Wood, R., 2013. The seasonal cycle of planetary boundary layer depth determined using COSMIC radio occultation data. J. Geophys. Res.: Atmos. 118 (12) 422-12,434. Chandrashekar, G., Sahin, F., 2014. A survey on feature selection methods. Comput. Electr. Eng. 40, 16–28.
  8. Chen, G., Li, S., Knibbs, L.D., Hamm, N., Cao, W., LI, T., Guo, J., Ren, H., Abramson, M.J., Guo, Y., 2018. A machine learning method to estimate PM 2.5 concentrations across China with remote sensing, meteorological and land use information. Sci. Total Environ. 636, 52–60.
  9. Chimot, J., Veefkind, J.P., Vlemmix, T., Levelt, P.F., 2018. Spatial distribution analysis of the OMI aerosol layer height: a pixel-by-pixel comparison to CALIOP observations. Atmos. Meas. Tech. 11, 2257–2277.
  10. Choi, Y., Ghim,