Satellite-based prediction of surface dust mass concentration in southeastern Iran using an intelligent approach

Springer Science and Business Media LLC - 2023
Seyed Babak Haji Seyed Asadollah1,2, Ahmad Sharafati3,4, Davide Motta5, Antonio Jodar-Abellan6,2,7, Miguel Ángel Pardo2
1Department of Environmental Resources Engineering, State University of New York College of Environmental Science and Forestry, Syracuse, USA
2Department of Civil Engineering, University of Alicante, Alicante, Spain
3New Era and Development in Civil Engineering Research Group, Scientific Research Center, Al-Ayen University, Thi-Qar, Nasiriyah, 64001, Iraq
4Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
5Department of Mechanical and Construction Engineering, Northumbria University, Newcastle upon Tyne, UK
6Spanish Research Council, Centro de Edafología y Biología Aplicada del Segura (CEBAS-CSIC), Soil and Water Conservation Group, Murcia, Spain
7Centro de Investigación e Innovacion Agroalimentaria y Agroambiental (CIAGRO-UMH), Miguel Hernandez University, Orihuela, Spain

Tóm tắt

The southeastern section of Iran, especially the province of Khuzestan, experience severe air pollution levels, such as high values of surface dust mass concentration (SDMC). The province lacks accurate and well-placed ground observational stations, therefore the only viable approach for evaluating SDMC is via remote sensing. In this study, meteorological, hydrological and geological data on 11 input variables from Modern-Era Retrospective analysis for Research and Applications Version 2 (MERRA-2), global precipitation measurement (GPM) and Global Land Data Assimilation System (GLDAS) for the year 2018 are used for prediction of the SDMC values, also obtained from another MERRA-2 mission. For real-time prediction, Pearson’s correlation coefficient (PCC) analysis shows that wind-related variables—surface wind speed, surface aerodynamic conductance and surface pressure—are those with the highest correlation with SDMC. Using the gradient boosting regression (GBR) algorithm, these three variables can simulate SDMC with good accuracy $$(R^{2} = 0.76,\;NSE = 0.76, \;N{\text{-}}RMSE = 0.48 \;and\;N{\text{-}}MAE = 0.34)$$ . Furthermore, near-future SDMC forecasting down to 8 days prior of SMDC occurrence is also carried out. A sequential forward feature selection of the input variables, based on PCC, is used for four lead times and results show that surface pressure and heat flux govern near-future predictions. With $$R^{2} = 0.46$$ and $$N{\text{-}}RMSE = 0.74$$ , GBR shows good potential for forecasting SDMC 8 days in advance. Real-time and near-future simulation results generally show that robust SDMC prediction can be obtained using exclusively remote sensing data, without ground-based observations.

Từ khóa


Tài liệu tham khảo

Al-Othman A, Tawalbeh M, Martis R, Dhou S, Orhan M, Qasim M, Olabi AG (2022) Artificial intelligence and numerical models in hybrid renewable energy systems with fuel cells: advances and prospects. Energy Convers Manag 253:115154

Allison P (2013) What’s the best R-squared for logistic regression. Stat Horiz 13

Amaral SS, De Carvalho JA, Costa MAM, Pinheiro C (2015) An overview of particulate matter measurement instruments. Atmosphere 6(9):1327–1345

Anderson JO, Thundiyil JG, Stolbach A (2012) Clearing the air: a review of the effects of particulate matter air pollution on human health. J Med Toxicol 8(2):166–175

Arkian F, Nicholson SE (2018) Long-term variations of aerosol optical depth and aerosol radiative forcing over Iran based on satellite and AERONET data. Environ Monit Assess 190(1):1–15

Asadollah SBHS, Khan N, Sharafati A, Shahid S, Chung E-S, Wang X-J (2021a) Prediction of heat waves using meteorological variables in diverse regions of Iran with advanced machine learning models. Stoch Environ Res Risk Assess 36:1959–1974

Asadollah SBHS, Sharafati A, Motta D, Yaseen ZM (2021b) River water quality index prediction and uncertainty analysis: a comparative study of machine learning models. J Environ Chem Eng 9(1):104599

Asadollah SBHS, Sharafati A, Shahid S (2022) Application of ensemble machine learning model in downscaling and projecting climate variables over different climate regions in Iran. Environ Sci Pollut Res 29(12):17260–17279

Bahad P, Saxena P (2020) Study of adaboost and gradient boosting algorithms for predictive analytics. In: International conference on intelligent computing and smart communication 2019. Springer, pp 235–244

Brook RD, Rajagopalan S (2009) Particulate matter, air pollution, and blood pressure. J Am Soc Hypertens 3(5):332–350

Campbell JB, Wynne RH (2011) Introduction to remote sensing. Guilford Press

Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci 7:e623

Chok NS (2010) Pearson’s versus Spearman’s and Kendall’s correlation coefficients for continuous data. University of Pittsburgh

Chu Y, Liu Y, Li X, Liu Z, Lu H, Lu Y, Mao Z et al (2016) A review on predicting ground PM2.5 concentration using satellite aerosol optical depth. Atmosphere 7(10):129

Chudnovsky AA, Koutrakis P, Kloog I, Melly S, Nordio F, Lyapustin A, Wang Y et al (2014) Fine particulate matter predictions using high resolution Aerosol Optical Depth (AOD) retrievals. Atmos Environ 89:189–198

Dadashi-Roudbari A, Ahmadi M (2020) Evaluating temporal and spatial variability and trend of aerosol optical depth (550 nm) over Iran using data from MODIS on board the Terra and Aqua satellites. Arab J Geosci 13(6):1–23

Daniali M, Karimi N (2019) Spatiotemporal analysis of dust patterns over Mesopotamia and their impact on Khuzestan province, Iran. Nat Hazards 97(1):259–281

Davis SM, Swain PH (1978) Remote sensing: the quantitative approach. McGraw-Hill International Book Company, New York

Di Q, Kloog I, Koutrakis P, Lyapustin A, Wang Y, Schwartz J (2016) Assessing PM2.5 exposures with high spatiotemporal resolution across the continental United States. Environ Sci Technol 50(9):4712–4721

Diao M, Holloway T, Choi S, O’Neill SM, Al-Hamdan MZ, Donkelaar AV, Martin RV et al (2019) Methods, availability, and applications of PM2.5 exposure estimates derived from ground measurements, satellite, and atmospheric models. J Air Waste Manag Assoc 69(12):1391–1414

Donkelaar AV, Martin RV, Brauer M, Kahn R, Levy R, Verduzco C, Villeneuve PJ (2010) Global estimates of ambient fine particulate matter concentrations from satellite-based aerosol optical depth: development and application. Environ Health Perspect 118(6):847–855

Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232

Gelaro R, McCarty W, Suárez MJ, Todling R, Molod A, Takacs L, Randles CA et al (2017) The modern-era retrospective analysis for research and applications, version 2 (MERRA-2). J Clim 30(14):5419–5454

Ghozat A, Sharafati A, Hosseini SA (2022) Satellite-based monitoring of meteorological drought over different regions of Iran: application of the CHIRPS precipitation product. Environ Sci Pollut Res 29:1–18

Gomis D, Ruiz S, Sotillo MG, Álvarez-Fanjul E, Terradas J (2008) Low frequency Mediterranean sea level variability: the contribution of atmospheric pressure and wind. Glob Planet Change 63(2–3):215–229

Gueymard CA, Yang D (2020) Worldwide validation of CAMS and MERRA-2 reanalysis aerosol optical depth products using 15 years of AERONET observations. Atmos Environ 225:117216

Guo H, Xu M, Hu Q (2011) Changes in near-surface wind speed in China: 1969–2005. Int J Climatol 31(3):349–358

Hamanaka RB, Mutlu GM (2018) Particulate matter air pollution: effects on the cardiovascular system. Front Endocrinol 9:680

Hauke J, Kossowski T (2011) Comparison of values of Pearson’s and Spearman’s correlation coefficient on the same sets of data. Wydział Nauk Geograficznych i Geologicznych Uniwersytetu im. Adama Mickiewicza

Johnson NE, Bonczak B, Kontokosta CE (2018) Using a gradient boosting model to improve the performance of low-cost aerosol monitors in a dense, heterogeneous urban environment. Atmos Environ 184:9–16

Just AC, Wright RO, Schwartz J, Coull BA, Baccarelli AA, Tellez-Rojo MM, Moody E et al (2015) Using high-resolution satellite aerosol optical depth to estimate daily PM2.5 geographical distribution in Mexico City. Environ Sci Technol 49(14):8576–8584

Karandish F, Šimůnek J (2016) A comparison of numerical and machine-learning modeling of soil water content with limited input data. J Hydrol 543:892–909

Kianian B, Liu Y, Chang HH (2021) Imputing satellite-derived aerosol optical depth using a multi-resolution spatial model and random forest for PM2.5 prediction. Remote Sens 13(1):126

Kwasny F, Madl P, Hofmann W (2010) Correlation of air quality data to ultrafine particles (UFP) concentration and size distribution in ambient air. Atmosphere 1(1):3–14

Lee HJ, Coull BA, Bell ML, Koutrakis P (2012) Use of satellite-based aerosol optical depth and spatial clustering to predict ambient PM2.5 concentrations. Environ Res 118:8–15

Lee M, Kloog I, Chudnovsky A, Lyapustin A, Wang Y, Melly S, Coull B et al (2016) Spatiotemporal prediction of fine particulate matter using high-resolution satellite images in the Southeastern US 2003–2011. J Eposure Sci Environ Epidemiol 26(4):377–384

Liu D, Li L (2015) Application study of comprehensive forecasting model based on entropy weighting method on trend of PM25 concentration in Guangzhou, China. Int J Environ Res Public Health 12(6):7085–7099

Liu S, Lu L, Mao D, Jia L (2007) Evaluating parameterizations of aerodynamic resistance to heat transfer using field measurements. Hydrol Earth Syst Sci 11(2):769–783

Mallick K, Wandera L, Bhattarai N, Hostache R, Kleniewska M, Chormanski J (2018) A critical evaluation on the role of aerodynamic and canopy–surface conductance parameterization in SEB and SVAT models for simulating evapotranspiration: a case study in the upper biebrza national park wetland in poland. Water 10(12):1753

Mehdizadeh S, Behmanesh J, Khalili K (2017) Evaluating the performance of artificial intelligence methods for estimation of monthly mean soil temperature without using meteorological data. Environ Earth Sci 76(8):1–16

MERRA, G. (2AD) tavgU_2d_lnd_Nx: 2d, diurnal, time-averaged, single-level, assimilation, land surface diagnostics V5. 12.4. EarthData GES DISC NASA

Mirakbari M, Ebrahimi Khusfi Z (2020) Investigation of spatial and temporal changes in atmospheric aerosol using aerosol optical depth in Southeastern Iran. J RS GIS Nat Resour 11(3):87–105

Mirzaei M, Amanollahi J, Tzanis CG (2019) Evaluation of linear, nonlinear, and hybrid models for predicting PM 2.5 based on a GTWR model and MODIS AOD data. Air Qual Atmos Health 12(10):1215–1224

Nabavi SO, Haimberger L, Abbasi R, Samimi C (2018) Prediction of aerosol optical depth in West Asia using deterministic models and machine learning algorithms. Aeol Res 35:69–84

Nakata M, Sano I, Mukai S, Holben BN (2013) Spatial and temporal variations of atmospheric aerosol in Osaka. Atmosphere 4(2):157–168

Nguyen DL, Kim JY, Ghim YS, Shim S-G (2015) Influence of regional biomass burning on the highly elevated organic carbon concentrations observed at Gosan, South Korea during a strong Asian dust period. Environ Sci Pollut Res 22(5):3594–3605

Nie P, Roccotelli M, Fanti MP, Ming Z, Li Z (2021) Prediction of home energy consumption based on gradient boosting regression tree. Energy Rep 7:1246–1255

Nourani V, Baghanam AH, Adamowski J, Kisi O (2014) Applications of hybrid wavelet–artificial intelligence models in hydrology: a review. J Hydrol 514:358–377

Raaschou-Nielsen O, Beelen R, Wang M, Hoek G, Andersen ZJ, Hoffmann B, Stafoggia M et al (2016) Particulate matter air pollution components and risk for lung cancer. Environ Int 87:66–73

Randles CA, Da Silva AM, Buchard V, Colarco PR, Darmenov A, Govindaraju R, Smirnov A et al (2017) The MERRA-2 aerosol reanalysis, 1980 onward. Part I: system description and data assimilation evaluation. J Clim 30(17):6823–6850

Ratner B (2009) The correlation coefficient: its values range between+ 1/− 1, or do they? J Target Meas Anal Mark 17(2):139–142

Rebekić A, Lončarić Z, Petrović S, Marić S (2015) Pearson’s or Spearman’s correlation coefficient-which one to use? Poljoprivreda 21(2):47–54

Reichle RH, Draper CS, Liu Q, Girotto M, Mahanama SPP, Koster RD, De Lannoy GJM (2017) Assessment of MERRA-2 land surface hydrology estimates. J Clim 30(8):2937–2960

Rezaei M, Farajzadeh M, Mielonen T, Ghavidel Y (2019) Analysis of spatio-temporal dust aerosol frequency over Iran based on satellite data. Atmos Pollut Res 10(2):508–519

Rodell M, Houser PR, Jambor UEA, Gottschalck J, Mitchell K, Meng C-JJ, Arsenault K et al (2004) The global land data assimilation system. Bull Am Meteor Soc 85(3):381–394. https://doi.org/10.1175/BAMS-85-3-381

Sabetghadam S, Khoshsima M, Alizadeh-Choobari O (2018) Spatial and temporal variations of satellite-based aerosol optical depth over Iran in Southwest Asia: Identification of a regional aerosol hot spot. Atmos Pollut Res 9(5):849–856

Salami H, Khorami S, Yazdani S, Saleh I (2021) Economic evaluation of the damages of dust bowl on crop yield by choice experiment method in Khuzestan Province of Iran. Int J Agric Manag Dev 11(3)

Shafizadeh-Moghadam H, Minaei M, Pontius RG Jr, Asghari A, Dadashpoor H (2021) Integrating a forward feature selection algorithm, random forest, and cellular automata to extrapolate urban growth in the Tehran-Karaj Region of Iran. Comput Environ Urban Syst 87:101595

Sharafati A, Asadollah SBHS, Hosseinzadeh M (2020a) The potential of new ensemble machine learning models for effluent quality parameters prediction and related uncertainty. Process Saf Environ Prot 140:68–78

Sharafati A, Asadollah SBHS, Motta D, Yaseen ZM (2020b) Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis. Hydrol Sci J 65:2022–2042

Shiru MS, Shahid S, Chae S-T, Chung E-S (2022) Replicability of annual and seasonal precipitation by CMIP5 and CMIP6 GCMs over East Asia. KSCE J Civ Eng 26:1–12

Silva FG, Sena I, Lima LA, Fernandes FP, Pacheco MF, Vaz CB, Lima J, et al (2022) External climate data extraction using the forward feature selection method in the context of occupational safety. In: International conference on computational science and its applications. Springer, pp 3–14

Srivastava C, Singh S, Singh AP (2018) Estimation of air pollution in Delhi using machine learning techniques. In: 2018 International conference on computing, power and communication technologies (GUCON). IEEE, pp 304–309

Sun E, Xu X, Che H, Tang Z, Gui K, An L, Lu C et al (2019) Variation in MERRA-2 aerosol optical depth and absorption aerosol optical depth over China from 1980 to 2017. J Atmos Solar Terr Phys 186:8–19

Tao T, Shi P, Wang H, Yuan L, Wang S (2021) Performance evaluation of linear and nonlinear models for short-term forecasting of tropical-storm winds. Appl Sci 11(20):9441

U.S. Environmental Protection Agency, Office of Air Quality Planning and Standards (1996) Review of the national ambient air quality standards for particulate matter: Policy assessment of scientific and technical information. DIANE Publishing

Ukhov A, Mostamandi S, Silva AD, Flemming J, Alshehri Y, Shevchenko I, Stenchikov G (2020) Assessment of natural and anthropogenic aerosol air pollution in the Middle East using MERRA-2, CAMS data assimilation products, and high-resolution WRF-Chem model simulations. Atmos Chem Phys 20(15):9281–9310

USEPA, Office of Air and Radiation (2019) Health and environmental effects of particulate matter (PM). Retrieved

Veselovskii I, Goloub P, Podvin T, Tanre D, Silva AD, Colarco P, Castellanos P et al (2018) Characterization of smoke and dust episode over West Africa: comparison of MERRA-2 modeling with multiwavelength Mie-Raman lidar observations. Atmos Meas Tech 11(2):949–969

Wang W-C, Chau K-W, Cheng C-T, Qiu L (2009) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J Hydrol 374(3–4):294–306

Wang F, Wang Y, Zhang K, Hu M, Weng Q, Zhang H (2021) Spatial heterogeneity modeling of water quality based on random forest regression and model interpretation. Environ Res 202:111660

Wei Z (2021) Forecasting wind waves in the US Atlantic Coast using an artificial neural network model: towards an AI-based storm forecast system. Ocean Eng 237:109646

WHO (2014) 7 million premature deaths annually linked to air pollution

Xu X, Wu H, Yang X, Xie L (2020) Distribution and transport characteristics of dust aerosol over Tibetan Plateau and Taklimakan Desert in China using MERRA-2 and CALIPSO data. Atmos Environ 237:117670

Xu J, Lu W, Li J, Yuan H (2022) Dependency maximization forward feature selection algorithms based on normalized cross-covariance operator and its approximated form for high-dimensional data. Inf Sci 617:416–434

Yao W, Che H, Gui K, Wang Y, Zhang X (2020) Can MERRA-2 reanalysis data reproduce the three-dimensional evolution characteristics of a typical dust process in East Asia? A case study of the dust event in May 2017. Remote Sens 12(6):902

Younis H, Anwar MW, Khan MUG, Sikandar A, Bajwa UI (2021) A new sequential forward feature selection (SFFS) algorithm for mining best topological and biological features to predict protein complexes from protein–protein interaction networks (PPINs). Interdiscip Sci Comput Life Sci 13(3):371–388

Yousefi R, Wang F, Ge Q, Shaheen A (2020) Long-term aerosol optical depth trend over Iran and identification of dominant aerosol types. Sci Total Environ 722:137906

Zarasvandi A (2009) Environmental impacts of dust storms in the Khuzestan province. Environmental Protection Agency (EPA) of Khuzestan province, internal report

Zarasvandi A, Carranza EJM, Moore F, Rastmanesh F (2011) Spatio-temporal occurrences and mineralogical–geochemical characteristics of airborne dusts in Khuzestan Province (southwestern Iran). J Geochem Explor 111(3):138–151

Zhang Y, Haghani A (2015) A gradient boosting method to improve travel time prediction. Transp Res Part C Emerg Technol 58:308–324

Zhang X, Chu Y, Wang Y, Zhang K (2018) Predicting daily PM2. 5 concentrations in Texas using high-resolution satellite aerosol optical depth. Sci Total Environ 631:904–911

Zhang J, Ma G, Huang Y, Aslani F, Nener B (2019) Modelling uniaxial compressive strength of lightweight self-compacting concrete using random forest regression. Constr Build Mater 210:713–719

Zhu X, Zhang P, Xie M (2021) A joint long short-term memory and AdaBoost regression approach with application to remaining useful life estimation. Measurement 170:108707

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Thông tin tác giả