Design of an early alert system for PM2.5 through a stochastic method and machine learning models

Abadi M. et al., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. vo.2.4.1. (Version 0.2.4.1). Tensorflow. airALERT, 2005. AirAlert information. 〈http://www.airalert.info/〉 (Accessed 19 June 2020). Asante-Duah, 2017 Baena-Salazar, 2019, Red neuronal artificial aplicada para el pronóstico de eventos críticos de PM2.5 en el Valle de Aburrá, DYNA, 86 Ballesteros-González, 2020, Estimating the air quality and health impacts of biomass burning in northern South America using a chemical transport model Sci, Total Environ., 739, 10.1016/j.scitotenv.2020.139755 Barnston, 1992, Correspondence among the Correlation, RMSE and Heidke Forecast verification Measures; Refinement of the Heidke Score, Weather Forecast., 7, 699, 10.1175/1520-0434(1992)007<0699:CATCRA>2.0.CO;2 Boylan, 2006, PM and light extinction model performance metrics, goals, and criteria for three-dimensional air quality models, Atmos. Environ., 40, 4946, 10.1016/j.atmosenv.2005.09.087 Brook, 2010, Particulate Matter Air Pollution and Cardiovascular Disease, Circulation, 121, 2331, 10.1161/CIR.0b013e3181dbece1 Bu, 2019, Exposure to commonly-used phthalates and the associated health risks in the indoor environment of urban China, Sci. Total Environ., 658, 843, 10.1016/j.scitotenv.2018.12.260 Byun, 2006, Review of the governing equations, computational algorithms, and other components of the Models- 3 Community Multiscale Air Quality (CMAQ) modeling system, Appl. Mech. Rev., 59, 51, 10.1115/1.2128636 Calderón-Garcidueñas, 2008, Systemic Inflammation, Endothelial Dysfunction, and Activation in Clinically Healthy Children Exposed to Air Pollutants, Inhal. Toxicol., 20, 499, 10.1080/08958370701864797 Casallas, 2020, Validation of PM10 and PM2.5 early alert in Bogotá, Colombia, through the modeling software WRF-CHEM, Environ. Sci. Pollut. Res, 27, 35930, 10.1007/s11356-019-06997-9 Casallas, 2021, Long short-term memory artificial neural network approach to forecast meteorology and PM2.5 local variables in Bogotá, Colombia, Model. Earth Syst. Environ. Casallas, 2021, Understanding convective storms in a tropical, high-altitude location with in-situ meteorological observations and GPS-derived water vapor. Atmósfera, Early Release Castillo-Camacho, 2020, Personal Exposure to PM2.5 in the Massive Transport System of Bogotá and Medellín, Colombia, Asian J. Atmos. Environ., 14, 210, 10.5572/ajae.2020.14.3.210 Chai, 2013, Evaluation of the United States National Air Quality Forecast Capability experimental real-time predictions in 2010 using Air Quality System ozone and NO 2 measurements, Geosci. Model Dev., 6, 1831, 10.5194/gmd-6-1831-2013 Chollet, F., et al., 2015. Keras. GitHub. Retrieved from 〈https://github.com/fchollet/keras〉. vo.2.4.3. (Version o.2.4.3). Keras. Cobourn, 2010, An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations, Atmos. Environ., 44, 3015, 10.1016/j.atmosenv.2010.05.009 Commission Directive, 2015, Ambient air quality and cleaner air for Europe, European Parliament, Counc. Eur. Union Commission Directive, 2016, The reduction of national emissions of certain atmospheric pollutants, amending Directive 2003/35/EC and repealing Directive 2001/81/EC, Eur. Parliam., Counc. Eur. Union Comrie, 1997, Comparing Neural Networks and Regression Models for Ozone Forecasting, J. Air Waste Manag. Assoc., 47, 653, 10.1080/10473289.1997.10463925 Cortes, 1995, Support-vector networks, Mach. Learn, 20, 273, 10.1007/BF00994018 Dominguez-Calle, 2014, Estado del arte de los sistemas de alerta temprana en Colombia, Rev. Acad. Colomb. Cienc., 38, 321 EPA, 2014, AQI - Air Quality Index. A Guide to Air Quality and Your Health, EPA-456/F. -14-002 Decreto 595 of 2015, 2015. Adopting Bogotá’s Environmental Early Warning System for its Air Component SATAB-air, EO, Office of the Mayor of Bogotá. 〈https://www.alcaldiabogota.gov.co/sisjur/normas/Norma1.jsp?i=64242〉 (accessed 12 January 2021). EPA., 2020. Probabilistic Risk Assessment to Inform Decision Making: Frequently Asked Questions (Washington (DC): Risk Assessment Forum, US Environmental Protection Agency). EPA/100/R-14/003. 〈https://www.epa.gov/osa/probabilistic-risk-assessment-inform-decision-making-frequently-asked-questions〉 (accessed 12 January 2021). Fletcher, 2009, Support vector machines explained, Univ. Coll. Lond. Franceschi, 2018, Discovering relationships and forecasting PM10 and PM2.5 concentrations in Bogotá, Colombia, using Artificial Neural Networks, Principal Component Analysis, and k-means clustering, Atmos. Pollut. Res., 9, 912, 10.1016/j.apr.2018.02.006 Greene, 2006, 3, 86 Gómez Ortega, 2018, Sistema de Alerta Temprana Ambiental y Efectos en Salud – SATAES, una Herram. Para. la Acción Gómez Peláez, 2020, Air quality status and trends over large cities in South America, Environ. Sci. Policy, 114, 422, 10.1016/j.envsci.2020.09.009 González, 2018, High-resolution air quality modeling in a medium-sized city in the tropical Andes: Assessment of local and global emissions in understanding ozone and PM10 dynamics, Atmos. Pollut. Res., 9, 934, 10.1016/j.apr.2018.03.003 Guevara-Luna, 2020, Implementation and evaluation of WRF simulation over a city with complex terrain using Alos-Palsar 0.4 s topography, Environ. Sci. Pollut. Res, 27, 37818, 10.1007/s11356-020-09824-8 Hochreiter, 1997, Long Short-Term Memory, Neural Comput., 9, 1735, 10.1162/neco.1997.9.8.1735 Hou, W., Li, Z., Zhang Yuhuan, Xu, H., Zhang Y., Li K., Li D., Wei, P., Ma, Y., 2014. Using support vector regression to predict PM10 and PM2.5. IOP Conference Series: Earth and Environmental Science. 17, 012268. 10.1088/1755–1315/17/1/012268. Holton, 2004 Huang, 2018, A deep CNN-LSM model for particulate matter (PM2.5) forecasting in smart cities, Sensors, 1, 2220, 10.3390/s18072220 Inness, 2019, The CAMS reanalysis of atmospheric composition, Atmos. Chem. Phys., 19, 3515, 10.5194/acp-19-3515-2019 Ivakhnenko, 1965 Ivakhnenko, 1967 Jorquera, 2021, Air quality management in Chile: Effectiveness of PM2.5 regulations, Urban Clim., 35, 10.1016/j.uclim.2020.100764 Kelly, 2011, Monitoring air pollution: Use of early warning systems for public health, Respirology, 17, 7, 10.1111/j.1440-1843.2011.02065.x Kumar, 2016, Application of WRF-CHEM model to simulate PM10 concentration over Bogotá, Aerosol Air Qual. Res., 16, 1206, 10.4209/aaqr.2015.05.0318 Kumar, 2018, Five steps to improve air-quality forecasts, Nature, 561, 27, 10.1038/d41586-018-06150-5 Liu, 2020, Bioaccessibility, source impact and probabilistic health risk of the toxic metals in PM2. 5 based on lung fluids test and Monte Carlo simulations, J. Clean. Prod., 283 Liu, 2020, A new risk probability calculation method for urban ecological risk assessment, Environ. Res. Lett., 15, 10.1088/1748-9326/ab6667 Longo, 2013, The chemistry CATT-BRAMS model (CCATT-BRAMS 4.5): a regional atmospheric model system for integrated air quality and weather forecasting and research, Geosci. Model Dev. Discuss., 6, 1173 Lu, 2005, Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends, Chemosphere, 59, 693, 10.1016/j.chemosphere.2004.10.032 Lu, 2019, Assessing the association between fine particulate matter (PM2.5) constituents and cardiovascular diseases in a mega-city of Pakistan, Environ. Pollut., 252B, 1412, 10.1016/j.envpol.2019.06.078 Makowski, 2000, Modeling paradigms applied to the analysis of European air quality, Eur. J. Oper. Res., 122, 219, 10.1016/S0377-2217(99)00230-1 Martonen, 2003, Risk assessment dosimetry model for inhaled particulate matter: I. Human subjects, Toxicol. Lett., 138, 119, 10.1016/S0378-4274(02)00411-3 Maas, 2016, Towards Cleaner Air. Scientific Assessment Report 2016: Summary for Policymakers, EMEP Steer. Body Work. Group Eff. Conv. Long. -Range Transbound. Air Pollut., Oslo McFarland, 2020, A Monte Carlo framework for probabilistic analysis and variance decomposition with distribution parameter uncertainty, Reliab. Eng. Syst. Saf., 197, 10.1016/j.ress.2020.106807 Mendez-Espinosa, 2020, Air quality variations in Northern South America during the COVID-19 lockdown, Sci. Total Environ., 749, 10.1016/j.scitotenv.2020.141621 Mogollón-Sotelo, 2020, A support vector machine model to forecast ground-level PM2.5 in a highly populated city with a complex terrain, Air Qual. Atmos. Health, 14, 399, 10.1007/s11869-020-00945-0 Ndiaye, 2019, Safe Grid Search with Optimal Complexity, Proc. 36th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res., 97, 4771 Liao, 2021, Statistical Approaches for Forecasting Primary Air Pollutants: A Review, Atmosphere, 12, 686, 10.3390/atmos12060686 Lira, 2007, Air quality prediction in Uberlândia, Brazil, using linear models and neural networks, Comput. Aided Chem. Eng., 24, 51, 10.1016/S1570-7946(07)80032-0 Pedregosa, 2011, Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12, 2825 Prechelt, L., 1998. Early Stopping - But When?. In: Orr G.B., Müller KR. (eds) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science. 1524. https://doi.org/10.1007/3–540-49430–8_3. Pulido, J.C., Vasquez, J.A., Hernandez, L.A., 2020. Validación de los modelos de calidad del aire empleados por el SIMCAB. Final report. Bogotá, Colombia: Dept air, auditory and visual quality, District Secretary of Environment. Apr. Report No. 2020ER68620. Rojas, 2004, Revisión de las emisiones de material particulado por la combustión de Diesel y Biodiesel, Rev. De. Ing., 20 Saide, 2015, Air quality forecasting for winter‐time PM2. 5 episodes occurring in multiple cities in central and southern Chile, J. Geophys. Res.: Atmospheres, 121, 558, 10.1002/2015JD023949 Sayeed, 2021, Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks, Atmos. Environ., 253, 10.1016/j.atmosenv.2021.118376 Shahraiyni, 2016, Statistical modeling approaches for PM10 prediction in urban areas; A review of 21st century studies, Atmosphere, 7, 15, 10.3390/atmos7020015 Skamarock, 2019, A Description of the Advanced Research WRFVersion 4. Tech. rep, NCAR Tech. Note NCAR/TN-556+STR Sokhi, 2021, A global observational analysis to understand changes in air quality during exceptionally low anthropogenic emission conditions, Environ. Int., 157, 10.1016/j.envint.2021.106818 Tao, 2019, Air Pollution Forecasting using a Deep Learning Model based on 1D Convnets and Bidirectional GRU, IEEE Access, 7, 76690, 10.1109/ACCESS.2019.2921578 Tzanis, 2019, Applying linear and nonlinear models for the estimation of particulate matter variability, Environ. Pollut., 246, 89, 10.1016/j.envpol.2018.11.080 UNECE, 2007, Report of the fourth and fifth meetings of the Expert Group on Particulate Matter (Report ECE/EB.AIR/WG.5/2007/18), UN Econ. Soc. Counc. UNECE, 2013, Protocol to Abate Acidification, Eutrophication and Ground-level Ozone as amended on 4 May 2012 (Gothenburg Protocol), Treaties Other Int. WAQI, 2007. About the World Air Quality Index project. 〈https://waqi.info/〉. (accessed 10 April 2020). Wan, 2020, Science-policy interplay on air pollution governance in China, Environ. Sci. Policy, 107, 150, 10.1016/j.envsci.2020.03.003 Wang, 2018, A county-level estimate of PM 2.5 related chronic mortality risk in China based on multi-model exposure data, Environ. Int., 110, 105, 10.1016/j.envint.2017.10.015 Wen, 2009, Association between media alerts of air quality index and change of outdoor activity among adult asthma in six states, Brfss. J. Com. Health, 34, 40, 10.1007/s10900-008-9126-4 WHO, 2015. Reducing Global Health Risks Through Mitigation of Short-Lived Climate Pollutants. Scoping Report for Policy-makers. 〈https://apps.who.int/iris/bitstream/handle/10665/189524/9789241565080_eng.pdf;jsessionid=1A08270BB7B2D3BC974EA81554DA2E0C?sequence=1〉. (accessed 01 March 2020). WHO, 2018. Ambient (outdoor) air pollution. 〈https://www.who.int/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health〉 (accessed 24 December 2020). Willmott, 1985, Statistics for the evaluation and comparison of models, J. Geophys. Res.: Oceans, 90, 8995, 10.1029/JC090iC05p08995 Xing, 2016, The impact of PM2.5 on the human respiratory system. Journal of thoracic disease, 8 Zarate, 2007, Air quality modelling over Bogotá, Colombia: Combined techniques to estimate and evaluate emission inventories, Atmos. Environ., 41, 6302, 10.1016/j.atmosenv.2007.03.011 Zhang, 2012, Real-time air quality forecasting, part I: history, techniques and current status, Atmos. Environ., 60, 632, 10.1016/j.atmosenv.2012.06.031 DANE, 2018. Proyecciones de Población Bogotá. 〈https://www.dane.gov.co/index.php/estadisticas-por-tema/demografia-y-poblacion/proyecciones-de-poblacion/proyecciones-de-poblacion-bogota〉 (accessed 13 february 2021). SDA, 2020. Reporte de estaciones. 〈http://rmcab.ambientebogota.gov.co/Report/stationreport〉 (accessed 02 february 2020).