Articles | Volume 19, issue 20
Research article 18 Oct 2019
Research article | 18 Oct 2019
Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model
Hyun S. Kim et al.
No articles found.
Arman Pouyaei, Yunsoo Choi, Jia Jung, Bavand Sadeghi, and Chul Han Song
Geosci. Model Dev., 13, 3489–3505,Short summary
This paper introduces a novel Lagrangian model (Concentration Trajectory of Air pollution with an Integrated Lagrangian model, C-TRAIL) for showing the source and receptor areas by following polluted air masses. To investigate the concentrations and trajectories of air masses simultaneously, we use the trajectory-grid (TG) Lagrangian advection model. The TG model follows the concentrations of representative air
packetsof species along trajectories determined by the wind field.
Sojin Lee, Chul Han Song, Kyung Man Han, Daven K. Henze, Kyunghwa Lee, Jinhyeok Yu, Jung-Hun Woo, Jia Jung, Yunsoo Choi, Pablo E. Saide, and Gregory R. Carmichael
Geosci. Model Dev. Discuss.,
Revised manuscript not accepted
Kyunghwa Lee, Jinhyeok Yu, Sojin Lee, Mieun Park, Hun Hong, Soon Young Park, Myungje Choi, Jhoon Kim, Younha Kim, Jung-Hun Woo, Sang-Woo Kim, and Chul H. Song
Geosci. Model Dev., 13, 1055–1073,Short summary
For the purpose of providing reliable and robust air quality predictions, an operational air quality prediction system was developed for the main air quality criteria species in South Korea (PM10, PM2.5, CO, O3 and SO2) by preparing the initial conditions for model simulations via data assimilation using satellite- and ground-based observations. The performance of the developed air quality prediction system was evaluated using ground in situ data during the KORUS-AQ campaign period.
Myungje Choi, Jhoon Kim, Jaehwa Lee, Mijin Kim, Young-Je Park, Brent Holben, Thomas F. Eck, Zhengqiang Li, and Chul H. Song
Atmos. Meas. Tech., 11, 385–408,Short summary
This study is a major version upgrade of the aerosol product from GOCI, the first and unique ocean color imager in geostationary earth orbit. It describes the improvement of version 2 of the GOCI Yonsei aerosol retrieval algorithm for near-real-time processing with improved accuracy from the modification of cloud masking, surface reflectance, etc. The product is validated against AERONET/SONET over East Asia with analyses of various errors features, and a pixel-level uncertainty is calculated.
Myungje Choi, Jhoon Kim, Jaehwa Lee, Mijin Kim, Young-Je Park, Ukkyo Jeong, Woogyung Kim, Hyunkee Hong, Brent Holben, Thomas F. Eck, Chul H. Song, Jae-Hyun Lim, and Chang-Keun Song
Atmos. Meas. Tech., 9, 1377–1398,Short summary
The Geostationary Ocean Color Imager (GOCI) is the first ocean color sensor in geostationary orbit. It enables hourly aerosol optical properties to be observed in high spatial resolution. This study presents improvements of the GOCI Yonsei Aerosol Retrieval (YAER) algorithm and its validation results using ground-based and other satellite-based observation products during DRAGON-NE Asia 2012 Campaign. Retrieval errors are also analyzed according to various factors through the validation studies.
S. Lee, C. H. Song, R. S. Park, M. E. Park, K. M. Han, J. Kim, M. Choi, Y. S. Ghim, and J.-H. Woo
Geosci. Model Dev., 9, 17–39,Short summary
We developed an integrated air quality modeling system using AOD data retrieved from a geostationary satellite sensor, GOCI (Geostationary Ocean Color Imager), over Northeast Asia with an application of the spatiotemporal-kriging (STK) method and conducted short-term hindcast runs using the developed system. It appears that the STK approach can greatly reduce not only the errors and biases of AOD and PM10 predictions but also the computational burden of a chemical weather forecast (CWF).
K. M. Han, S. Lee, L. S. Chang, and C. H. Song
Atmos. Chem. Phys., 15, 1913–1938,
S. Seo, J. Kim, H. Lee, U. Jeong, W. Kim, B. N. Holben, S.-W. Kim, C. H. Song, and J. H. Lim
Atmos. Chem. Phys., 15, 319–334,Short summary
The estimation of PM10 from optical measurement of AERONET and MODIS by various empirical models was evaluated for the DRAGON-Asia campaign. The results showed the importance of boundary layer height (BLH) and effective radius (Reff) in estimating PM10. The highest correlation between the estimated and measured values was found to be 0.81 in winter due to the stagnant air mass and low BLH, while the poorest values were 0.54 in spring due to the influence of long-range transport above BLH.
H.-K. Kim, J.-H. Woo, R. S. Park, C. H. Song, J.-H. Kim, S.-J. Ban, and J.-H. Park
Atmos. Chem. Phys., 14, 7461–7484,
R. S. Park, S. Lee, S.-K. Shin, and C. H. Song
Atmos. Chem. Phys., 14, 2185–2201,
M. E. Park, C. H. Song, R. S. Park, J. Lee, J. Kim, S. Lee, J.-H. Woo, G. R. Carmichael, T. F. Eck, B. N. Holben, S.-S. Lee, C. K. Song, and Y. D. Hong
Atmos. Chem. Phys., 14, 659–674,
K. Lee and C. E. Chung
Atmos. Chem. Phys., 13, 2907–2921,
Related subject area
Subject: Aerosols | Research Activity: Atmospheric Modelling | Altitude Range: Troposphere | Science Focus: Physics (physical properties and processes)Drivers of the fungal spore bioaerosol budget: observational analysis and global modelingImproving the sectional Model for Simulating Aerosol Interactions and Chemistry (MOSAIC) aerosols of the Weather Research and Forecasting-Chemistry (WRF-Chem) model with the revised Gridpoint Statistical Interpolation system and multi-wavelength aerosol optical measurements: the dust aerosol observation campaign at Kashi, near the Taklimakan Desert, northwestern ChinaA revised mineral dust emission scheme in GEOS-Chem: improvements in dust simulations over ChinaQuantifying the range of the dust direct radiative effect due to source mineralogy uncertaintyTechnical note: The enhancement limit of coagulation scavenging of small charged particlesThe effect of meteorological conditions and atmospheric composition in the occurrence and development of new particle formation (NPF) events in EuropeEffectiveness of emission control in reducing PM2.5 pollution in central China during winter haze episodes under various potential synoptic controlsAssessment of meteorology vs. control measures in the China fine particular matter trend from 2013 to 2019 by an environmental meteorology indexA global model perturbed parameter ensemble study of secondary organic aerosol formationAssimilating aerosol optical properties related to size and absorption from POLDER/PARASOL with an ensemble data assimilation systemChanges in black carbon emissions over Europe due to COVID-19 lockdownsEffects of marine organic aerosols as sources of immersion-mode ice-nucleating particles on high-latitude mixed-phase cloudsInsights into particulate matter pollution in the North China Plain during wintertime: local contribution or regional transport?Factors controlling marine aerosol size distributions and their climate effects over the northwest Atlantic Ocean regionMass accommodation and gas–particle partitioning in secondary organic aerosols: dependence on diffusivity, volatility, particle-phase reactions, and penetration depthEvident PM2.5 drops in the east of China due to the COVID-19 quarantine measures in FebruaryWildfire smoke-plume rise: a simple energy balance parameterizationEffective radiative forcing from emissions of reactive gases and aerosols – a multi-model comparisonProcesses controlling the vertical aerosol distribution in marine stratocumulus regions – a sensitivity study using the climate model NorESM1-MPrecipitation response to aerosol–radiation and aerosol–cloud interactions in regional climate simulations over EuropeAeroCom phase III multi-model evaluation of the aerosol life cycle and optical properties using ground- and space-based remote sensing as well as surface in situ observationsResponse of dust emissions in southwestern North America to 21st century trends in climate, CO2 fertilization, and land use: implications for air qualityRevisiting the relationship between Atlantic dust and tropical cyclone activity using aerosol optical depth reanalyses: 2003–2018How Asian aerosols impact regional surface temperatures across the globeWeaker cooling by aerosols due to dust–pollution interactionsSource backtracking for dust storm emission inversion using an adjoint method: case study of Northeast ChinaCharacteristics of surface energy balance and atmospheric circulation during hot-and-polluted episodes and their synergistic relationships with urban heat islands over the Pearl River Delta regionStudy on the impact of three Asian industrial regions on PM2.5 in Taiwan and the process analysis during transportParticle aging and aerosol–radiation interaction affect volcanic plume dispersion: evidence from the Raikoke 2019 eruptionThe warming Tibetan Plateau improves winter air quality in the Sichuan Basin, ChinaUncertainty in aerosol radiative forcing impacts the simulated global monsoon in the 20th centuryEffects of 3D electric field on saltation during dust storms: an observational and numerical studyAir quality impact of the Northern California Camp Fire of November 2018Amplification of South Asian haze by water vapour–aerosol interactionsAssessment of regional aerosol radiative effects under the SWAAMI campaign – Part 2: Clear-sky direct shortwave radiative forcing using multi-year assimilated data over the Indian subcontinentThe determination of highly time-resolved and source-separated black carbon emission rates using radon as a tracer of atmospheric dynamicsUnderstanding processes that control dust spatial distributions with global climate models and satellite observationsHeterogeneous nucleation of water vapor on different types of black carbon particlesImpacts of atmospheric transport and biomass burning on the inter-annual variation in black carbon aerosols over the Tibetan PlateauA complex aerosol transport event over Europe during the 2017 Storm Ophelia in CAMS forecast systems: analysis and evaluationSensitivity analysis of the surface ozone and fine particulate matter to meteorological parameters in ChinaHow aerosols and greenhouse gases influence the diurnal temperature rangeEvaluation of climate model aerosol trends with ground-based observations over the last 2 decades – an AeroCom and CMIP6 analysisImpact of biomass burning aerosols on radiation, clouds, and precipitation over the Amazon: relative importance of aerosol–cloud and aerosol–radiation interactionsDirect and semi-direct radiative forcing of biomass-burning aerosols over the southeast Atlantic (SEA) and its sensitivity to absorbing properties: a regional climate modeling studyTechnical note: Estimating aqueous solubilities and activity coefficients of mono- and α,ω-dicarboxylic acids using COSMOthermModels transport Saharan dust too low in the atmosphere: a comparison of the MetUM and CAMS forecasts with observationsDependency of particle size distribution at dust emission on friction velocity and atmospheric boundary-layer stabilityUsing machine learning to derive cloud condensation nuclei number concentrations from commonly available measurementsConstraints on global aerosol number concentration, SO2 and condensation sink in UKESM1 using ATom measurements
Ruud H. H. Janssen, Colette L. Heald, Allison L. Steiner, Anne E. Perring, J. Alex Huffman, Ellis S. Robinson, Cynthia H. Twohy, and Luke D. Ziemba
Atmos. Chem. Phys., 21, 4381–4401,Short summary
Bioaerosols are ubiquitous in the atmosphere and have the potential to affect cloud formation, as well as human and ecosystem health. However, their emissions are not well quantified, which hinders the assessment of their role in atmospheric processes. Here, we develop two new emission schemes for fungal spores based on multi-annual datasets of spore counts. We find that our modeled global emissions and burden are an order of magnitude lower than previous estimates.
Wenyuan Chang, Ying Zhang, Zhengqiang Li, Jie Chen, and Kaitao Li
Atmos. Chem. Phys., 21, 4403–4430,Short summary
Aerosol simulation in WRF-Chem often uses the MOSAIC aerosol mechanism. Still, we need variational data assimilation (DA) for the MOSAIC aerosols to blend aerosol optical measurements. This study provides a developed GSI variational DA system, with a tangent linear operator designed for multi-source and multi-wavelength aerosol optical measurements. We successfully applied the DA system in an aerosol field campaign to assimilate aerosol optical data in northwestern China.
Rong Tian, Xiaoyan Ma, and Jianqi Zhao
Atmos. Chem. Phys., 21, 4319–4337,Short summary
We improve the treatment of the dust emission process in GEOS-Chem by considering the effect of geographical variation of aerodynamic roughness length, smooth roughness length and soil texture, as well as the Owen effect and a more physically based formulation of sandblasting efficiency, which improve estimated threshold friction velocity and dust concentrations over China. Our study highlights the importance of incorporation of realistic land-surface properties into the dust emission scheme.
Longlei Li, Natalie M. Mahowald, Ron L. Miller, Carlos Pérez García-Pando, Martina Klose, Douglas S. Hamilton, Maria Gonçalves Ageitos, Paul Ginoux, Yves Balkanski, Robert O. Green, Olga Kalashnikova, Jasper F. Kok, Vincenzo Obiso, David Paynter, and David R. Thompson
Atmos. Chem. Phys., 21, 3973–4005,Short summary
For the first time, this study quantifies the range of the dust direct radiative effect due to uncertainty in the soil mineral abundance using all currently available information. We show that the majority of the estimated direct radiative effect range is due to uncertainty in the simulated mass fractions of iron oxides and thus their soil abundance, which is independent of the model employed. We therefore prove the necessity of considering mineralogy for understanding dust–climate interactions.
Naser G. A. Mahfouz and Neil M. Donahue
Atmos. Chem. Phys., 21, 3827–3832,Short summary
In this technical note, we show that the limit of the coagulation scavenging enhancement of charged particles is asymptotically 2; that is, at the limit, charged particles are lost at twice the rate of their neutral counterparts. This has serious implications for aerosol particle survivability where ions play a role in nucleation and growth. Such cases can happen readily in experiments and cannot be neglected in the atmosphere.
Dimitrios Bousiotis, James Brean, Francis D. Pope, Manuel Dall'Osto, Xavier Querol, Andrés Alastuey, Noemi Perez, Tuukka Petäjä, Andreas Massling, Jacob Klenø Nøjgaard, Claus Nordstrøm, Giorgos Kouvarakis, Stergios Vratolis, Konstantinos Eleftheriadis, Jarkko V. Niemi, Harri Portin, Alfred Wiedensohler, Kay Weinhold, Maik Merkel, Thomas Tuch, and Roy M. Harrison
Atmos. Chem. Phys., 21, 3345–3370,Short summary
New particle formation events from 16 sites over Europe have been studied, and the influence of meteorological and atmospheric composition variables has been investigated. Some variables, like solar radiation intensity and temperature, have a positive effect on the occurrence of these events, while others have a negative effect, affecting different aspects such as the rate at which particles are formed or grow. This effect varies depending on the site type and magnitude of these variables.
Yingying Yan, Yue Zhou, Shaofei Kong, Jintai Lin, Jian Wu, Huang Zheng, Zexuan Zhang, Aili Song, Yongqing Bai, Zhang Ling, Dantong Liu, and Tianliang Zhao
Atmos. Chem. Phys., 21, 3143–3162,Short summary
We analyze the effectiveness of emission reduction for local and upwind regions during winter haze episodes controlled by the main potential synoptic patterns over central China, a regional pollutant transport hub with sub-basin topography. Our results provide an opportunity to effectively mitigate haze pollution via local emission control actions in coordination with regional collaborative actions according to different synoptic patterns.
Sunling Gong, Hongli Liu, Bihui Zhang, Jianjun He, Hengde Zhang, Yaqiang Wang, Shuxiao Wang, Lei Zhang, and Jie Wang
Atmos. Chem. Phys., 21, 2999–3013,Short summary
Surface concentrations of PM2.5 in China have had a declining trend since 2013 across the country. This research found that the control measures of emission reduction are the dominant factors in the PM2.5 declining trends in various regions. The contribution by the meteorology to the surface PM2.5 concentrations from 2013 to 2019 was not found to show a consistent trend, fluctuating positively or negatively by about 5% on the annual average and 10–20% for the fall–winter heavy-pollution seasons.
Kamalika Sengupta, Kirsty Pringle, Jill S. Johnson, Carly Reddington, Jo Browse, Catherine E. Scott, and Ken Carslaw
Atmos. Chem. Phys., 21, 2693–2723,Short summary
Global models consistently underestimate atmospheric secondary organic aerosol (SOA), which has significant climatic implications. We use a perturbed parameter model ensemble and ground-based observations to reduce the uncertainty in modelling SOA formation from oxidation of volatile organic compounds. We identify plausible parameter spaces for the yields of extremely low-volatility, low-volatility, and semi-volatile organic compounds based on model–observation match for three key model outputs.
Athanasios Tsikerdekis, Nick A. J. Schutgens, and Otto P. Hasekamp
Atmos. Chem. Phys., 21, 2637–2674,Short summary
Accurate representation of aerosols in the atmosphere is hard to achieve due to their complex microphysical and optical properties and uncertain emissions. In our work, we employ a data assimilation method which integrates model simulations with satellite observation related to the amount, size and the light absorption of aerosol. The use of these observations in an experiment improves aerosol representation and it is recommended for utilization in future data assimilation practices.
Nikolaos Evangeliou, Stephen M. Platt, Sabine Eckhardt, Cathrine Lund Myhre, Paolo Laj, Lucas Alados-Arboledas, John Backman, Benjamin T. Brem, Markus Fiebig, Harald Flentje, Angela Marinoni, Marco Pandolfi, Jesus Yus-Dìez, Natalia Prats, Jean P. Putaud, Karine Sellegri, Mar Sorribas, Konstantinos Eleftheriadis, Stergios Vratolis, Alfred Wiedensohler, and Andreas Stohl
Atmos. Chem. Phys., 21, 2675–2692,Short summary
Following the transmission of SARS-CoV-2 to Europe, social distancing rules were introduced to prevent further spread. We investigate the impacts of the European lockdowns on black carbon (BC) emissions by means of in situ observations and inverse modelling. BC emissions declined by 23 kt in Europe during the lockdowns as compared with previous years and by 11 % as compared to the period prior to lockdowns. Residential combustion prevailed in Eastern Europe, as confirmed by remote sensing data.
Xi Zhao, Xiaohong Liu, Susannah M. Burrows, and Yang Shi
Atmos. Chem. Phys., 21, 2305–2327,Short summary
Organic sea spray particles influence aerosol and cloud processes over the ocean. This study introduces the emission, cloud droplet activation, and ice nucleation (IN) of marine organic aerosol (MOA) into the Community Earth System Model. Our results indicate that MOA IN particles dominate primary ice nucleation below 400 hPa over the Southern Ocean and Arctic boundary layer. MOA enhances cloud forcing over the Southern Ocean in the austral winter and summer.
Jiarui Wu, Naifang Bei, Yuan Wang, Xia Li, Suixin Liu, Lang Liu, Ruonan Wang, Jiaoyang Yu, Tianhao Le, Min Zuo, Zhenxing Shen, Junji Cao, Xuexi Tie, and Guohui Li
Atmos. Chem. Phys., 21, 2229–2249,Short summary
A source-oriented version of the WRF-Chem model is developed to conduct source identification of wintertime PM2.5 in the North China Plain. Trans-boundary transport of air pollutants generally dominates the haze pollution in Beijing and Tianjin. The air quality in Hebei, Shandong, and Shanxi is generally controlled by local emissions. Primary aerosol species, such as EC and POA, are generally controlled by local emissions, while secondary aerosol shows evident regional characteristics.
Betty Croft, Randall V. Martin, Richard H. Moore, Luke D. Ziemba, Ewan C. Crosbie, Hongyu Liu, Lynn M. Russell, Georges Saliba, Armin Wisthaler, Markus Müller, Arne Schiller, Martí Galí, Rachel Y.-W. Chang, Erin E. McDuffie, Kelsey R. Bilsback, and Jeffrey R. Pierce
Atmos. Chem. Phys., 21, 1889–1916,Short summary
North Atlantic Aerosols and Marine Ecosystems Study measurements combined with GEOS-Chem-TOMAS modeling suggest that several not-well-understood key factors control northwest Atlantic aerosol number and size. These synergetic and climate-relevant factors include particle formation near and above the marine boundary layer top, particle growth by marine secondary organic aerosol on descent, particle formation/growth related to dimethyl sulfide, sea spray aerosol, and ship emissions.
Manabu Shiraiwa and Ulrich Pöschl
Atmos. Chem. Phys., 21, 1565–1580,Short summary
Mass accommodation is a crucial process in secondary organic aerosol partitioning that depends on volatility, diffusivity, reactivity, and particle penetration depth of the chemical species involved. For efficient kinetic modeling, we introduce an effective mass accommodation coefficient that accounts for the above influencing factors, can be applied in the common Fuchs–Sutugin approximation, and helps to resolve inconsistencies and shortcomings of earlier experimental and model investigations.
Zhicong Yin, Yijia Zhang, Huijun Wang, and Yuyan Li
Atmos. Chem. Phys., 21, 1581–1592,Short summary
It is a must to disentangle the contributions of stable meteorology from the effects of the COVID-19 lockdown. A 59 % decline in PM2.5 related to the COVID-19 pandemic was found in North China. The COVID-19 quarantine measures decreased the PM2.5 in the Yangtze River Delta by 72 %. In Hubei Province where most pneumonia cases were confirmed, the impact of the total emission reduction (72 %) evidently exceeded the rising percentage of PM2.5 driven by meteorology (13 %).
Nadya Moisseeva and Roland Stull
Atmos. Chem. Phys., 21, 1407–1425,Short summary
Wildfire smoke-plume rise, which determines the emissions injection height, is widely recognized as an area of uncertainty within regional and global chemical transport models. In this work we propose a simple energy balance parameterization to predict the mean smoke equilibrium height for fires of arbitrary shape and intensity.
Gillian D. Thornhill, William J. Collins, Ryan J. Kramer, Dirk Olivié, Ragnhild B. Skeie, Fiona M. O'Connor, Nathan Luke Abraham, Ramiro Checa-Garcia, Susanne E. Bauer, Makoto Deushi, Louisa K. Emmons, Piers M. Forster, Larry W. Horowitz, Ben Johnson, James Keeble, Jean-Francois Lamarque, Martine Michou, Michael J. Mills, Jane P. Mulcahy, Gunnar Myhre, Pierre Nabat, Vaishali Naik, Naga Oshima, Michael Schulz, Christopher J. Smith, Toshihiko Takemura, Simone Tilmes, Tongwen Wu, Guang Zeng, and Jie Zhang
Atmos. Chem. Phys., 21, 853–874,Short summary
This paper is a study of how different constituents in the atmosphere, such as aerosols and gases like methane and ozone, affect the energy balance in the atmosphere. Different climate models were run using the same inputs to allow an easy comparison of the results and to understand where the models differ. We found the effect of aerosols is to reduce warming in the atmosphere, but this effect varies between models. Reactions between gases are also important in affecting climate.
Lena Frey, Frida A.-M. Bender, and Gunilla Svensson
Atmos. Chem. Phys., 21, 577–595,Short summary
We investigate the vertical distribution of aerosol in the climate model NorESM1-M in five regions of marine stratocumulus clouds. We thereby analyze the total aerosol extinction to facilitate a comparison with satellite data. We find that the model underestimates aerosol extinction throughout the troposphere, especially elevated aerosol layers. Further, we perform sensitivity experiments to identify the processes most important for vertical aerosol distribution in our model.
José María López-Romero, Juan Pedro Montávez, Sonia Jerez, Raquel Lorente-Plazas, Laura Palacios-Peña, and Pedro Jiménez-Guerrero
Atmos. Chem. Phys., 21, 415–430,Short summary
The effect of aerosols on regional climate simulations presents large uncertainties due to their complex and non-linear interactions with a wide variety of factors, including aerosol–radiation and aerosol–cloud interactions. We show how these interactions are strongly conditioned by the meteorological situation and the type of aerosol. While natural aerosols tend to increase precipitation in some areas, anthropogenic aerosols decrease the number of rainy days in some pollutant regions.
Jonas Gliß, Augustin Mortier, Michael Schulz, Elisabeth Andrews, Yves Balkanski, Susanne E. Bauer, Anna M. K. Benedictow, Huisheng Bian, Ramiro Checa-Garcia, Mian Chin, Paul Ginoux, Jan J. Griesfeller, Andreas Heckel, Zak Kipling, Alf Kirkevåg, Harri Kokkola, Paolo Laj, Philippe Le Sager, Marianne Tronstad Lund, Cathrine Lund Myhre, Hitoshi Matsui, Gunnar Myhre, David Neubauer, Twan van Noije, Peter North, Dirk J. L. Olivié, Samuel Rémy, Larisa Sogacheva, Toshihiko Takemura, Kostas Tsigaridis, and Svetlana G. Tsyro
Atmos. Chem. Phys., 21, 87–128,Short summary
Simulated aerosol optical properties as well as the aerosol life cycle are investigated for 14 global models participating in the AeroCom initiative. Considerable diversity is found in the simulated aerosol species emissions and lifetimes, also resulting in a large diversity in the simulated aerosol mass, composition, and optical properties. A comparison with observations suggests that, on average, current models underestimate the direct effect of aerosol on the atmosphere radiation budget.
Yang Li, Loretta J. Mickley, and Jed O. Kaplan
Atmos. Chem. Phys., 21, 57–68,Short summary
Climate models predict a shift toward warmer, drier environments in southwestern North America. Under future climate, the two main drivers of dust trends play opposing roles: (1) CO2 fertilization enhances vegetation and, in turn, decreases dust, and (2) increasing land use enhances dust emissions from northern Mexico. In the worst-case scenario, elevated dust concentrations spread widely over the domain by 2100 in spring, suggesting a large climate penalty on air quality and human health.
Peng Xian, Philip J. Klotzbach, Jason P. Dunion, Matthew A. Janiga, Jeffrey S. Reid, Peter R. Colarco, and Zak Kipling
Atmos. Chem. Phys., 20, 15357–15378,Short summary
Using dust AOD (DAOD) data from three aerosol reanalyses, we explored the correlative relationships between DAOD and multiple indices representing seasonal Atlantic TC activities. A robust negative correlation with Caribbean DAOD and Atlantic TC activity was found. We documented for the first time the regional differences of this relationship for over the Caribbean and the tropical North Atlantic. We also evaluated the impacts of potential confounding climate factors in this relationship.
Joonas Merikanto, Kalle Nordling, Petri Räisänen, Jouni Räisänen, Declan O'Donnell, Antti-Ilari Partanen, and Hannele Korhonen
Atmos. Chem. Phys. Discuss.,
Revised manuscript accepted for ACPShort summary
Human-induced aerosols concentrate around their emission sources, yet their climate effects span far and wide. Here, we use two climate models to robustly explore the mechanisms how Asian aerosols impact temperatures across the globe. A total removal of Asian aerosols increases the global temperatures by 0.26 ± 0.04 °C in the models, with most of the uncertainty arising from modelled cloud responses.
Klaus Klingmüller, Vlassis A. Karydis, Sara Bacer, Georgiy L. Stenchikov, and Jos Lelieveld
Atmos. Chem. Phys., 20, 15285–15295,Short summary
Particulate air pollution cools the climate and partially masks the greenhouse warming by reflecting sunlight and enhancing the reflection by clouds. The intensity of this cooling depends on interactions between pollution and desert dust within the atmosphere. Our simulations with a global atmospheric chemistry-climate model indicate that these interactions significantly weaken the cooling.
Jianbing Jin, Arjo Segers, Hong Liao, Arnold Heemink, Richard Kranenburg, and Hai Xiang Lin
Atmos. Chem. Phys., 20, 15207–15225,Short summary
Data assimilation provides a powerful tool to estimate emission inventories by feeding observations. This emission inversion relies on the correct assumption about the emission uncertainty, which describes the potential spatiotemporal spreads of sources. However, an unrepresentative uncertainty is unavoidable. Especially in the complex dust emission, the uncertainties can hardly all be taken into account. This study reports how adjoint can be used to detect errors in the emission uncertainty.
Ifeanyichukwu C. Nduka, Steve Hung Lam Yim, Chi-Yung Tam, and Jianping Guo
Atmos. Chem. Phys. Discuss.,
Preprint under review for ACPShort summary
This study analyzed the nature, mechanisms and drivers for Hot-and-Polluted episodes (HPEs) in the Pearl River Delta, China. A total of eight HPEs were identified and can be grouped into three clusters of HPEs that were respectively driven (1) by weak subsidence and convection induced by approaching tropical cyclones, (2) by calm conditions with low wind speed at the lower atmosphere, and (3) by the combination of both aforementioned conditions.
Ming-Tung Chuang, Maggie Chel Gee Ooi, Neng-Huei Lin, Joshua S. Fu, Chung-Te Lee, Sheng-Hsiang Wang, Ming-Cheng Yen, Steven Soon-Kai Kong, and Wei-Syun Huang
Atmos. Chem. Phys., 20, 14947–14967,Short summary
This study evaluated the impact of Asian haze from the three biggest industrial regions on Taiwan and analyzed the process during transport. The production and removal process revealed the mechanisms of long-range transport. This is the first time that the brute force method and process analysis technique has been applied in a Community Multiscale Air Quality Modeling System. Also, this study simulated the interesting transboundary transport of pollutants from southern mainland China to Taiwan.
Lukas O. Muser, Gholam Ali Hoshyaripour, Julia Bruckert, Ákos Horváth, Elizaveta Malinina, Sandra Wallis, Fred J. Prata, Alexei Rozanov, Christian von Savigny, Heike Vogel, and Bernhard Vogel
Atmos. Chem. Phys., 20, 15015–15036,Short summary
Volcanic aerosols endanger aircraft and thus disrupt air travel globally. For aviation safety, it is vital to know the location and lifetime of such aerosols in the atmosphere. Here we show that the interaction of volcanic particles with each other eventually reduces their atmospheric lifetime. Moreover, we demonstrate that sunlight heats these particles, which lifts them several kilometers in the atmosphere. These findings support a more reliable forecast of volcanic aerosol dispersion.
Shuyu Zhao, Tian Feng, Xuexi Tie, and Zebin Wang
Atmos. Chem. Phys., 20, 14873–14887,Short summary
The Tibetan Plateau has been experiencing a rapid warming during the last 40 years, particularly in winter. The warming leads to an increase in the planetary boundary layer height and a decrease in the relative humidity in the Sichuan Basin, causing a reduction of PM2.5 concentration by 17.5 % (~25.1 μg m−3), of which the reduction in secondary aerosols is 19.7 μg m−3. These findings indicate that the warming plateau plays an important role in mitigating air quality in downstream.
Jonathan K. P. Shonk, Andrew G. Turner, Amulya Chevuturi, Laura J. Wilcox, Andrea J. Dittus, and Ed Hawkins
Atmos. Chem. Phys., 20, 14903–14915,Short summary
We use a set of model simulations of the 20th century to demonstrate that the uncertainty in the cooling effect of man-made aerosol emissions has a wide range of impacts on global monsoons. For the weakest cooling, the impact of aerosol is overpowered by greenhouse gas (GHG) warming and monsoon rainfall increases in the late 20th century. For the strongest cooling, aerosol impact dominates over GHG warming, leading to reduced monsoon rainfall, particularly from 1950 to 1980.
Huan Zhang and You-He Zhou
Atmos. Chem. Phys., 20, 14801–14820,Short summary
We assess the effects of triboelectric charging on wind-blown sand via observations and a numerical model. The 3D electric field within a few centimetres of the ground is characterized for the first time. By using the discrete element method together with the particle-charging model, we explicitly account for the particle–particle charging during collisions. We find that triboelectric charging could enhance the total mass flux and saltation height by up to 20 % and 15 %, respectively.
Brigitte Rooney, Yuan Wang, Jonathan H. Jiang, Bin Zhao, Zhao-Cheng Zeng, and John H. Seinfeld
Atmos. Chem. Phys., 20, 14597–14616,Short summary
Wildfires have become increasingly prevalent. Intense smoke consisting of particulate matter (PM) leads to an increased risk of morbidity and mortality. The record-breaking Camp Fire ravaged Northern California for two weeks in 2018. Here, we employ a comprehensive chemical transport model along with ground-based and satellite observations to characterize the PM concentrations across Northern California and to investigate the pollution sensitivity predictions to key parameters of the model.
Vijayakumar Sivadasan Nair, Filippo Giorgi, and Usha Keshav Hasyagar
Atmos. Chem. Phys., 20, 14457–14471,Short summary
Air pollution and wintertime fog over South Asia is a major concern due to its significant implications on air quality, visibility and health. Coupled model simulations show that hygroscopic growth of aerosols contributes significantly to the aerosol-induced cooling at the surface. Our analysis demonstrates that the aerosol–moisture interaction is the most significant contributor favouring and strengthening the high-aerosol conditions (poor air quality) prevailing over South Asia during winter.
Harshavardhana Sunil Pathak, Sreedharan Krishnakumari Satheesh, Krishnaswamy Krishna Moorthy, and Ravi Shankar Nanjundiah
Atmos. Chem. Phys., 20, 14237–14252,Short summary
We have estimated the aerosol radiative forcing (ARF) by employing the assimilated, gridded aerosol datasets over the Indian region. The present ARF estimates are more accurate and certain than those estimated using the currently available, latest satellite-retrieved aerosol products. Therefore, the present ARF estimates and corresponding assimilated aerosol products emerge as potential candidates for improving the aerosol climate impact assessment at regional, subregional and seasonal scales.
Asta Gregorič, Luka Drinovec, Irena Ježek, Janja Vaupotič, Matevž Lenarčič, Domen Grauf, Longlong Wang, Maruška Mole, Samo Stanič, and Griša Močnik
Atmos. Chem. Phys., 20, 14139–14162,Short summary
We present a new method for the determination of highly time-resolved and source-separated black carbon emission rates. The atmospheric dynamics is quantified using the atmospheric radon concentration. Different intensity and daily dynamics of black carbon emission rates for two different environments are presented: urban and rural area. The method can be used to assess the efficiency of pollution mitigation measures, thereby avoiding the influence of variable meteorology.
Mingxuan Wu, Xiaohong Liu, Hongbin Yu, Hailong Wang, Yang Shi, Kang Yang, Anton Darmenov, Chenglai Wu, Zhien Wang, Tao Luo, Yan Feng, and Ziming Ke
Atmos. Chem. Phys., 20, 13835–13855,Short summary
The spatiotemporal distributions of dust aerosol simulated by global climate models (GCMs) are highly uncertain. In this study, we evaluate dust extinction profiles, optical depth, and surface concentrations simulated in three GCMs and one reanalysis against multiple satellite retrievals and surface observations to gain process-level understanding. Our results highlight the importance of correctly representing dust emission, dry/wet deposition, and size distribution in GCMs.
Ari Laaksonen, Jussi Malila, and Athanasios Nenes
Atmos. Chem. Phys., 20, 13579–13589,Short summary
Aerosol particles containing black carbon are ubiquitous in the atmosphere and originate from combustion processes. We examine their capability to act as condensation centers for water vapor. We make use of published experimental data sets for different types of black carbon particles, ranging from very pure particles to particles that contain both black carbon and water soluble organic matter, and we show that a recently developed theory reproduces most of the experimental results.
Han Han, Yue Wu, Jane Liu, Tianliang Zhao, Bingliang Zhuang, Honglei Wang, Yichen Li, Huimin Chen, Ye Zhu, Hongnian Liu, Qin'geng Wang, Shu Li, Tijian Wang, Min Xie, and Mengmeng Li
Atmos. Chem. Phys., 20, 13591–13610,Short summary
Combining simulations from a global chemical transport model and a trajectory model, we find that black carbon aerosols from South Asia and East Asia contribute 77 % of the surface black carbon in the Tibetan Plateau. The Asian monsoon largely modulates inter-annual transport of black carbon from non-local regions to the Tibetan Plateau surface in most seasons, while inter-annual fire activities in South Asia influence black carbon concentration over the Tibetan Plateau surface mainly in spring.
Dimitris Akritidis, Eleni Katragkou, Aristeidis K. Georgoulias, Prodromos Zanis, Stergios Kartsios, Johannes Flemming, Antje Inness, John Douros, and Henk Eskes
Atmos. Chem. Phys., 20, 13557–13578,Short summary
We assess the Copernicus Atmosphere Monitoring Service (CAMS) global and regional forecasts performance during a complex aerosol transport event over Europe induced by the passage of Storm Ophelia in mid-October 2017. Comparison with satellite observations reveals a satisfactory performance of CAMS global forecast assisted by data assimilation, while comparison with ground-based measurements indicates that the CAMS regional system over-performs compared to the global one in terms of air quality.
Zhihao Shi, Lin Huang, Jingyi Li, Qi Ying, Hongliang Zhang, and Jianlin Hu
Atmos. Chem. Phys., 20, 13455–13466,Short summary
Meteorological conditions play important roles in the formation of O3 and PM2.5 pollution in China. O3 is most sensitive to temperature and the sensitivity is dependent on the O3 chemistry formation or loss regime. PM2.5 is negatively sensitive to temperature, wind speed, and planetary boundary layer height and positively sensitive to humidity. The results imply that air quality in certain regions of China is sensitive to climate changes.
Camilla W. Stjern, Bjørn H. Samset, Olivier Boucher, Trond Iversen, Jean-François Lamarque, Gunnar Myhre, Drew Shindell, and Toshihiko Takemura
Atmos. Chem. Phys., 20, 13467–13480,Short summary
The span between the warmest and coldest temperatures over a day is a climate parameter that influences both agriculture and human health. Using data from 10 models, we show how individual climate drivers such as greenhouse gases and aerosols produce distinctly different responses in this parameter in high-emission regions. Given the high uncertainty in future aerosol emissions, this improved understanding of the temperature responses may ultimately help these regions prepare for future changes.
Augustin Mortier, Jonas Gliß, Michael Schulz, Wenche Aas, Elisabeth Andrews, Huisheng Bian, Mian Chin, Paul Ginoux, Jenny Hand, Brent Holben, Hua Zhang, Zak Kipling, Alf Kirkevåg, Paolo Laj, Thibault Lurton, Gunnar Myhre, David Neubauer, Dirk Olivié, Knut von Salzen, Ragnhild Bieltvedt Skeie, Toshihiko Takemura, and Simone Tilmes
Atmos. Chem. Phys., 20, 13355–13378,Short summary
We present a multiparameter analysis of the aerosol trends over the last 2 decades in the different regions of the world. In most of the regions, ground-based observations show a decrease in aerosol content in both the total atmospheric column and at the surface. The use of climate models, assessed against these observations, reveals however an increase in the total aerosol load, which is not seen with the sole use of observation due to partial coverage in space and time.
Lixia Liu, Yafang Cheng, Siwen Wang, Chao Wei, Mira L. Pöhlker, Christopher Pöhlker, Paulo Artaxo, Manish Shrivastava, Meinrat O. Andreae, Ulrich Pöschl, and Hang Su
Atmos. Chem. Phys., 20, 13283–13301,Short summary
This modeling paper reveals how aerosol–cloud interactions (ACIs) and aerosol–radiation interactions (ARIs) induced by biomass burning (BB) aerosols act oppositely on radiation, cloud, and precipitation in the Amazon during the dry season. The varying relative significance of ACIs and ARIs with BB aerosol concentration leads to a nonlinear dependence of the total climate response on BB aerosol loading and features the growing importance of ARIs at high aerosol loading.
Marc Mallet, Fabien Solmon, Pierre Nabat, Nellie Elguindi, Fabien Waquet, Dominique Bouniol, Andrew Mark Sayer, Kerry Meyer, Romain Roehrig, Martine Michou, Paquita Zuidema, Cyrille Flamant, Jens Redemann, and Paola Formenti
Atmos. Chem. Phys., 20, 13191–13216,Short summary
This paper presents numerical simulations using two regional climate models to study the impact of biomass fire plumes from central Africa on the radiative balance of this region. The results indicate that biomass fires can either warm the regional climate when they are located above low clouds or cool it when they are located above land. They can also alter sea and land surface temperatures by decreasing solar radiation at the surface. Finally, they can also modify the atmospheric dynamics.
Noora Hyttinen, Reyhaneh Heshmatnezhad, Jonas Elm, Theo Kurtén, and Nønne L. Prisle
Atmos. Chem. Phys., 20, 13131–13143,Short summary
We present aqueous solubilities and activity coefficients of mono- and dicarboxylic acids (C1–C6 and C2–C8, respectively) estimated using the COSMOtherm program. In addition, we have calculated effective equilibrium constants of dimerization and hydration of the same acids in the condensed phase. We were also able to improve the agreement between experimental and estimated properties of monocarboxylic acids in aqueous solutions by including clustering reactions in COSMOtherm calculations.
Debbie O'Sullivan, Franco Marenco, Claire L. Ryder, Yaswant Pradhan, Zak Kipling, Ben Johnson, Angela Benedetti, Melissa Brooks, Matthew McGill, John Yorks, and Patrick Selmer
Atmos. Chem. Phys., 20, 12955–12982,Short summary
Mineral dust is an important component of the climate system, and we assess how well it is predicted by two operational models. We flew an aircraft in the dust layers in the eastern Atlantic, and we also make use of satellites. We show that models predict the dust layer too low and that it predicts the particles to be too small. We believe that these discrepancies may be overcome if models can be constrained with operational observations of dust vertical and size-resolved distribution.
Yaping Shao, Jie Zhang, Masahide Ishizuka, Masao Mikami, John Leys, and Ning Huang
Atmos. Chem. Phys., 20, 12939–12953,Short summary
It has been recognized in earlier research that particle size distribution of dust at emission (dust PSD) is dependent on friction velocity. This recognition has been challenged in some recent papers. Based on the analysis of experimental data, we confirm that dust PSD is dependent on friction velocity and atmospheric boundary-layer stability. By theoretical and numerical analysis, we reveal the reasons for this dependency.
Arshad Arjunan Nair and Fangqun Yu
Atmos. Chem. Phys., 20, 12853–12869,Short summary
Small particles in the atmosphere can affect cloud formation and properties and thus Earth's energy budget. These cloud condensation nuclei (CCN) contribute the largest uncertainties in climate change modeling. To reduce these uncertainties, it is important to quantify CCN numbers accurately, measurements of which are sparse. We propose and evaluate a machine learning method to estimate CCN, in the absence of their direct measurements, using more common measurements of weather and air quality.
Ananth Ranjithkumar, Hamish Gordon, Christina Williamson, Andrew Rollins, Kirsty J. Pringle, Agnieszka Kupc, Nathan Luke Abraham, Charles A. Brock, and Kenneth S. Carslaw
Atmos. Chem. Phys. Discuss.,
Revised manuscript accepted for ACPShort summary
The effect aerosols have on climate can be better understood by studying their vertical and spatial distribution throughout the atmosphere. We use observation data from the ATom Campaign and evaluate the vertical profile of aerosol number concentration, Sulphur dioxide and condensation sink using UKESM (UK earth system model). We identify uncertainties in key atmospheric processes that help improve their theoretical representation in global climate models.
Abdul-Wahab, S. A. and Al-Alawi, S. M.: Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks, Environ. Modell. Softw., 17, 219–228, 2002.
Amarasinghe, K., Marino, D. L., and Manic, M: Deep neural networks for energy load forecasting, Proceedings of the 26th IEEE International Symposium on Industrial Electronics, 19–21 June, Scotland, UK, 1483–1488, 2017.
Ayinde, B. O., Inanc, T., and Zurada, J. M.: On Correlation of Features Extracted by Deep Neural Networks, arXiv:1901.10900v1, 2019.
Bengio, Y., Simard, P., and Frasconi, P.: Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Networ., 5, 157–166, 1994.
Berge, E., Huang, H.-C., Chang, J., and Liu, T.-H.: A study of importance of initial conditions for photochemical oxidant modeling, J. Geophys. Res.-Atmos., 106, 1347–1363, 2001.
Carmichael, G. R., Adhikary, B., Kulkarni, S., D'Allura, A., Tang, Y., Streets, D., Zhang, Q., Bond, T. C., Ramanathan, V., Jamroensan, A., and Marrapu, P.: Asian aerosols: Current and year 2030 distributions and implications to human health and regional climate change, Environ. Sci. Technol., 43, 5811–5817, 2009.
Che, Z., Purushotham, S., Cho, K., Sontag, D., and Liu, Y.: Recurrent neural networks for multivariate time series with missing values, Sci. Rep., 8, 6085, https://doi.org/10.1038/s41598-018-24271-9, 2018.
Cho, K., van Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bahdanau, D., and Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation, Proceedings of the 19th Conference on Empirical Methods in Natural Language Processing, 25–29 October, Doha, Qatar, 1724–1734, 2014.
Chung, C. E., Ramanathan, V., Carmichael, G., Kulkarni, S., Tang, Y., Adhikary, B., Leung, L. R., and Qian, Y.: Anthropogenic aerosol radiative forcing in Asia derived from regional models with atmospheric and aerosol data assimilation, Atmos. Chem. Phys., 10, 6007–6024, https://doi.org/10.5194/acp-10-6007-2010, 2010.
Collins, W. D., Rasch, P. J., Eaton, B. E., Khattatov, B. V., Lamarque, J.-F., and Zender, C. S.: Simulating aerosols using a chemical transport model with assimilation of satellite aerosol retrievals: Methodology for INDOEX, J. Geophys. Res., 106, 7313–7336, 2001.
Connor, J. T., Martin, D., and Atlas, L. E.: Recurrent neural networks and robust time series prediction, IEEE Trans. Neural Networ., 5, 240–253, 1994.
Davidson, C. I., Phalen, R. F., and Solomon, P. A.: Airborne particulate matter and human health: A review, Aerosol Sci. Tech., 39, 737–749, 2005.
Dockery, D. W., Schwartz, J., and Spengler, J. D.: Air pollution and daily mortality: associations with particulates and acid aerosols, Environ. Res., 59, 362–373, 1992.
Emmons, L. K., Walters, S., Hess, P. G., Lamarque, J.-F., Pfister, G. G., Fillmore, D., Granier, C., Guenther, A., Kinnison, D., Laepple, T., Orlando, J., Tie, X., Tyndall, G., Wiedinmyer, C., Baughcum, S. L., and Kloster, S.: Description and evaluation of the Model for Ozone and Related chemical Tracers, version 4 (MOZART-4), Geosci. Model Dev., 3, 43–67, https://doi.org/10.5194/gmd-3-43-2010, 2010.
Fan, Y., Qian, Y., Xie, F.-L., and Soong, F. K.: TTS synthesis with bidirectional LSTM based recurrent neural networks, Proceedings of the 15th Annual Conference of the International Speech Communication Association, 14–18 September, Singapore, Singapore, 1964–1968, 2014.
Forster, P., Ramaswamy, V., Artaxo, P., Berntsen, T., Betts, R., Fahey, D. W., Haywood, J., Lean, J., Lowe, D. C., Myhre, G., Nganga, J., Prinn, R., Raga, G., Schulz, M., and Van Dorland, R.: Changes in atmospheric constituents and in radiative forcing, in: Climate change 2007: The physical science basis. Contribution of working group i to the fourth assessment report of the intergovernmental panel on climate change, edited by: Solomon, S., Qin, D., Manning, M., Chen, Z., Marquis, M., Averyt, K. B., Tignor, M., and Miller, H. L., Cambridge University Press, Cambridge, UK and New York, 2007.
Freeman, B. S., Taylor, G., Gharabaghi, B., and Thé, J.: Forecasting air quality time series using deep learning, J. Air Waste Manage., 68, 866–886, 2018.
Guenther, A., Karl, T., Harley, P., Wiedinmyer, C., Palmer, P. I., and Geron, C.: Estimates of global terrestrial isoprene emissions using MEGAN (Model of Emissions of Gases and Aerosols from Nature), Atmos. Chem. Phys., 6, 3181–3210, https://doi.org/10.5194/acp-6-3181-2006, 2006.
Guyon, I.: A scaling law for the validation-set traning-set size ratio, AT&T Bell Laboratories, https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.1337 (last access: 16 October 2019), 1997.
Han, K. M., Lee, C. K., Lee, J., Kim, J., and Song, C. H.: A comparison study between model-predicted and OMI-retrieved tropospheric NO2 columns over the Korean peninsula, Atmos. Environ., 45, 2962–2971, 2011.
Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions, Int. J. Uncertain. Fuzz., 6, 107–116, 1998.
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, 1997.
Holloway, T., Spak, S. N., Barker, D., Bretl, M., Moberg, C., Hayhoe, K., Van Dorn, J., and Wuebbles, D.: Change in ozone air pollution over Chicago associated with global climate change, J. Geophys. Res.-Atmos., 113 D22306, https://doi.org/10.1029/2007JD009775, 2008.
Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., and Brasseur, O.: A neural network forecast for daily average PM10 concentrations in Belgium, Atmos. Environ., 39, 3279–3289, 2005.
Hope III, C. A. and Dockery, D. W.: Health effects of fine particulate air pollution: lines that connect, J. Air Waste Manage., 56, 709–742, 2006.
Kingma, D. and Ba, J.: Adam: A method for stochastic optimization, Proceedings of the 3rd International Conference on Learning Representations, 3–8 May, San Diego, USA, arXiv:1412.6980v9, 2015.
Li, X., Peng, L., Yao, X., Cui, S., Hu, Y., You, C., and Chi, T.: Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation, Environ. Pollut., 231, 997–1004, 2017.
Liu, Y., Franklin, M., Kahn, R., and Koutrakis, P.: Using aerosol optical thickness to predict ground-level PM2.5 concentrations in the St. Louis area: A comparison between MISR and MODIS, Remote Sens. Environ., 107, 33–44, 2007.
Lu, W.-Z. and Wang, W.-J.: Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends, Chemosphere, 59, 693–701, 2005.
Ma, X., Tao, Z., Wang, Y., Yu, H., and Wang, Y.: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data, Transport Res. C Emer., 54, 187–197, 2015.
Mahsereci, M., Ballers, L., Lassner, C., and Henning, P.: Early stopping without a validation set, arXiv:1703.09580, 2017.
Mourdoukoutas, P.: IBM To Buy The Weather Company, Forbes, available at: https://www.forbes.com/ (last access: 13 October 2019), 2015.
Nair, V. and Hinton, G. E.: Rectified linear units improve restricted Boltzmann machines, Proceedings of the 27th International Conference on Machine Learning, 21–24 June, Haifa, Israel, 432, 2010.
Ong, B. T., Sugiura, K., and Zettsu, K.: Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5, Neural Comput. Appl., 26, 1553–1566, 2016.
Park, R. S., Song, C. H., Han, K. M., Park, M. E., Lee, S.-S., Kim, S.-B., and Shimizu, A.: A study on the aerosol optical properties over East Asia using a combination of CMAQ-simulated aerosol optical properties and remote-sensing data via a data assimilation technique, Atmos. Chem. Phys., 11, 12275–12296, https://doi.org/10.5194/acp-11-12275-2011, 2011.
Park, R. S., Lee, S., Shin, S.-K., and Song, C. H.: Contribution of ammonium nitrate to aerosol optical depth and direct radiative forcing by aerosols over East Asia, Atmos. Chem. Phys., 14, 2185–2201, https://doi.org/10.5194/acp-14-2185-2014, 2014a.
Park, M. E., Song, C. H., Park, R. S., Lee, J., Kim, J., Lee, S., Woo, J.-H., Carmichael, G. R., Eck, T. F., Holben, B. N., Lee, S.-S., Song, C. K., and Hong, Y. D.: New approach to monitor transboundary particulate pollution over Northeast Asia, Atmos. Chem. Phys., 14, 659–674, https://doi.org/10.5194/acp-14-659-2014, 2014b.
Reid, C. E., Jerrett, M., Petersen, M. L., Pfister, G. G., Morefield, P. E., Tager, I. B., Raffuse, S. M., and Balmes, J. R.: Spatiotemporal prediction of fine particulate matter during the 2008 Northern California wildfires using machine learning, Environ. Sci. Technol., 49, 3887–3896, 2015.
Saad, E. W., Prokhorov, D. V., and Wunsch, D. C.: Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks, IEEE Trans. Neural Networ., 9, 1456–1470, 1998.
Seaman, N. L.: Meteorological modeling for air-quality assessments, Atmos. Environ., 34, 2231–2259, 2000.
Shin, S. E., Jung, C. H., and Kim, Y. P.: Analysis of the measurement difference for the PM10 concentrations between Beta-ray absorption and gravimetric methods at Gosan, Aerosol Air Qual. Res., 11, 846–853, 2011.
Tang, Y., Lee, P., Tsidulko, M., Huang, H.-C., McQueen, J. T., DiMego, G. J., Emmons, L. K., Pierce, R. B., Thompson, A. M., Lin, H.-M., Kang, D., Tong, D., Yu, S., Mathur, R., Pleim, J. E., Otte, T. L., Pouliot, G., Young, J. O., Schere, K. L., Davidson, P. M., and Stajner, I.: The impact of chemical lateral boundary conditions on CMAQ predictions of tropospheric ozone over the continental United States, Environ. Fluid Mech., 9, 43–58, 2009.
Wang, S. X., Zhao, B., Cai, S. Y., Klimont, Z., Nielsen, C. P., Morikawa, T., Woo, J. H., Kim, Y., Fu, X., Xu, J. Y., Hao, J. M., and He, K. B.: Emission trends and mitigation options for air pollutants in East Asia, Atmos. Chem. Phys., 14, 6571–6603, https://doi.org/10.5194/acp-14-6571-2014, 2014.
Wiedinmyer, C., Akagi, S. K., Yokelson, R. J., Emmons, L. K., Al-Saadi, J. A., Orlando, J. J., and Soja, A. J.: The Fire INventory from NCAR (FINN): a high resolution global model to estimate the emissions from open burning, Geosci. Model Dev., 4, 625–641, https://doi.org/10.5194/gmd-4-625-2011, 2011.
Woo, J.-H., Kim, Y., Park, R., Choi, Y., Simpson, I. J., Emmons, L. K., and Streets, D. G.: Understanding emissions in East Asia – The KORUS 2015 emissions inventory, Proceedings of the American Geophysical Union Fall Meeting, 11–15 December, New Oreleans, USA, A11Q-04, 2017.
Yi, J. and Prybutok, R.: A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area, Environ. Pollut., 92 , 349–357, 1996.
Yu, H., Dickinson, R. E., Chin, M., Kaufman, Y. J., Holben, B. N., Geogdzhayev, I. V., and Mishchenko, M. I.: Annual cycle of global distributions of aerosol optical depth from integration of MODIS retrievals and GOCART model simulations, J. Geophys. Res., 108, 4128, https://doi.org/10.1029/2002JD002717, 2003.
In this study, a deep recurrent neural network system based on a long short-term memory (LSTM) model was developed for daily PM10 and PM2.5 predictions in South Korea. In general, the accuracies of the LSTM-based predictions were superior to the 3-D CTM-based predictions. Based on this, we concluded that the LSTM-based system could be applied to daily operational PM forecasts in South Korea. We expect that similar AI systems can be applied to the predictions of other atmospheric pollutants.
In this study, a deep recurrent neural network system based on a long short-term memory (LSTM)...