Articles | Volume 14, issue 7
https://doi.org/10.5194/gmd-14-4641-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-14-4641-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
28 Jul 2021
Model description paper |
| 28 Jul 2021
| 28 Jul 2021
Exploring deep learning for air pollutant emission estimation
Lin Huang
Microsoft Research Lab – Asia, Beijing, China
Song Liu
State Key Joint Laboratory of Environmental Simulation and Pollution
Control, School of Environment, Tsinghua University, Beijing, China
State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex, Beijing, China
Zeyuan Yang
School of Economics and Management, Tsinghua University, Beijing,
China
Jia Xing
CORRESPONDING AUTHOR
State Key Joint Laboratory of Environmental Simulation and Pollution
Control, School of Environment, Tsinghua University, Beijing, China
State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex, Beijing, China
Jia Zhang
CORRESPONDING AUTHOR
Microsoft Research Lab – Asia, Beijing, China
Jiang Bian
Microsoft Research Lab – Asia, Beijing, China
Siwei Li
School of Remote Sensing and Information Engineering, Wuhan
University, Wuhan, China
State Key Laboratory of Information Engineering in Surveying, Mapping
and Remote Sensing, Wuhan University, Wuhan, China
Shovan Kumar Sahu
State Key Joint Laboratory of Environmental Simulation and Pollution
Control, School of Environment, Tsinghua University, Beijing, China
State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex, Beijing, China
Shuxiao Wang
State Key Joint Laboratory of Environmental Simulation and Pollution
Control, School of Environment, Tsinghua University, Beijing, China
State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex, Beijing, China
Tie-Yan Liu
Microsoft Research Lab – Asia, Beijing, China
Related authors
No articles found.
Weijie Zou, Zhenping Yin, Tingxin Sun, Zhichao Bu, Yaru Dai, Haofei Wang, Longlong Wang, Yun He, Shuangliang Li, Jiarui Cheng, Xuan Wang, Siwei Li, and Detlef Müller
EGUsphere, https://doi.org/10.5194/egusphere-2026-3036, https://doi.org/10.5194/egusphere-2026-3036, 2026
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
Short summary
Cloud layers can be identified from ground-based laser observations, but stable and consistent results across different instruments and sites remain challenging. This study develops a transferable artificial intelligence method using multi-wavelength lidar signals. It improves cloud boundary detection, works with limited expert labels, and is tested at independent sites with weather balloon checks. It supports reliable automated cloud and aerosol processing.
Jinchun Yi, Yiyang Huang, Ge Han, Hongyuan Zhang, Zhipeng Pei, Haotian Luo, Yichi Zhang, Tianqi Shi, Siwei Li, and Wei Gong
Atmos. Chem. Phys., 26, 8475–8504, https://doi.org/10.5194/acp-26-8475-2026, https://doi.org/10.5194/acp-26-8475-2026, 2026
Short summary
Short summary
This study presents a new way to estimate human-caused carbon dioxide emissions from cities using satellite observations. It combines measurements of nitrogen dioxide and carbon dioxide to better track emissions from urban areas. By applying this approach to several major cities with different environments, the study shows that combining multiple satellite observations can reduce uncertainty and provide more reliable city-level emission estimates.
Shuling Xu, Yang Liu, Sha Yu, Weidong Jia, Yongye Jiang, Yuqin Li, Zeyuan Liu, Andy Miller, Jianxiang Shen, Jingyang Song, Can Wang, Huaxuan Wang, Rui Wang, Fan Wu, Hongzhi Zhang, Mengting Zhu, Rongqi Zhu, Jenna Behrendt, Matthew Binsted, Jing Cheng, Robert Dahowski, Casie Davidson, Shiyu Deng, Jay Fuhrman, Matthew Gidden, Chaoyi Guo, Jill Horing, Hanwoong Kim, Chaojun Li, Bo Liu, Xunzhang Pan, Pralit Patel, Meiyin Qian, Yang Qiu, Tianming Shao, Yisheng Sun, Lining Wang, Yuyao Yang, Brinda Yarlagadda, Zihua Yin, Jian Zang, Qianzhi Zhang, Wenjia Cai, Wenying Chen, Leon Clarke, Ryna Cui, Nathan Hultman, Bengang Li, Jiashuo Li, Xi Lu, Haewon McJeon, Bo Wang, Can Wang, Peng Wang, Shuxiao Wang, Zhaohua Wang, Lixiao Zhang, Qiang Zhang, and Yang Ou
EGUsphere, https://doi.org/10.5194/egusphere-2026-1919, https://doi.org/10.5194/egusphere-2026-1919, 2026
Short summary
Short summary
This study introduces a new open-source model GCAM-China-v8, developed by the community to better understand China’s energy and emissions at both national and provincial levels. The model links detailed regional systems with global trends, allowing users to explore how economic growth, technology, and policy choices shape future pathways. It provides a transparent and flexible tool to support research and decision making on energy and climate issues.
Hua Zhang, Shuxiao Wang, Xi Zhao, Zhijun Wu, Yan Yin, Siyu Chen, Dantong Liu, Jingchuan Chen, Hui Jiang, Jiewen Shen, Da Gao, Dejia Yin, Yicong He, Zeqi Li, Shengyue Li, Zhaoxin Dong, Manish Shrivastava, and Bin Zhao
EGUsphere, https://doi.org/10.5194/egusphere-2025-5277, https://doi.org/10.5194/egusphere-2025-5277, 2025
Short summary
Short summary
Mineral dust can initiate ice formation in clouds, affecting cloud properties and regional climate. Using an improved model, we examined their contrasting impacts in mixed-phase and ice clouds over East Asia. In mixed-phase clouds, dust promotes liquid-to-ice conversion and reduces cloud reflectivity, causing moderate warming, whereas in ice clouds, it greatly enhances ice formation and leads to stronger warming. This study advances understanding of aerosol–cloud–climate interactions.
Zeqi Li, Bin Zhao, Shengyue Li, Zhezhe Shi, Dejia Yin, Qingru Wu, Fenfen Zhang, Xiao Yun, Guanghan Huang, Yun Zhu, and Shuxiao Wang
Earth Syst. Sci. Data, 17, 5113–5135, https://doi.org/10.5194/essd-17-5113-2025, https://doi.org/10.5194/essd-17-5113-2025, 2025
Short summary
Short summary
This study uses an ensemble machine learning model to predict long-term, high-resolution cooking activity data, establishing China’s first county-level cooking emission inventory spanning 1990–2021. It covers key pollutants such as polycyclic aromatic hydrocarbons. It reveals emissions’ long-term spatiotemporal trends and driving factors, such as population migration and economic growth, offering efficient control strategies. This dataset is crucial for air pollution and health impact studies.
Yuying Cui, Qingru Wu, Shuxiao Wang, Kaiyun Liu, Shengyue Li, Zhezhe Shi, Daiwei Ouyang, Zhongyan Li, Qinqin Chen, Changwei Lü, Fei Xie, Yi Tang, Yan Wang, and Jiming Hao
Earth Syst. Sci. Data, 17, 3315–3328, https://doi.org/10.5194/essd-17-3315-2025, https://doi.org/10.5194/essd-17-3315-2025, 2025
Short summary
Short summary
We develop P-CAME, a long-term gridded emission inventory for China spanning from 1978 to 2021. P-CAME enhances the accuracy of emissions mapping, identifies potential pollution hotspots, and aligns with observed Hg0 concentration trends. With its improved spatial resolution and reliable long-term trends, P-CAME offers valuable support for global emissions modeling, legacy impact studies, and evaluations of the Minamata Convention.
Ashu Dastoor, Hélène Angot, Johannes Bieser, Flora Brocza, Brock Edwards, Aryeh Feinberg, Xinbin Feng, Benjamin Geyman, Charikleia Gournia, Yipeng He, Ian M. Hedgecock, Ilia Ilyin, Jane Kirk, Che-Jen Lin, Igor Lehnherr, Robert Mason, David McLagan, Marilena Muntean, Peter Rafaj, Eric M. Roy, Andrei Ryjkov, Noelle E. Selin, Francesco De Simone, Anne L. Soerensen, Frits Steenhuisen, Oleg Travnikov, Shuxiao Wang, Xun Wang, Simon Wilson, Rosa Wu, Qingru Wu, Yanxu Zhang, Jun Zhou, Wei Zhu, and Scott Zolkos
Geosci. Model Dev., 18, 2747–2860, https://doi.org/10.5194/gmd-18-2747-2025, https://doi.org/10.5194/gmd-18-2747-2025, 2025
Short summary
Short summary
This paper introduces the Multi-Compartment Mercury (Hg) Modeling and Analysis Project (MCHgMAP) aimed at informing the effectiveness evaluations of two multilateral environmental agreements: the Minamata Convention on Mercury and the Convention on Long-Range Transboundary Air Pollution. The experimental design exploits a variety of models (atmospheric, land, oceanic ,and multimedia mass balance models) to assess the short- and long-term influences of anthropogenic Hg releases into the environment.
Yuzhi Jin, Jiandong Wang, Chao Liu, David C. Wong, Golam Sarwar, Kathleen M. Fahey, Shang Wu, Jiaping Wang, Jing Cai, Zeyuan Tian, Zhouyang Zhang, Jia Xing, Aijun Ding, and Shuxiao Wang
Atmos. Chem. Phys., 25, 2613–2630, https://doi.org/10.5194/acp-25-2613-2025, https://doi.org/10.5194/acp-25-2613-2025, 2025
Short summary
Short summary
Black carbon (BC) affects climate and the environment, and its aging process alters its properties. Current models, like WRF-CMAQ, lack full accounting for it. We developed the WRF-CMAQ-BCG model to better represent BC aging by introducing bare and coated BC species and their conversion. The WRF-CMAQ-BCG model introduces the capability to simulate BC mixing states and bare and coated BC wet deposition, and it improves the accuracy of BC mass concentration and aerosol optics.
Zhouyang Zhang, Jiandong Wang, Jiaping Wang, Nicole Riemer, Chao Liu, Yuzhi Jin, Zeyuan Tian, Jing Cai, Yueyue Cheng, Ganzhen Chen, Bin Wang, Shuxiao Wang, and Aijun Ding
Atmos. Chem. Phys., 25, 1869–1881, https://doi.org/10.5194/acp-25-1869-2025, https://doi.org/10.5194/acp-25-1869-2025, 2025
Short summary
Short summary
Black carbon (BC) exerts notable warming effects. We use a particle-resolved model to investigate the long-term behavior of the BC mixing state, revealing its compositions, coating thickness distribution, and optical properties all stabilize with a characteristic time of less than 1 d. This study can effectively simplify the description of the BC mixing state, which facilitates the precise assessment of the optical properties of BC aerosols in global and chemical transport models.
Jiewen Shen, Bin Zhao, Shuxiao Wang, An Ning, Yuyang Li, Runlong Cai, Da Gao, Biwu Chu, Yang Gao, Manish Shrivastava, Jingkun Jiang, Xiuhui Zhang, and Hong He
Atmos. Chem. Phys., 24, 10261–10278, https://doi.org/10.5194/acp-24-10261-2024, https://doi.org/10.5194/acp-24-10261-2024, 2024
Short summary
Short summary
We extensively compare various cluster-dynamics-based parameterizations for sulfuric acid–dimethylamine nucleation and identify a newly developed parameterization derived from Atmospheric Cluster Dynamic Code (ACDC) simulations as being the most reliable one. This study offers a valuable reference for developing parameterizations of other nucleation systems and is meaningful for the accurate quantification of the environmental and climate impacts of new particle formation.
Siwei Li, Yu Ding, Jia Xing, and Joshua S. Fu
Earth Syst. Sci. Data, 16, 3781–3793, https://doi.org/10.5194/essd-16-3781-2024, https://doi.org/10.5194/essd-16-3781-2024, 2024
Short summary
Short summary
Surface PM2.5 data have gained widespread application in health assessments and related fields, while the inherent uncertainties in PM2.5 data persist due to the lack of ground-truth data across the space. This study provides a novel testbed, enabling comprehensive evaluation across the entire spatial domain. The optimized deep-learning model with spatiotemporal features successfully retrieved surface PM2.5 concentrations in China (2013–2021), with reduced biases induced by sample imbalance.
Da Gao, Bin Zhao, Shuxiao Wang, Yuan Wang, Brian Gaudet, Yun Zhu, Xiaochun Wang, Jiewen Shen, Shengyue Li, Yicong He, Dejia Yin, and Zhaoxin Dong
Atmos. Chem. Phys., 23, 14359–14373, https://doi.org/10.5194/acp-23-14359-2023, https://doi.org/10.5194/acp-23-14359-2023, 2023
Short summary
Short summary
Surface PM2.5 concentrations can be enhanced by aerosol–radiation interactions (ARIs) and aerosol–cloud interactions (ACIs). In this study, we found PM2.5 enhancement induced by ACIs shows a significantly smaller decrease ratio than that induced by ARIs in China with anthropogenic emission reduction from 2013 to 2021, making ACIs more important for enhancing PM2.5 concentrations. ACI-induced PM2.5 enhancement needs to be emphatically considered to meet the national PM2.5 air quality standard.
Zeqi Li, Shuxiao Wang, Shengyue Li, Xiaochun Wang, Guanghan Huang, Xing Chang, Lyuyin Huang, Chengrui Liang, Yun Zhu, Haotian Zheng, Qian Song, Qingru Wu, Fenfen Zhang, and Bin Zhao
Earth Syst. Sci. Data, 15, 5017–5037, https://doi.org/10.5194/essd-15-5017-2023, https://doi.org/10.5194/essd-15-5017-2023, 2023
Short summary
Short summary
This study developed the first full-volatility organic emission inventory for cooking sources in China, presenting high-resolution cooking emissions during 2015–2021. It identified the key subsectors and hotspots of cooking emissions, analyzed emission trends and drivers, and proposed future control strategies. The dataset is valuable for accurately simulating organic aerosol formation and evolution and for understanding the impact of organic emissions on air pollution and climate change.
Chupeng Zhang, Shangfei Hai, Yang Gao, Yuhang Wang, Shaoqing Zhang, Lifang Sheng, Bin Zhao, Shuxiao Wang, Jingkun Jiang, Xin Huang, Xiaojing Shen, Junying Sun, Aura Lupascu, Manish Shrivastava, Jerome D. Fast, Wenxuan Cheng, Xiuwen Guo, Ming Chu, Nan Ma, Juan Hong, Qiaoqiao Wang, Xiaohong Yao, and Huiwang Gao
Atmos. Chem. Phys., 23, 10713–10730, https://doi.org/10.5194/acp-23-10713-2023, https://doi.org/10.5194/acp-23-10713-2023, 2023
Short summary
Short summary
New particle formation is an important source of atmospheric particles, exerting critical influences on global climate. Numerical models are vital tools to understanding atmospheric particle evolution, which, however, suffer from large biases in simulating particle numbers. Here we improve the model chemical processes governing particle sizes and compositions. The improved model reveals substantial contributions of newly formed particles to climate through effects on cloud condensation nuclei.
Yuyang Li, Jiewen Shen, Bin Zhao, Runlong Cai, Shuxiao Wang, Yang Gao, Manish Shrivastava, Da Gao, Jun Zheng, Markku Kulmala, and Jingkun Jiang
Atmos. Chem. Phys., 23, 8789–8804, https://doi.org/10.5194/acp-23-8789-2023, https://doi.org/10.5194/acp-23-8789-2023, 2023
Short summary
Short summary
We set up a new parameterization for 1.4 nm particle formation rates from sulfuric acid–dimethylamine (SA–DMA) nucleation, fully including the effects of coagulation scavenging and cluster stability. Incorporating the new parameterization into 3-D chemical transport models, we achieved better consistencies between simulation results and observation data. This new parameterization provides new insights into atmospheric nucleation simulations and its effects on atmospheric pollution or health.
Shengyue Li, Shuxiao Wang, Qingru Wu, Yanning Zhang, Daiwei Ouyang, Haotian Zheng, Licong Han, Xionghui Qiu, Yifan Wen, Min Liu, Yueqi Jiang, Dejia Yin, Kaiyun Liu, Bin Zhao, Shaojun Zhang, Ye Wu, and Jiming Hao
Earth Syst. Sci. Data, 15, 2279–2294, https://doi.org/10.5194/essd-15-2279-2023, https://doi.org/10.5194/essd-15-2279-2023, 2023
Short summary
Short summary
This study compiled China's emission inventory of air pollutants and CO2 during 2005–2021 (ABaCAS-EI v2.0) based on unified emission-source framework. The emission trends and its drivers are analyzed. Key sectors and regions with higher synergistic reduction potential of air pollutants and CO2 are identified. Future control measures are suggested. The dataset and analyses provide insights into the synergistic reduction of air pollutants and CO2 emissions for China and other developing countries.
Shixian Zhai, Daniel J. Jacob, Drew C. Pendergrass, Nadia K. Colombi, Viral Shah, Laura Hyesung Yang, Qiang Zhang, Shuxiao Wang, Hwajin Kim, Yele Sun, Jin-Soo Choi, Jin-Soo Park, Gan Luo, Fangqun Yu, Jung-Hun Woo, Younha Kim, Jack E. Dibb, Taehyoung Lee, Jin-Seok Han, Bruce E. Anderson, Ke Li, and Hong Liao
Atmos. Chem. Phys., 23, 4271–4281, https://doi.org/10.5194/acp-23-4271-2023, https://doi.org/10.5194/acp-23-4271-2023, 2023
Short summary
Short summary
Anthropogenic fugitive dust in East Asia not only causes severe coarse particulate matter air pollution problems, but also affects fine particulate nitrate. Due to emission control efforts, coarse PM decreased steadily. We find that the decrease of coarse PM is a major driver for a lack of decrease of fine particulate nitrate, as it allows more nitric acid to form fine particulate nitrate. The continuing decrease of coarse PM requires more stringent ammonia and nitrogen oxides emission controls.
Xiao He, Xuan Zheng, Shaojun Zhang, Xuan Wang, Ting Chen, Xiao Zhang, Guanghan Huang, Yihuan Cao, Liqiang He, Xubing Cao, Yuan Cheng, Shuxiao Wang, and Ye Wu
Atmos. Chem. Phys., 22, 13935–13947, https://doi.org/10.5194/acp-22-13935-2022, https://doi.org/10.5194/acp-22-13935-2022, 2022
Short summary
Short summary
With the use of two-dimensional gas chromatography time-of-flight mass spectrometry (GC × GC ToF-MS), we successfully give a comprehensive characterization of particulate intermediate-volatility and semi-volatile organic compounds (I/SVOCs) emitted from heavy-duty diesel vehicles. I/SVOCs are speciated, identified, and quantified based on the patterns of the mass spectrum, and the gas–particle partitioning is fully addressed.
Yi Cheng, Shaofei Kong, Liquan Yao, Huang Zheng, Jian Wu, Qin Yan, Shurui Zheng, Yao Hu, Zhenzhen Niu, Yingying Yan, Zhenxing Shen, Guofeng Shen, Dantong Liu, Shuxiao Wang, and Shihua Qi
Earth Syst. Sci. Data, 14, 4757–4775, https://doi.org/10.5194/essd-14-4757-2022, https://doi.org/10.5194/essd-14-4757-2022, 2022
Short summary
Short summary
This work establishes the first emission inventory of carbonaceous aerosols from cooking, fireworks, sacrificial incense, joss paper burning, and barbecue, using multi-source datasets and tested emission factors. These emissions were concentrated in specific periods and areas. Positive and negative correlations between income and emissions were revealed in urban and rural regions. The dataset will be helpful for improving modeling studies and modifying corresponding emission control policies.
Lulu Cui, Di Wu, Shuxiao Wang, Qingcheng Xu, Ruolan Hu, and Jiming Hao
Atmos. Chem. Phys., 22, 11931–11944, https://doi.org/10.5194/acp-22-11931-2022, https://doi.org/10.5194/acp-22-11931-2022, 2022
Short summary
Short summary
A 1-year campaign was conducted to characterize VOCs at a Beijing urban site during different episodes. VOCs from fuel evaporation and diesel exhaust, particularly toluene, xylenes, trans-2-butene, acrolein, methyl methacrylate, vinyl acetate, 1-butene, and 1-hexene, were the main contributors. VOCs from diesel exhaust as well as coal and biomass combustion were found to be the dominant contributors for SOAFP, particularly the VOC species toluene, 1-hexene, xylenes, ethylbenzene, and styrene.
Mengying Li, Shaocai Yu, Xue Chen, Zhen Li, Yibo Zhang, Zhe Song, Weiping Liu, Pengfei Li, Xiaoye Zhang, Meigen Zhang, Yele Sun, Zirui Liu, Caiping Sun, Jingkun Jiang, Shuxiao Wang, Benjamin N. Murphy, Kiran Alapaty, Rohit Mathur, Daniel Rosenfeld, and John H. Seinfeld
Atmos. Chem. Phys., 22, 11845–11866, https://doi.org/10.5194/acp-22-11845-2022, https://doi.org/10.5194/acp-22-11845-2022, 2022
Short summary
Short summary
This study constructed an emission inventory of condensable particulate matter (CPM) in China with a focus on organic aerosols (OAs), based on collected CPM emission information. The results show that OA emissions are enhanced twofold for the years 2014 and 2017 after the inclusion of CPM in the new inventory. Sensitivity cases demonstrated the significant contributions of CPM emissions from stationary combustion and mobile sources to primary, secondary, and total OA concentrations.
Shansi Wang, Siwei Li, Jia Xing, Yu Ding, Senlin Hu, Shuchang Liu, Yu Qin, Zhaoxin Dong, Jiaxin Dong, Ge Song, and Lechao Dong
Atmos. Chem. Phys. Discuss., https://doi.org/10.5194/acp-2022-368, https://doi.org/10.5194/acp-2022-368, 2022
Preprint withdrawn
Short summary
Short summary
Future warming meteorological conditions may enhance the influence of regional transport on PM2.5 pollution. Our results prove that climate-friendly policy could lead to considerable co-benefits in mitigating the regional transport of PM2.5 in future. Meanwhile, climate change will exert larger impacts on across-regional (long-distance) transport than inner (neighboring provinces) regional transport, highlighting the significance of multi-regional cooperation in the future.
Jiandong Wang, Jia Xing, Shuxiao Wang, Rohit Mathur, Jiaping Wang, Yuqiang Zhang, Chao Liu, Jonathan Pleim, Dian Ding, Xing Chang, Jingkun Jiang, Peng Zhao, Shovan Kumar Sahu, Yuzhi Jin, David C. Wong, and Jiming Hao
Atmos. Chem. Phys., 22, 5147–5156, https://doi.org/10.5194/acp-22-5147-2022, https://doi.org/10.5194/acp-22-5147-2022, 2022
Short summary
Short summary
Aerosols reduce surface solar radiation and change the photolysis rate and planetary boundary layer stability. In this study, the online coupled meteorological and chemistry model was used to explore the detailed pathway of how aerosol direct effects affect secondary inorganic aerosol. The effects through the dynamics pathway act as an equally or even more important route compared with the photolysis pathway in affecting secondary aerosol concentration in both summer and winter.
Yuqiang Zhang, Drew Shindell, Karl Seltzer, Lu Shen, Jean-Francois Lamarque, Qiang Zhang, Bo Zheng, Jia Xing, Zhe Jiang, and Lei Zhang
Atmos. Chem. Phys., 21, 16051–16065, https://doi.org/10.5194/acp-21-16051-2021, https://doi.org/10.5194/acp-21-16051-2021, 2021
Short summary
Short summary
In this study, we use a global chemical transport model to simulate the effects on global air quality and human health due to emission changes in China from 2010 to 2017. By performing sensitivity analysis, we found that the air pollution control policies not only decrease the air pollutant concentration but also bring significant co-benefits in air quality to downwind regions. The benefits for the improved air pollution are dominated by PM2.5.
Shuping Zhang, Golam Sarwar, Jia Xing, Biwu Chu, Chaoyang Xue, Arunachalam Sarav, Dian Ding, Haotian Zheng, Yujing Mu, Fengkui Duan, Tao Ma, and Hong He
Atmos. Chem. Phys., 21, 15809–15826, https://doi.org/10.5194/acp-21-15809-2021, https://doi.org/10.5194/acp-21-15809-2021, 2021
Short summary
Short summary
Six heterogeneous HONO chemistry updates in CMAQ significantly improve HONO concentration. HONO production is primarily controlled by the heterogeneous reactions on ground and aerosol surfaces during haze. Additional HONO chemistry updates increase OH and production of secondary aerosols: sulfate, nitrate, and SOA.
Cited articles
Aardenne, J. V. and Pulles, T.: Uncertainty in emission inventories: What
do we mean and how could we assess it?, Thesis Wageningen University, 2002.
Appel, K. W., Pouliot, G. A., Simon, H., Sarwar, G., Pye, H. O. T., Napelenok, S. L., Akhtar, F., and Roselle, S. J.: Evaluation of dust and trace metal estimates from the Community Multiscale Air Quality (CMAQ) model version 5.0, Geosci. Model Dev., 6, 883–899, https://doi.org/10.5194/gmd-6-883-2013, 2013.
Appel, K. W., Napelenok, S., Hogrefe, C., Pouliot, G., Foley, K. M.,
Roselle, S. J., Pleim, J. E., Bash, J., Pye, H. O. T., and Heath, N.:
Overview and Evaluation of the Community Multiscale Air Quality (CMAQ)
Modeling System Version 5.2, in: Air Pollution
Modeling and its Application XXV, edited by: Mensink, C. and Kallos, G., ITM 2016, Springer Proceedings in Complexity, Springer, Cham, 69–73, https://doi.org/10.1007/978-3-319-57645-9_11,
2018.
Bottou, L.: Large-Scale Machine Learning with Stochastic Gradient Descent,
Physica-Verlag HD, 2010.
Brioude, J., Angevine, W. M., Ahmadov, R., Kim, S.-W., Evan, S., McKeen, S. A., Hsie, E.-Y., Frost, G. J., Neuman, J. A., Pollack, I. B., Peischl, J., Ryerson, T. B., Holloway, J., Brown, S. S., Nowak, J. B., Roberts, J. M., Wofsy, S. C., Santoni, G. W., Oda, T., and Trainer, M.: Top-down estimate of surface flux in the Los Angeles Basin using a mesoscale inverse modeling technique: assessing anthropogenic emissions of CO, NOx and CO2 and their impacts, Atmos. Chem. Phys., 13, 3661–3677, https://doi.org/10.5194/acp-13-3661-2013, 2013.
Byun, D.: Science algorithms of the EPA Models-3 community multiscale air
quality (CMAQ) modeling system, U.S. Environmental Protection Agency, EPA/600/R-99/030, 1999.
Cho, K., Merrienboer, B. V., Bahdanau, D., and Bengio, Y.: On the Properties
of Neural Machine Translation: Encoder-Decoder Approaches, arXiv [preprint],
arXiv:1409.1259, 2014.
Chung, J., Gulcehre, C., Cho, K., and Bengio, Y.: Empirical Evaluation of
Gated Recurrent Neural Networks on Sequence Modeling, arXiv [preprint],
arXiv:1412.3555, 2014.
Ding, D., Xing, J., Wang, S., Liu, K., and Hao, J.: Estimated contributions
of emissions controls, meteorological factors, population growth, and
changes in baseline mortality to reductions in ambient PM2.5 and
PM2.5-related mortality in China, 2013–2017, Environ. Health
Persp., 127, 067009, https://doi.org/10.1289/EHP4157, 2019.
Ding, D., Yun, Z., Jang, C., Lin, C. J., Wang, S., Fu, J., and Jian, G.:
Evaluation of health benefit using BenMAP-CE with an integrated scheme of
model and monitor data during Guangzhou Asian Games, J. Environ., 42, 9–18,
2016.
Fan, J., Li, Q., Hou, J., Feng, X., Karimian, H., and Lin, S.: A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4/W2, 15–22, https://doi.org/10.5194/isprs-annals-IV-4-W2-15-2017, 2017.
Friedl, M. A., Mciver, D. K., Hodges, J. C. F., Zhang, X. Y., Muchoney, D.,
Strahler, A. H., Woodcock, C. E., Gopal, S., Schneider, A., and Cooper, A.:
Global land cover mapping from MODIS: algorithms and early results, Remote
Sens. Environ., 83, 287–302, 2002.
Ghil, M. and Malanotte-Rizzoli, P.: Data Assimilation in Meteorology and
Oceanography, Adv. Geophys., 33, 141–266, 1991.
Guo, S., Hu, M., Zamora, M. L., Peng, J., and Zhang, R.: Elucidating severe
urban haze formation in China, P. Natl. Acad.
Sci. USA, 111, 17373, https://doi.org/10.1073/pnas.1419604111, 2014.
He, D., Xia, Y., Qin, T., Wang, L., Yu, N., Liu, T.-Y., and Ma, W.-Y.: Dual
learning for machine translation, Proceedings of the 30th International
Conference on Neural Information Processing Systems, Barcelona, Spain,
820–828, 2016.
He, K.: Multi-resolution Emission Inventory for China (MEIC): model
framework and 1990–2010 anthropogenic emissions, American Geophysical Union, Fall Meeting, A32B-05, 2012.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image
Recognition, arXiv [preprint], arXiv:1512.03385, 2015a.
He, K., Zhang, X., Ren, S., and Sun, J.: Delving Deep into Rectifiers:
Surpassing Human-Level Performance on ImageNet Classification, arXiv [preprint], arXiv:1502.01852, 2015b.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural
Comput., 9, 1735–1780, 1997.
Huang, G., Liu, Z., Laurens, V. D. M., and Weinberger, K. Q.: Densely
Connected Convolutional Networks, arXiv [preprint], arXiv:1608.06993, 2016.
Huang, L., Liu, S., Yang, Z., Xing, J., Zhang, J., Bian, J., Li, S., Sahu,
S. K., Wang, S., and Liu, T.-Y.: The Inventory Optimization Code for
Exploring Deep Learning in Air Pollutant Emission Estimation Scale, Zenodo, https://doi.org/10.5281/zenodo.4607127, 2021.
Health Effects Institute: State of global air 2019, Health Effects Institute, Boston, 2019.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network
Training by Reducing Internal Covariate Shift, arXiv [preprint], arXiv:1502.03167, 2015.
Kain, J. S.: The Kain–Fritsch convective parameterization: an update,
J. Appl. Meteorol., 43, 170–181, 2004.
Kingma, D. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv [preprint], arXiv:1412.6980, 2014.
Krizhevsky, A., Sutskever, I., and Hinton, G.: ImageNet Classification with
Deep Convolutional Neural Networks, Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, December 2012, 1097–1105, 2012.
Li, G.: Report on the completion of environmental conditions and
environmental protection targets for 2018, The National People's Congress, available at: http://wx.h2o-china.com/news/290686.html (last access: 26 June 2021), 2019 (in Chinese).
Liu, S., Xing, J., Westervelt, D. M., Liu, S., Ding, D., Fiore, A. M.,
Kinney, P. L., Zhang, Y., He, M. Z., and Zhang, H.: Role of emission
controls in reducing the 2050 climate change penalty for PM2.5 in China,
Sci. Total Environ., 765, 144338, https://doi.org/10.1016/j.scitotenv.2020.144338, 2020.
Liu, S., Xing, J., Zhang, H., Ding, D., Zhang, F., Zhao, B., Sahu, S. K.,
and Wang, S.: Climate-driven trends of biogenic volatile organic compound
emissions and their impacts on summertime ozone and secondary organic
aerosol in China in the 2050s, Atmos. Environ., 218, 117020, https://doi.org/10.1016/j.atmosenv.2019.117020, 2019.
Mlawer, E., Clough, S., and Kato, S.: Shortwave clear-sky model measurement
intercomparison using RRTM, in: Proceedings of the Eighth ARM Science Team Meeting, 23–27, 1998.
Mlawer, E. J., Taubman, S. J., Brown, P. D., Iacono, M. J., and Clough, S.
A.: Radiative transfer for inhomogeneous atmospheres: RRTM, a validated
correlated-k model for the longwave, J. Geophys. Res.-Atmos., 102, 16663–16682, 1997.
Morrison, H., Thompson, G., and Tatarskii, V.: Impact of cloud microphysics
on the development of trailing stratiform precipitation in a simulated
squall line: Comparison of one-and two-moment schemes, Mon. Weather
Rev., 137, 991–1007, 2009.
Pleim, J. E.: A combined local and nonlocal closure model for the
atmospheric boundary layer. Part I: Model description and testing, J. Appl. Meteorol. Climatol., 46, 1383–1395, 2007.
Pleim, J. E. and Xiu, A.: Development and testing of a surface flux and
planetary boundary layer model for application in mesoscale models, J. Appl. Meteorol., 34, 16–32, 1995.
Richter, A., Burrows, J. P., Nüss, H., Granier, C., and Niemeier, U.:
Increase in nitrogen dioxide over China observed from space, Nature,
437, 129–132, 2005.
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks
for Biomedical Image Segmentation, arXiv [preprint], arXiv:1505.04597, 2015.
Sarwar, G., Luecken, D., Yarwood, G., Whitten, G. Z., and Carter, W. P. L.:
Impact of an Updated Carbon Bond Mechanism on Predictions from the CMAQ
Modeling System: Preliminary Assessment, J. Appl. Meteorol.
Climatol., 47, 3–14, 2008.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and
Salakhutdinov, R.: Dropout: A Simple Way to Prevent Neural Networks from
Overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014.
Tao, Q., Liu, F., Li, Y., and Sidorov, D.: Air Pollution Forecasting Using a
Deep Learning Model Based on 1D Convnets and Bidirectional GRU, IEEE Access,
7, 76690–76698, 2019.
US EPA Office of Research and Development: CMAQ (Version 5.2), Zenodo, https://doi.org/10.5281/zenodo.1167892, 2017.
Vallero, D.: Translating Diverse Environmental Data into Reliable
Information, Elsevier Reference Monographs, 25–41, 2017.
Vesilind, P. A., Peirce, J. J., and Weiner, R. F.: Air
Pollution, chap. 18, Elsevier Inc., 1988.
Wen, C., Liu, S., Yao, X., Peng, L., Li, X., Hu, Y., and Chi, T.: A novel
spatiotemporal convolutional long short-term neural network for air
pollution prediction, Sci. Total Environ., 654, 1091–1099,
2019.
Wikle, C. K.: Atmospheric modeling, data assimilation, and predictability,
Technometrics, 47, 521, https://doi.org/10.1198/tech.2005.s326, 2003.
Xing, J., Li, S., Ding, D., Kelly, J. T., and Hao, J.: Data Assimilation of
Ambient Concentrations of Multiple Air Pollutants Using an
Emission-Concentration Response Modeling Framework, Atmosphere, 11, 1289, https://doi.org/10.3390/atmos11121289, 2020a.
Xing, J., Li, S., Jiang, Y., Wang, S., Ding, D., Dong, Z., Zhu, Y., and Hao, J.: Quantifying the emission changes and associated air quality impacts during the COVID-19 pandemic on the North China Plain: a response modeling study, Atmos. Chem. Phys., 20, 14347–14359, https://doi.org/10.5194/acp-20-14347-2020, 2020b.
Xing, J., Zheng, S., Ding, D., Kelly, J. T., Wang, S., Li, S., Qin, T., Ma,
M., Dong, Z., Jang, C., Zhu, Y., Zheng, H., Ren, L., Liu, T.-Y., and Hao,
J.: Deep Learning for Prediction of the Air Quality Response to Emission
Changes, Environ. Sci. Technol., 54, 8589–8600, 2020c.
Xiu, A. and Pleim, J. E.: Development of a land surface model. Part I:
Application in a mesoscale meteorological model, J. Appl.
Meteorol., 40, 192–209, 2001.
Yang, X., Pang, J., Teng, F., Gong, R., and Springer, C.: The environmental
co-benefit and economic impact of China's low-carbon pathways: Evidence from
linking bottom-up and top-down models, Renew. Sustain. Energ.
Rev., 136, 110438, https://doi.org/10.1016/j.rser.2020.110438, 2021.
Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R.: Deconvolutional
networks, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010.
Zhang, C., Be Ngio, S., Hardt, M., Recht, B., and Vinyals, O.: Understanding
deep learning requires rethinking generalization, arXiv [preprint], arXiv:1611.03530, 2016.
Zhao, B., Wang, S., Wang, J., Fu, J. S., Liu, T., Xu, J., Fu, X., and Hao,
J.: Impact of national NOx and SO2 control policies on particulate matter pollution in China, Atmos. Environ., 77, 453–463, 2013.
Zheng, B., Tong, D., Li, M., Liu, F., Hong, C., Geng, G., Li, H., Li, X., Peng, L., Qi, J., Yan, L., Zhang, Y., Zhao, H., Zheng, Y., He, K., and Zhang, Q.: Trends in China's anthropogenic emissions since 2010 as the consequence of clean air actions, Atmos. Chem. Phys., 18, 14095–14111, https://doi.org/10.5194/acp-18-14095-2018, 2018.
Zheng, H., Zhao, B., Wang, S., Wang, T., Ding, D., Chang, X., Liu, K., Xing,
J., Dong, Z., and Aunan, K.: Transition in source contributions of PM2.5
exposure and associated premature mortality in China during 2005–2015,
Environ. Int., 132, 105111, https://doi.org/10.1016/j.envint.2019.105111, 2019.
Short summary
Accurate estimation of emissions is a prerequisite for effectively controlling air pollution, but current methods lack either sufficient data or a representation of nonlinearity. Here, we proposed a novel deep learning method to model the dual relationship between emissions and pollutant concentrations. Emissions can be updated by back-propagating the gradient of the loss function measuring the deviation between simulations and observations, resulting in better model performance.
Accurate estimation of emissions is a prerequisite for effectively controlling air pollution,...
