Articles | Volume 15, issue 10
https://doi.org/10.5194/gmd-15-4225-2022
© Author(s) 2022. 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-15-4225-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
A comparative analysis for a deep learning model (hyDL-CO v1.0) and Kalman filter to predict CO concentrations in China
Weichao Han
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, Anhui, 230026, China
Tai-Long He
Department of Physics, University of Toronto, Toronto, ON, M5S 1A7, Canada
Zhaojun Tang
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, Anhui, 230026, China
Min Wang
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, Anhui, 230026, China
Dylan Jones
Department of Physics, University of Toronto, Toronto, ON, M5S 1A7, Canada
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, Anhui, 230026, China
Related authors
No articles found.
Nikhil Dadheech, Tai-Long He, and Alexander J. Turner
Atmos. Chem. Phys., 25, 5159–5174, https://doi.org/10.5194/acp-25-5159-2025, https://doi.org/10.5194/acp-25-5159-2025, 2025
Short summary
Short summary
We developed an efficient GHG (greenhouse gas) flux inversion framework using a machine-learning emulator (FootNet) as a surrogate for an atmospheric transport model, resulting in a 650 × speedup. Paradoxically, the flux inversion using the ML (machine-learning) model outperforms the full-physics model in our case study. We attribute this to the ML model mitigating transport errors in the GHG flux inversion.
Sina Voshtani, Dylan B. A. Jones, Debra Wunch, Drew C. Pendergrass, Paul O. Wennberg, David F. Pollard, Isamu Morino, Hirofumi Ohyama, Nicholas M. Deutscher, Frank Hase, Ralf Sussmann, Damien Weidmann, Rigel Kivi, Omaira García, Yao Té, Jack Chen, Kerry Anderson, Robin Stevens, Shobha Kondragunta, Aihua Zhu, Douglas Worthy, Senen Racki, Kathryn McKain, Maria V. Makarova, Nicholas Jones, Emmanuel Mahieu, Andrea Cadena-Caicedo, Paolo Cristofanelli, Casper Labuschagne, Elena Kozlova, Thomas Seitz, Martin Steinbacher, Reza Mahdi, and Isao Murata
EGUsphere, https://doi.org/10.5194/egusphere-2025-858, https://doi.org/10.5194/egusphere-2025-858, 2025
Short summary
Short summary
We assess the complementarity of the greater temporal coverage provided by ground-based remote sensing data with the spatial coverage of satellite observations when these data are used together to quantify CO emissions from extreme wildfires in 2023. Our results reveal that the commonly used biomass burning emission inventories significantly underestimate the fire emissions and emphasize the importance of the ground-based remote sensing data in reducing uncertainties in the estimated emissions.
Tai-Long He, Nikhil Dadheech, Tammy M. Thompson, and Alexander J. Turner
Geosci. Model Dev., 18, 1661–1671, https://doi.org/10.5194/gmd-18-1661-2025, https://doi.org/10.5194/gmd-18-1661-2025, 2025
Short summary
Short summary
It is computationally expensive to infer greenhouse gas (GHG) emissions using atmospheric observations. This is partly due to the detailed model used to represent atmospheric transport. We demonstrate how a machine learning (ML) model can be used to simulate high-resolution atmospheric transport. This type of ML model will help estimate GHG emissions using dense observations, which are becoming increasingly common with the proliferation of urban monitoring networks and geostationary satellites.
Dylan Jones, Lucas Prates, Zhen Qu, William Cheng, Kazuyuki Miyazaki, Takashi Sekiya, Antje Inness, Rajesh Kumar, Xiao Tang, Helen Worden, Gerbrand Koren, and Vincent Huijen
EGUsphere, https://doi.org/10.5194/egusphere-2024-3759, https://doi.org/10.5194/egusphere-2024-3759, 2025
Short summary
Short summary
We evaluate five chemical reanalysis products to assess their potential to provide useful information on tropospheric ozone variability. We find that the reanalyses produce consistent information on ozone variations in the free troposphere, but have large discrepancies at the surface. The results suggests that improvements in the reanalyses are needed to better exploit the assimilated observations to enhance the utility of the reanalysis products at the surface.
Zhaojun Tang, Zhe Jiang, Jiaqi Chen, Panpan Yang, and Yanan Shen
Geosci. Model Dev., 16, 6377–6392, https://doi.org/10.5194/gmd-16-6377-2023, https://doi.org/10.5194/gmd-16-6377-2023, 2023
Short summary
Short summary
We designed a new framework to facilitate emission inventory updates in the adjoint of GEOS-Chem model. It allows us to support Harmonized Emissions Component (HEMCO) emission inventories conveniently and to easily add more emission inventories following future updates in GEOS-Chem forward simulations. Furthermore, we developed new modules to support MERRA-2 meteorological data; this allows us to perform long-term analysis with consistent meteorological data.
Rui Zhu, Zhaojun Tang, Xiaokang Chen, Xiong Liu, and Zhe Jiang
Geosci. Model Dev., 16, 6337–6354, https://doi.org/10.5194/gmd-16-6337-2023, https://doi.org/10.5194/gmd-16-6337-2023, 2023
Short summary
Short summary
A single ozone (O3) tracer mode was developed in this work to build the capability of the GEOS-Chem model for rapid O3 simulation. It is combined with OMI and surface O3 observations to investigate the changes in tropospheric O3 in China in 2015–2020. The assimilations indicate rapid surface O3 increases that are underestimated by the a priori simulations. We find stronger increases in tropospheric O3 columns over polluted areas and a large discrepancy by assimilating different observations.
Rui Zhu, Zhaojun Tang, Xiaokang Chen, Xiong Liu, and Zhe Jiang
Atmos. Chem. Phys., 23, 9745–9763, https://doi.org/10.5194/acp-23-9745-2023, https://doi.org/10.5194/acp-23-9745-2023, 2023
Short summary
Short summary
Ozone Monitoring Instrument (OMI) and surface O3 observations are used to investigate the changes in tropospheric O3 in the USA and Europe in 2005–2020. The surface-based assimilations show limited changes in surface and tropospheric column O3. The OMI-based assimilations show larger decreases in tropospheric O3 columns in 2010–2014, related to a decline in free-tropospheric NO2. Analysis suggests limited impacts of local emissions decline on tropospheric O3 over the USA and Europe in 2005–2020.
Brendan Byrne, David F. Baker, Sourish Basu, Michael Bertolacci, Kevin W. Bowman, Dustin Carroll, Abhishek Chatterjee, Frédéric Chevallier, Philippe Ciais, Noel Cressie, David Crisp, Sean Crowell, Feng Deng, Zhu Deng, Nicholas M. Deutscher, Manvendra K. Dubey, Sha Feng, Omaira E. García, David W. T. Griffith, Benedikt Herkommer, Lei Hu, Andrew R. Jacobson, Rajesh Janardanan, Sujong Jeong, Matthew S. Johnson, Dylan B. A. Jones, Rigel Kivi, Junjie Liu, Zhiqiang Liu, Shamil Maksyutov, John B. Miller, Scot M. Miller, Isamu Morino, Justus Notholt, Tomohiro Oda, Christopher W. O'Dell, Young-Suk Oh, Hirofumi Ohyama, Prabir K. Patra, Hélène Peiro, Christof Petri, Sajeev Philip, David F. Pollard, Benjamin Poulter, Marine Remaud, Andrew Schuh, Mahesh K. Sha, Kei Shiomi, Kimberly Strong, Colm Sweeney, Yao Té, Hanqin Tian, Voltaire A. Velazco, Mihalis Vrekoussis, Thorsten Warneke, John R. Worden, Debra Wunch, Yuanzhi Yao, Jeongmin Yun, Andrew Zammit-Mangion, and Ning Zeng
Earth Syst. Sci. Data, 15, 963–1004, https://doi.org/10.5194/essd-15-963-2023, https://doi.org/10.5194/essd-15-963-2023, 2023
Short summary
Short summary
Changes in the carbon stocks of terrestrial ecosystems result in emissions and removals of CO2. These can be driven by anthropogenic activities (e.g., deforestation), natural processes (e.g., fires) or in response to rising CO2 (e.g., CO2 fertilization). This paper describes a dataset of CO2 emissions and removals derived from atmospheric CO2 observations. This pilot dataset informs current capabilities and future developments towards top-down monitoring and verification systems.
Hongxia Zhu, Rui Li, Shuping Yang, Chun Zhao, Zhe Jiang, and Chen Huang
Atmos. Chem. Phys., 23, 2421–2437, https://doi.org/10.5194/acp-23-2421-2023, https://doi.org/10.5194/acp-23-2421-2023, 2023
Short summary
Short summary
The impacts of atmospheric dust aerosols and cloud dynamic conditions on precipitation vertical development in southeastern China were studied using multiple satellite observations. It was found that the precipitating drops under dusty conditions grow faster in the middle layer but slower in the upper and lower layers compared with their pristine counterparts. Quantitative estimation of the sensitivity of the precipitation top temperature to the dust aerosol optical depth is also provided.
Tai-Long He, Dylan B. A. Jones, Kazuyuki Miyazaki, Kevin W. Bowman, Zhe Jiang, Xiaokang Chen, Rui Li, Yuxiang Zhang, and Kunna Li
Atmos. Chem. Phys., 22, 14059–14074, https://doi.org/10.5194/acp-22-14059-2022, https://doi.org/10.5194/acp-22-14059-2022, 2022
Short summary
Short summary
We use a deep-learning (DL) model to estimate Chinese NOx emissions by combining satellite analysis and in situ measurements. Our results are consistent with conventional analyses of Chinese NOx emissions. Comparison with mobility data shows that the DL model has a better capability to capture changes in NOx. We analyse Chinese NOx emissions during the COVID-19 pandemic lockdown period. Our results illustrate the potential use of DL as a complementary tool for conventional air quality studies.
Zhaojun Tang, Jiaqi Chen, and Zhe Jiang
Atmos. Chem. Phys., 22, 7815–7826, https://doi.org/10.5194/acp-22-7815-2022, https://doi.org/10.5194/acp-22-7815-2022, 2022
Short summary
Short summary
We provide a comparative analysis to explore the effects of satellite and surface measurements on atmospheric CO in data assimilations in 2015–2020 over East Asia. We find possible overestimated enhancements of atmospheric CO by assimilating surface CO measurements due to model representation errors, and a large discrepancy in the derived trends of CO columns due to different vertical sensitivities of satellite and surface observations to lower and free troposphere.
Heba S. Marey, James R. Drummond, Dylan B. A. Jones, Helen Worden, Merritt N. Deeter, John Gille, and Debbie Mao
Atmos. Meas. Tech., 15, 701–719, https://doi.org/10.5194/amt-15-701-2022, https://doi.org/10.5194/amt-15-701-2022, 2022
Short summary
Short summary
In this study, an analysis has been performed to understand the improvements in observational coverage over Canada in the new MOPITT V9 product. Temporal and spatial analysis of V9 indicates a general coverage gain of 15–20 % relative to V8, which varies regionally and seasonally; e.g., the number of successful MOPITT retrievals in V9 was doubled over Canada in winter. Also, comparison with the corresponding IASI instrument indicated generally good agreement, with about a 5–10 % positive bias.
Sabour Baray, Daniel J. Jacob, Joannes D. Maasakkers, Jian-Xiong Sheng, Melissa P. Sulprizio, Dylan B. A. Jones, A. Anthony Bloom, and Robert McLaren
Atmos. Chem. Phys., 21, 18101–18121, https://doi.org/10.5194/acp-21-18101-2021, https://doi.org/10.5194/acp-21-18101-2021, 2021
Short summary
Short summary
We use 2010–2015 surface and satellite observations to disentangle methane from anthropogenic and natural sources in Canada. Using a chemical transport model (GEOS-Chem), the mismatch between modelled and observed methane concentrations can be used to infer emissions according to Bayesian statistics. Compared to prior knowledge, we show higher anthropogenic emissions attributed to energy and/or agriculture in Western Canada and lower natural emissions from Boreal wetlands.
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.
Beata Bukosa, Jenny Fisher, Nicholas Deutscher, and Dylan Jones
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2021-173, https://doi.org/10.5194/gmd-2021-173, 2021
Revised manuscript not accepted
Short summary
Short summary
Human activities led to rising levels of greenhouse gases (carbon dioxide (CO2), methane (CH4), carbon monoxide (CO)) in the atmosphere, threatening our future. We use models and measurements to predict and understand the climatological impact of these gases. Here, we describe a new simulation in the GEOS-Chem model that uses a more accurate method to simulate CO2, CH4 and CO, through their chemical dependence. Relative to the original simulations our results agree better with measurements.
Ilya Stanevich, Dylan B. A. Jones, Kimberly Strong, Martin Keller, Daven K. Henze, Robert J. Parker, Hartmut Boesch, Debra Wunch, Justus Notholt, Christof Petri, Thorsten Warneke, Ralf Sussmann, Matthias Schneider, Frank Hase, Rigel Kivi, Nicholas M. Deutscher, Voltaire A. Velazco, Kaley A. Walker, and Feng Deng
Atmos. Chem. Phys., 21, 9545–9572, https://doi.org/10.5194/acp-21-9545-2021, https://doi.org/10.5194/acp-21-9545-2021, 2021
Short summary
Short summary
We explore the utility of a weak-constraint (WC) four-dimensional variational (4D-Var) data assimilation scheme for mitigating systematic errors in methane simulation in the GEOS-Chem model. We use data from the Greenhouse Gases Observing Satellite (GOSAT) and show that, compared to the traditional 4D-Var approach, the WC scheme improves the agreement between the model and independent observations. We find that the WC corrections to the model provide insight into the source of the errors.
Vikram Khade, Saroja M. Polavarapu, Michael Neish, Pieter L. Houtekamer, Dylan B. A. Jones, Seung-Jong Baek, Tai-Long He, and Sylvie Gravel
Geosci. Model Dev., 14, 2525–2544, https://doi.org/10.5194/gmd-14-2525-2021, https://doi.org/10.5194/gmd-14-2525-2021, 2021
Short summary
Short summary
A new modeling system has been developed at Environment and Climate Change Canada to ingest observations of carbon monoxide (CO) into a coupled weather and constituent transport model. We show that accounting for the uncertainty in surface flux leads to a better estimate of CO distributions. The benefit of assimilating observations from different simulated networks varies with region. This is the first step towards developing a state and flux estimation system for greenhouse gases.
Shoma Yamanouchi, Camille Viatte, Kimberly Strong, Erik Lutsch, Dylan B. A. Jones, Cathy Clerbaux, Martin Van Damme, Lieven Clarisse, and Pierre-Francois Coheur
Atmos. Meas. Tech., 14, 905–921, https://doi.org/10.5194/amt-14-905-2021, https://doi.org/10.5194/amt-14-905-2021, 2021
Short summary
Short summary
Ammonia (NH3) is a major source of pollution in the air. As such, there have been increasing efforts to measure the atmospheric abundance of NH3 and its spatial and temporal variability. In this study, long-term measurements of NH3 over Toronto, Canada, derived from multiscale datasets are examined. These NH3 datasets were compared to each other and to a model to better understand NH3 variability and to assess model performance.
Erik Lutsch, Kimberly Strong, Dylan B. A. Jones, Thomas Blumenstock, Stephanie Conway, Jenny A. Fisher, James W. Hannigan, Frank Hase, Yasuko Kasai, Emmanuel Mahieu, Maria Makarova, Isamu Morino, Tomoo Nagahama, Justus Notholt, Ivan Ortega, Mathias Palm, Anatoly V. Poberovskii, Ralf Sussmann, and Thorsten Warneke
Atmos. Chem. Phys., 20, 12813–12851, https://doi.org/10.5194/acp-20-12813-2020, https://doi.org/10.5194/acp-20-12813-2020, 2020
Short summary
Short summary
This paper describes the use of a network of 10 Arctic and midlatitude ground-based FTIR measurement sites to detect enhancements of the wildfire tracers carbon monoxide, hydrogen cyanide, and ethane from 2003 to 2018. A tagged CO GEOS-Chem simulation is used for source attribution and to evaluate the relative contribution of CO sources to the FTIR measurements. The use of FTIR measurements allowed for the emission ratios of hydrogen cyanide and ethane to be quantified.
Cited articles
Andersson, T. R., Hosking, J. S., Perez-Ortiz, M., Paige, B., Elliott, A., Russell, C., Law, S., Jones, D. C., Wilkinson, J., Phillips, T., Byrne, J., Tietsche, S., Sarojini, B. B., Blanchard-Wrigglesworth, E., Aksenov, Y., Downie, R., and Shuckburgh, E.:
Seasonal Arctic sea ice forecasting with probabilistic deep learning, Nat. Commun., 12, 5124, https://doi.org/10.1038/s41467-021-25257-4, 2021.
Chen, X., Jiang, Z., Shen, Y., Li, R., Fu, Y., Liu, J., Han, H., Liao, H., Cheng, X., Jones, D. B. A., Worden, H., and Abad, G. G.:
Chinese regulations are working – why is surface ozone over industrialized areas still high? Applying lessons from Northeast US air quality evolution, Geophys. Res. Lett., 48, e2021GL092816, https://doi.org/10.1029/2021GL092816, 2021.
Chen, Y., Cui, S., Chen, P., Yuan, Q., Kang, P., and Zhu, L.:
An LSTM-based neural network method of particulate pollution forecast in China, Environ. Res. Lett., 16, 044006, https://doi.org/10.1088/1748-9326/abe1f5, 2021.
Feng, S., Jiang, F., Wu, Z., Wang, H., Ju, W., and Wang, H.:
CO Emissions Inferred From Surface CO Observations Over China in December 2013 and 2017, J. Geophys. Res.-Atmos., 125, 2019JD031808, https://doi.org/10.1029/2019jd031808, 2020.
Fisher, J. A., Murray, L. T., Jones, D. B. A., and Deutscher, N. M.:
Improved method for linear carbon monoxide simulation and source attribution in atmospheric chemistry models illustrated using GEOS-Chem v9, Geosci. Model Dev., 10, 4129–4144, https://doi.org/10.5194/gmd-10-4129-2017, 2017.
Gaubert, B., Bouarar, I., Doumbia, T., Liu, Y., Stavrakou, T., Deroubaix, A., Darras, S., Elguindi, N., Granier, C., Lacey, F., Müller, J. F., Shi, X., Tilmes, S., Wang, T., and Brasseur, G. P.:
Global Changes in Secondary Atmospheric Pollutants During the 2020 COVID-19 Pandemic, J. Geophys. Res.-Atmos., 126, 2020JD034213, https://doi.org/10.1029/2020jd034213, 2021.
Ghorbanzadeh, O., Crivellari, A., Ghamisi, P., Shahabi, H., and Blaschke, T.:
A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan), Sci. Rep.-UK, 11, 14629, https://doi.org/10.1038/s41598-021-94190-9, 2021.
He, K., Zhang, X., Ren, S., and Sun, J.:
Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016, Las Vegas, NV, USA, 770–778, 2016.
He, T. L., Jones, D. B. A., Miyazaki, K., Huang, B., Liu, Y., Jiang, Z., White, E. C., Worden, H. M., and Worden, J. R.:
Deep learning to evaluate US NOx emissions using surface ozone predictions, J. Geophys. Res.-Atmos., 127, e2021JD035597, https://doi.org/10.1029/2021jd035597, 2022.
Hoesly, R. M., Smith, S. J., Feng, L., Klimont, Z., Janssens-Maenhout, G., Pitkanen, T., Seibert, J. J., Vu, L., Andres, R. J., Bolt, R. M., Bond, T. C., Dawidowski, L., Kholod, N., Kurokawa, J.-I., Li, M., Liu, L., Lu, Z., Moura, M. C. P., O'Rourke, P. R., and Zhang, Q.:
Historical (1750–2014) anthropogenic emissions of reactive gases and aerosols from the Community Emissions Data System (CEDS), Geosci. Model Dev., 11, 369–408, https://doi.org/10.5194/gmd-11-369-2018, 2018.
Jiang, Z.: Deep learning model (hyDL-CO v1.0) to predict CO in China, https://doi.org/10.5281/zenodo.5913013 [code], 2022.
Jiang, Z., Worden, J. R., Worden, H., Deeter, M., Jones, D. B. A., Arellano, A. F., and Henze, D. K.:
A 15-year record of CO emissions constrained by MOPITT CO observations, Atmos. Chem. Phys., 17, 4565–4583, https://doi.org/10.5194/acp-17-4565-2017, 2017.
Kleinert, F., Leufen, L. H., and Schultz, M. G.:
IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany, Geosci. Model Dev., 14, 1–25, https://doi.org/10.5194/gmd-14-1-2021, 2021.
Kong, L., Tang, X., Zhu, J., Wang, Z., Fu, J. S., Wang, X., Itahashi, S., Yamaji, K., Nagashima, T., Lee, H.-J., Kim, C.-H., Lin, C.-Y., Chen, L., Zhang, M., Tao, Z., Li, J., Kajino, M., Liao, H., Wang, Z., Sudo, K., Wang, Y., Pan, Y., Tang, G., Li, M., Wu, Q., Ge, B., and Carmichael, G. R.:
Evaluation and uncertainty investigation of the NO2, CO and NH3 modeling over China under the framework of MICS-Asia III, Atmos. Chem. Phys., 20, 181–202, https://doi.org/10.5194/acp-20-181-2020, 2020.
Korznikov, K. A., Kislov, D. E., Altman, J., Doležal, J., Vozmishcheva, A. S., and Krestov, P. V.:
Using U-Net-Like Deep Convolutional Neural Networks for Precise Tree Recognition in Very High Resolution RGB (Red, Green, Blue) Satellite Images, Forests, 12, f12010066, https://doi.org/10.3390/f12010066, 2021.
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D.:
Backpropagation applied to hand written zip code recognition, Neural Comput., 1, 541–551, https://doi.org/10.1162/neco.1989.1.4.541, 1989.
Li, K., Jacob, D. J., Liao, H., Shen, L., Zhang, Q., and Bates, K. H.:
Anthropogenic drivers of 2013-2017 trends in summer surface ozone in China, P. Natl. Acad. Sci. USA, 116, 422–427, https://doi.org/10.1073/pnas.1812168116, 2019.
Li, K., Jacob, D. J., Shen, L., Lu, X., De Smedt, I., and Liao, H.:
Increases in surface ozone pollution in China from 2013 to 2019: anthropogenic and meteorological influences, Atmos. Chem. Phys., 20, 11423–11433, https://doi.org/10.5194/acp-20-11423-2020, 2020.
Li, M., Zhang, Q., Kurokawa, J.-I., Woo, J.-H., He, K., Lu, Z., Ohara, T., Song, Y., Streets, D. G., Carmichael, G. R., Cheng, Y., Hong, C., Huo, H., Jiang, X., Kang, S., Liu, F., Su, H., and Zheng, B.:
MIX: a mosaic Asian anthropogenic emission inventory under the international collaboration framework of the MICS-Asia and HTAP, Atmos. Chem. Phys., 17, 935–963, https://doi.org/10.5194/acp-17-935-2017, 2017.
Li, R., Zhao, Y., Zhou, W., Meng, Y., Zhang, Z., and Fu, H.:
Developing a novel hybrid model for the estimation of surface 8 h ozone (O3) across the remote Tibetan Plateau during 2005–2018, Atmos. Chem. Phys., 20, 6159–6175, https://doi.org/10.5194/acp-20-6159-2020, 2020.
Liu, P., Wei, Y., Wang, Q., Chen, Y., and Xie, J.:
Research on Post-Earthquake Landslide Extraction Algorithm Based on Improved U-Net Model, Remote Sens.-Basel, 12, rs12050894, https://doi.org/10.3390/rs12050894, 2020.
Lu, X., Ye, X., Zhou, M., Zhao, Y., Weng, H., Kong, H., Li, K., Gao, M., Zheng, B., Lin, J., Zhou, F., Zhang, Q., Wu, D., Zhang, L., and Zhang, Y.:
The underappreciated role of agricultural soil nitrogen oxide emissions in ozone pollution regulation in North China, Nat. Commun., 12, 5021, https://doi.org/10.1038/s41467-021-25147-9, 2021.
Ma, C., Wang, T., Mizzi, A. P., Anderson, J. L., Zhuang, B., Xie, M., and Wu, R.:
Multiconstituent Data Assimilation With WRF – Chem/DART: Potential for Adjusting Anthropogenic Emissions and Improving Air Quality Forecasts Over Eastern China, J. Geophys. Res.-Atmos., 124, 2019JD030421, https://doi.org/10.1029/2019jd030421, 2019.
Peng, Z., Lei, L., Liu, Z., Sun, J., Ding, A., Ban, J., Chen, D., Kou, X., and Chu, K.:
The impact of multi-species surface chemical observation assimilation on air quality forecasts in China, Atmos. Chem. Phys., 18, 17387–17404, https://doi.org/10.5194/acp-18-17387-2018, 2018.
Qi, W., Wei, M., Yang, W., Xu, C., and Ma, C.:
Automatic Mapping of Landslides by the ResU-Net, Remote Sens.-Basel, 12, rs12152487, https://doi.org/10.3390/rs12152487, 2020.
Quennehen, B., Raut, J.-C., Law, K. S., Daskalakis, N., Ancellet, G., Clerbaux, C., Kim, S.-W., Lund, M. T., Myhre, G., Olivié, D. J. L., Safieddine, S., Skeie, R. B., Thomas, J. L., Tsyro, S., Bazureau, A., Bellouin, N., Hu, M., Kanakidou, M., Klimont, Z., Kupiainen, K., Myriokefalitakis, S., Quaas, J., Rumbold, S. T., Schulz, M., Cherian, R., Shimizu, A., Wang, J., Yoon, S.-C., and Zhu, T.:
Multi-model evaluation of short-lived pollutant distributions over east Asia during summer 2008, Atmos. Chem. Phys., 16, 10765–10792, https://doi.org/10.5194/acp-16-10765-2016, 2016.
Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., and Mohamed, S.:
Skilful precipitation nowcasting using deep generative models of radar, Nature, 597, 672–677, https://doi.org/10.1038/s41586-021-03854-z, 2021.
Ronneberger, O., Fischer, P., and Brox, T.:
U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv [preprint], arXiv:1505.04597, 2015.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.:
Learning representations by back-propagating errors, Nature, 323, 533–536, https://doi.org/10.1038/323533a0, 1986.
Shi, X. and Brasseur, G. P.:
The Response in Air Quality to the Reduction of Chinese Economic Activities during the COVID-19 Outbreak, Geophys. Res. Lett., 47, e2020GL088070, https://doi.org/10.1029/2020GL088070, 2020.
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-C.:
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, arXiv [preprint], arXiv:1506.04214, 2015.
Shi, Z., Song, C., Liu, B., Lu, G., Xu, J., Van Vu, T., Elliott, R. J. R., Li, W., Bloss, W. J., and Harrison, R. M.:
Abrupt but smaller than expected changes in surface air quality attributable to COVID-19 lockdowns, Sci. Adv., 7, eabd6696, https://doi.org/10.1126/sciadv.abd6696, 2021.
Tang, Z., Chen, J., and Jiang, Z.:
Effects of satellite and surface measurements on atmospheric CO assimilations over East Asia in 2015–2020, Atmos. Chem. Phys. Discuss. [preprint], https://doi.org/10.5194/acp-2021-1035, in review, 2022.
Xing, X., Xiong, Y., Yang, R., Wang, R., Wang, W., Kan, H., Lu, T., Li, D., Cao, J., Penuelas, J., Ciais, P., Bauer, N., Boucher, O., Balkanski, Y., Hauglustaine, D., Brasseur, G., Morawska, L., Janssens, I. A., Wang, X., Sardans, J., Wang, Y., Deng, Y., Wang, L., Chen, J., Tang, X., and Zhang, R.:
Predicting the effect of confinement on the COVID-19 spread using machine learning enriched with satellite air pollution observations, P. Natl. Acad. Sci. USA, 118, e2109098118, https://doi.org/10.1073/pnas.2109098118, 2021.
Zhang, Y., Vu, T. V., Sun, J., He, J., Shen, X., Lin, W., Zhang, X., Zhong, J., Gao, W., Wang, Y., Fu, T. M., Ma, Y., Li, W., and Shi, Z.:
Significant Changes in Chemistry of Fine Particles in Wintertime Beijing from 2007 to 2017: Impact of Clean Air Actions, Environ. Sci. Tech., 54, 1344–1352, https://doi.org/10.1021/acs.est.9b04678, 2020.
Short summary
We present an application of a hybrid deep learning (DL) model on prediction of surface CO in China from 2015 to 2020, which utilizes both convolutional neural networks and long short-term memory neural networks. The DL model performance is better than a Kalman filter (KF) system in the training period (2005–2018). Furthermore, the DL model demonstrates good temporal extensibility: the mean bias and correlation coefficients are 95.7 ppb and 0.93 in the test period (2019–2020) over eastern China.
We present an application of a hybrid deep learning (DL) model on prediction of surface CO in...