Articles | Volume 14, issue 1
https://doi.org/10.5194/gmd-14-1-2021
© 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-14-1-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany
Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany
Institute of Geosciences, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
Lukas H. Leufen
Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany
Institute of Geosciences, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
Martin G. Schultz
Jülich Supercomputing Centre, Forschungszentrum Jülich, Jülich, Germany
Related authors
Felix Kleinert, Lukas H. Leufen, Aurelia Lupascu, Tim Butler, and Martin G. Schultz
Geosci. Model Dev., 15, 8913–8930, https://doi.org/10.5194/gmd-15-8913-2022, https://doi.org/10.5194/gmd-15-8913-2022, 2022
Short summary
Short summary
We examine the effects of spatially aggregated upstream information as input for a deep learning model forecasting near-surface ozone levels. Using aggregated data from one upstream sector (45°) improves the forecast by ~ 10 % for 4 prediction days. Three upstream sectors improve the forecasts by ~ 14 % on the first 2 d only. Our results serve as an orientation for other researchers or environmental agencies focusing on pointwise time-series predictions, for example, due to regulatory purposes.
Lukas Hubert Leufen, Felix Kleinert, and Martin G. Schultz
Geosci. Model Dev., 14, 1553–1574, https://doi.org/10.5194/gmd-14-1553-2021, https://doi.org/10.5194/gmd-14-1553-2021, 2021
Short summary
Short summary
MLAir provides a coherent end-to-end structure for a typical time series analysis workflow using machine learning (ML). MLAir is adaptable to a wide range of ML use cases, focusing in particular on deep learning. The user has a free hand with the ML model itself and can select from different methods during preprocessing, training, and postprocessing. MLAir offers tools to track the experiment conduction, documents necessary ML parameters, and creates a variety of publication-ready plots.
Biplob Dey, Toke Due Sjøgren, Peeyush Khare, Georgios I. Gkatzelis, Yizhen Wu, Sindhu Vasireddy, Martin Schultz, Alexander Knohl, Riikka Rinnan, Thorsten Hohaus, and Eva Y. Pfannerstill
EGUsphere, https://doi.org/10.5194/egusphere-2025-3779, https://doi.org/10.5194/egusphere-2025-3779, 2025
This preprint is open for discussion and under review for Biogeosciences (BG).
Short summary
Short summary
Trees release reactive gases that affect air quality and climate. We studied how these emissions from European beech and English oak change under realistic scenarios of combined and single heat and ozone stress. Heat increased emissions, while ozone reduced most of them. When stressors were combined, the effects were complex and varied by species. Machine learning identified key stress-related compounds. Our findings show that future tree stress may alter air quality and climate interactions.
Ramiyou Karim Mache, Sabine Schröder, Michael Langguth, Ankit Patnala, and Martin G. Schultz
EGUsphere, https://doi.org/10.5194/egusphere-2025-1399, https://doi.org/10.5194/egusphere-2025-1399, 2025
Short summary
Short summary
The TOAR-classifier model is a data-driven tool that allows for an objective classification of air quality measuring stations as urban, rural, or suburban. Such classification is important in the analysis of air pollutant trends and regional signatures. The model is employed in the second Tropospheric Ozone Assessment Report but can also be used in other research work.
Yugo Kanaya, Roberto Sommariva, Alfonso Saiz-Lopez, Andrea Mazzeo, Theodore K. Koenig, Kaori Kawana, James E. Johnson, Aurélie Colomb, Pierre Tulet, Suzie Molloy, Ian E. Galbally, Rainer Volkamer, Anoop Mahajan, John W. Halfacre, Paul B. Shepson, Julia Schmale, Hélène Angot, Byron Blomquist, Matthew D. Shupe, Detlev Helmig, Junsu Gil, Meehye Lee, Sean C. Coburn, Ivan Ortega, Gao Chen, James Lee, Kenneth C. Aikin, David D. Parrish, John S. Holloway, Thomas B. Ryerson, Ilana B. Pollack, Eric J. Williams, Brian M. Lerner, Andrew J. Weinheimer, Teresa Campos, Frank M. Flocke, J. Ryan Spackman, Ilann Bourgeois, Jeff Peischl, Chelsea R. Thompson, Ralf M. Staebler, Amir A. Aliabadi, Wanmin Gong, Roeland Van Malderen, Anne M. Thompson, Ryan M. Stauffer, Debra E. Kollonige, Juan Carlos Gómez Martin, Masatomo Fujiwara, Katie Read, Matthew Rowlinson, Keiichi Sato, Junichi Kurokawa, Yoko Iwamoto, Fumikazu Taketani, Hisahiro Takashima, Monica Navarro Comas, Marios Panagi, and Martin G. Schultz
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2024-566, https://doi.org/10.5194/essd-2024-566, 2025
Revised manuscript accepted for ESSD
Short summary
Short summary
The first comprehensive dataset of tropospheric ozone over oceans/polar regions is presented, including 77 ship/buoy and 48 aircraft campaign observations (1977–2022, 0–5000 m altitude), supplemented by ozonesonde and surface data. Air masses isolated from land for 72+ hours are systematically selected as essentially oceanic. Among the 11 global regions, they show daytime decreases of 10–16% in the tropics, while near-zero depletions are rare, unlike in the Arctic, implying different mechanisms.
Sebastian H. M. Hickman, Makoto Kelp, Paul T. Griffiths, Kelsey Doerksen, Kazuyuki Miyazaki, Elyse A. Pennington, Gerbrand Koren, Fernando Iglesias-Suarez, Martin G. Schultz, Kai-Lan Chang, Owen R. Cooper, Alexander T. Archibald, Roberto Sommariva, David Carlson, Hantao Wang, J. Jason West, and Zhenze Liu
EGUsphere, https://doi.org/10.5194/egusphere-2024-3739, https://doi.org/10.5194/egusphere-2024-3739, 2025
Short summary
Short summary
Machine learning is being more widely used across environmental and climate science. This work reviews the use of machine learning in tropospheric ozone research, focusing on three main application areas in which significant progress has been made. Common challenges in using machine learning across the three areas are highlighted, and future directions for the field are indicated.
Hantao Wang, Kazuyuki Miyazaki, Haitong Zhe Sun, Zhen Qu, Xiang Liu, Antje Inness, Martin Schultz, Sabine Schröder, Marc Serre, and J. Jason West
EGUsphere, https://doi.org/10.5194/egusphere-2024-3723, https://doi.org/10.5194/egusphere-2024-3723, 2025
Short summary
Short summary
We compare six datasets of global ground-level ozone, developed using geostatistical, machine learning, or reanalysis methods. The datasets show important differences from one another in ozone magnitude, greater than 5 ppb, and trends, globally and regionally. Compared with measurements, performance varies among datasets, and most overestimate ozone, particularly at lower concentrations. These differences among datasets highlight uncertainties for applications to health and other impacts.
Bing Gong, Michael Langguth, Yan Ji, Amirpasha Mozaffari, Scarlet Stadtler, Karim Mache, and Martin G. Schultz
Geosci. Model Dev., 15, 8931–8956, https://doi.org/10.5194/gmd-15-8931-2022, https://doi.org/10.5194/gmd-15-8931-2022, 2022
Short summary
Short summary
Inspired by the success of deep learning in various domains, we test the applicability of video prediction methods by generative adversarial network (GAN)-based deep learning to predict the 2 m temperature over Europe. Our video prediction models have skill in predicting the diurnal cycle of 2 m temperature up to 12 h ahead. Complemented by probing the relevance of several model parameters, this study confirms the potential of deep learning in meteorological forecasting applications.
Felix Kleinert, Lukas H. Leufen, Aurelia Lupascu, Tim Butler, and Martin G. Schultz
Geosci. Model Dev., 15, 8913–8930, https://doi.org/10.5194/gmd-15-8913-2022, https://doi.org/10.5194/gmd-15-8913-2022, 2022
Short summary
Short summary
We examine the effects of spatially aggregated upstream information as input for a deep learning model forecasting near-surface ozone levels. Using aggregated data from one upstream sector (45°) improves the forecast by ~ 10 % for 4 prediction days. Three upstream sectors improve the forecasts by ~ 14 % on the first 2 d only. Our results serve as an orientation for other researchers or environmental agencies focusing on pointwise time-series predictions, for example, due to regulatory purposes.
Swantje Preuschmann, Tanja Blome, Knut Görl, Fiona Köhnke, Bettina Steuri, Juliane El Zohbi, Diana Rechid, Martin Schultz, Jianing Sun, and Daniela Jacob
Adv. Sci. Res., 19, 51–71, https://doi.org/10.5194/asr-19-51-2022, https://doi.org/10.5194/asr-19-51-2022, 2022
Short summary
Short summary
The main aspect of the paper is to obtain transferable principles for the development of digital knowledge transfer products. As such products are still unstandardised, the authors explored challenges and approaches for product developments. The authors report what they see as useful principles for developing digital knowledge transfer products, by describing the experience of developing the Net-Zero-2050 Web-Atlas and the "Bodenkohlenstoff-App".
Clara Betancourt, Timo T. Stomberg, Ann-Kathrin Edrich, Ankit Patnala, Martin G. Schultz, Ribana Roscher, Julia Kowalski, and Scarlet Stadtler
Geosci. Model Dev., 15, 4331–4354, https://doi.org/10.5194/gmd-15-4331-2022, https://doi.org/10.5194/gmd-15-4331-2022, 2022
Short summary
Short summary
Ozone is a toxic greenhouse gas with high spatial variability. We present a machine-learning-based ozone-mapping workflow generating a transparent and reliable product. Going beyond standard mapping methods, this work combines explainable machine learning with uncertainty assessment to increase the integrity of the produced map.
Clara Betancourt, Timo Stomberg, Ribana Roscher, Martin G. Schultz, and Scarlet Stadtler
Earth Syst. Sci. Data, 13, 3013–3033, https://doi.org/10.5194/essd-13-3013-2021, https://doi.org/10.5194/essd-13-3013-2021, 2021
Short summary
Short summary
With the AQ-Bench dataset, we contribute to shared data usage and machine learning methods in the field of environmental science. The AQ-Bench dataset contains air quality data and metadata from more than 5500 air quality observation stations all over the world. The dataset offers a low-threshold entrance to machine learning on a real-world environmental dataset. AQ-Bench thus provides a blueprint for environmental benchmark datasets.
Lukas Hubert Leufen, Felix Kleinert, and Martin G. Schultz
Geosci. Model Dev., 14, 1553–1574, https://doi.org/10.5194/gmd-14-1553-2021, https://doi.org/10.5194/gmd-14-1553-2021, 2021
Short summary
Short summary
MLAir provides a coherent end-to-end structure for a typical time series analysis workflow using machine learning (ML). MLAir is adaptable to a wide range of ML use cases, focusing in particular on deep learning. The user has a free hand with the ML model itself and can select from different methods during preprocessing, training, and postprocessing. MLAir offers tools to track the experiment conduction, documents necessary ML parameters, and creates a variety of publication-ready plots.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, M., Kudlur, M., Levenberg, J., Mané, M., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, J., Sutskever, I., Talwar, J., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on
Heterogeneous Systems, available at: https://www.tensorflow.org/ (last access: 18 December 2020), 2015. a
Abdul Aziz, F. A. B., Abd. Rahman, N., and Mohd Ali, J.: Tropospheric Ozone
Formation Estimation in Urban City, Bangi, Using Artificial
Neural Network (ANN), Comput. Intel. Neurosc.,
2019, 1–10, https://doi.org/10.1155/2019/6252983,
2019. a
Abdul-Wahab, S. A., Bakheit, C. S., and Al-Alawi, S. M.: Principal component
and multiple regression analysis in modelling of ground-level ozone and
factors affecting its concentrations, Environ. Modell. Softw.,
20, 1263–1271, https://doi.org/10.1016/j.envsoft.2004.09.001,
2005. a
Avnery, S., Mauzerall, D. L., Liu, J., and Horowitz, L. W.: Global crop yield
reductions due to surface ozone exposure: 1. Year 2000 crop production
losses and economic damage, Atmos. Environ., 45, 2284–2296,
https://doi.org/10.1016/j.atmosenv.2010.11.045,
2011. a
Bai, S., Kolter, J. Z., and Koltun, V.: An Empirical Evaluation of
Generic Convolutional and Recurrent Networks for Sequence
Modeling, arXiv [preprint], arXiv:1803.01271, 2018. a
Bell, M. L., Zanobetti, A., and Dominici, F.: Who is More Affected by
Ozone Pollution? A Systematic Review and Meta-Analysis,
Am. J. Epidemiol., 180, 15–28, https://doi.org/10.1093/aje/kwu115, 2014. a
Bollmeyer, C., Keller, J. D., Ohlwein, C., Wahl, S., Crewell, S., Friederichs,
P., Hense, A., Keune, J., Kneifel, S., Pscheidt, I., Redl, S., and Steinke,
S.: Towards a high-resolution regional reanalysis for the European CORDEX
domain, Q. J. Roy. Meteor. Soc., 141, 1–15,
https://doi.org/10.1002/qj.2486,
2015. a
Brunner, D., Savage, N., Jorba, O., Eder, B., Giordano, L., Badia, A.,
Balzarini, A., Baró, R., Bianconi, R., Chemel, C., Curci, G., Forkel, R.,
Jiménez-Guerrero, P., Hirtl, M., Hodzic, A., Honzak, L., Im, U., Knote, C.,
Makar, P., Manders-Groot, A., van Meijgaard, E., Neal, L., Pérez, J. L.,
Pirovano, G., San Jose, R., Schröder, W., Sokhi, R. S., Syrakov, D., Torian,
A., Tuccella, P., Werhahn, J., Wolke, R., Yahya, K., Zabkar, R., Zhang, Y.,
Hogrefe, C., and Galmarini, S.: Comparative analysis of meteorological
performance of coupled chemistry-meteorology models in the context of
AQMEII phase 2, Atmos. Environ., 115, 470–498,
https://doi.org/10.1016/j.atmosenv.2014.12.032,
2015. a
Chollet, F.: Keras, available at: https://keras.io (last access: 18 December 2020), 2015. a
Clevert, D.-A., Unterthiner, T., and Hochreiter, S.: Fast and Accurate Deep
Network Learning by Exponential Linear Units (ELUs),
arXiv [preprint],
arXiv:1511.07289,
2016. a
Cobourn, W. G., Dolcine, L., French, M., and Hubbard, M. C.: A Comparison of
Nonlinear Regression and Neural Network Models for Ground-Level Ozone
Forecasting, J. Air Waste Ma., 50,
1999–2009, https://doi.org/10.1080/10473289.2000.10464228,
2000. a
Collins, W. J., Stevenson, D. S., Johnson, C. E., and Derwent, R. G.:
Tropospheric Ozone in a Global-Scale Three-Dimensional Lagrangian Model and
Its Response to NOX Emission Controls, J. Atmos. Chem., 26,
223–274, https://doi.org/10.1023/A:1005836531979,
1997. a
Comrie, A. C.: Comparing Neural Networks and Regression Models for Ozone
Forecasting, J. Air Waste Ma., 47,
653–663, https://doi.org/10.1080/10473289.1997.10463925,
1997. a
Dauphin, Y. N., Fan, A., Auli, M., and Grangier, D.: Language Modeling with
Gated Convolutional Networks, arXiv [preprint],
arXiv:1612.08083, 2017. a
Donner, L. J., Wyman, B. L., Hemler, R. S., Horowitz, L. W., Ming, Y., Zhao,
M., Golaz, J.-C., Ginoux, P., Lin, S.-J., Schwarzkopf, M. D., Austin, J.,
Alaka, G., Cooke, W. F., Delworth, T. L., Freidenreich, S. M., Gordon, C. T.,
Griffies, S. M., Held, I. M., Hurlin, W. J., Klein, S. A., Knutson, T. R.,
Langenhorst, A. R., Lee, H.-C., Lin, Y., Magi, B. I., Malyshev, S. L., Milly,
P. C. D., Naik, V., Nath, M. J., Pincus, R., Ploshay, J. J., Ramaswamy, V.,
Seman, C. J., Shevliakova, E., Sirutis, J. J., Stern, W. F., Stouffer, R. J.,
Wilson, R. J., Winton, M., Wittenberg, A. T., and Zeng, F.: The Dynamical
Core, Physical Parameterizations, and Basic Simulation Characteristics of the
Atmospheric Component AM3 of the GFDL Global Coupled Model CM3, J.
Climate, 24, 3484–3519, https://doi.org/10.1175/2011JCLI3955.1,
2011. a
Dye, T. S.: Guidelines for developing an air quality (ozone and PM2.5)
forecasting program, US Environmental Protection Agency, Office of Air
Quality Planning and Standards, Information Transfer and Program Integration
Division, AIRNow Program, available at:
https://nepis.epa.gov/Exe/ZyPURL.cgi?Dockey=2000F0ZT.txt (last access: 18 December 2020),
2003. a
Eslami, E., Choi, Y., Lops, Y., and Sayeed, A.: A real-time hourly ozone
prediction system using deep convolutional neural network, Neural Comput.
Appl., 32, 8783–8797, https://doi.org/10.1007/s00521-019-04282-x,
2020. a, b
Fleming, Z. L., Doherty, R. M., Von Schneidemesser, E., Malley, C. S., Cooper,
O. R., Pinto, J. P., Colette, A., Xu, X., Simpson, D., Schultz, M. G.,
Lefohn, A. S., Hamad, S., Moolla, R., Solberg, S., and Feng, Z.: Tropospheric
Ozone Assessment Report: Present-day ozone distribution and trends
relevant to human health, Elem. Sci. Anth., 6, 12, https://doi.org/10.1525/elementa.273,
2018. a, b
Fuentes, M. and Raftery, A. E.: Model Evaluation and Spatial
Interpolation by Bayesian Combination of Observations with Outputs
from Numerical Models, Biometrics, 61, 36–45,
https://doi.org/10.1111/j.0006-341X.2005.030821.x, 2005. a
Gardner, M. and Dorling, S.: Artificial Neural Network-Derived Trends in Daily
Maximum Surface Ozone Concentrations, J. Air Waste Ma., 51, 1202–1210, https://doi.org/10.1080/10473289.2001.10464338,
2001. a
Grell, G. A., Peckham, S. E., Schmitz, R., McKeen, S. A., Frost, G., Skamarock,
W. C., and Eder, B.: Fully coupled “online” chemistry within the WRF
model, Atmos. Environ., 39, 6957–6975,
https://doi.org/10.1016/j.atmosenv.2005.04.027,
2005. a
Horowitz, J. and Barakat, S.: Statistical analysis of the maximum concentration
of an air pollutant: Effects of autocorrelation and non-stationarity,
Atmos. Environ., 13, 811–818,
https://doi.org/10.1016/0004-6981(79)90272-5,
1979. a
Horowitz, L. W., Stacy, W., Mauzerall, D. L., Emmons, L. K., Rasch, P. J.,
Granier, C., Tie, X., Lamarque, J., Schultz, M. G., Tyndall, G. S., Orlando,
J. J., and Brasseur, G. P.: A global simulation of tropospheric ozone and
related tracers: Description and evaluation of MOZART, version 2, J.
Geophys. Res.-Atmos., 108, D12, https://doi.org/10.1029/2002JD002853,
2003. a
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep
Network Training by Reducing Internal Covariate Shift,
arXiv [preprint], arXiv:1502.03167,
2015. a
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.-A.:
Deep learning for time series classification: a review, Data Min.
Knowl. Disc., 33, 917–963, https://doi.org/10.1007/s10618-019-00619-1,
2019. a
Jacobson, M. Z.: Fundamentals of Atmospheric Modeling, Cambridge University
Press, Cambridge, UK, 2005. a
Jülich Supercomputing Centre: JUWELS: Modular Tier-0/1 Supercomputer
at Jülich Supercomputing Centre, Journal of large-scale research
facilities, 5, A135, https://doi.org/10.17815/jlsrf-5-171,
2019. a, b
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization,
arXiv [preprint], arXiv:1412.6980, 2014. a
Kleinert, F., Leufen, L. H., and Schultz, M. G.: IntelliO3-ts: Data, b2share,
https://doi.org/10.34730/c5dae21fac954aa6bdb4e86172221526,
2020a. a
Kleinert, F., Leufen, L. H., and Schultz, M. G.: IntelliO3-ts: Source
code and data,
https://doi.org/10.23728/b2share.5042cda41a4c49769cc4010d2 31ecdec, b2share,
2020b. a
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P.: Gradient-based learning
applied to document recognition, in: Proceedings of the IEEE, 86,
2278–2324,
https://doi.org/10.1109/5.726791, 1998. a
Lefohn, A. S., Malley, C. S., Simon, H., Wells, B., Xu, X., Zhang, L., and
Wang, T.: Responses of human health and vegetation exposure metrics to
changes in ozone concentration distributions in the European Union,
United States, and China, Atmos. Environ., 152, 123–145,
https://doi.org/10.1016/j.atmosenv.2016.12.025,
2017. a
Liu, B., Yan, S., Li, J., Qu, G., Li, Y., Lang, J., and Gu, R.: A
Sequence-to-Sequence Air Quality Predictor Based on the n-Step
Recurrent Prediction, IEEE Access, 7, 43331–43345,
https://doi.org/10.1109/ACCESS.2019.2908081,
2019. a
Ma, J., Li, Z., Cheng, J. C., Ding, Y., Lin, C., and Xu, Z.: Air quality
prediction at new stations using spatially transferred bi-directional long
short-term memory network, Sci. Total Environ., 705, 135771,
https://doi.org/10.1016/j.scitotenv.2019.135771, 2020. a, b
Maleki, H., Sorooshian, A., Goudarzi, G., Baboli, Z., Tahmasebi Birgani, Y.,
and Rahmati, M.: Air pollution prediction by using an artificial neural
network model, Clean Technol. Envir., 21, 1341–1352,
https://doi.org/10.1007/s10098-019-01709-w,
2019. a
Met Office: Cartopy: a cartographic python library with a Matplotlib
interface, Exeter, Devon, available at: https://scitools.org.uk/cartopy (last access: 18 December 2020),
2010–2015. a
Mills, G., Sharps, K., Simpson, D., Pleijel, H., Broberg, M., Uddling, J.,
Jaramillo, F., Davies, W. J., Dentener, F., Van den Berg, M., Agrawal, M.,
Agrawal, S., Ainsworth, E. A., Büker, P., Emberson, L., Feng, Z., Harmens,
H., Hayes, F., Kobayashi, K., Paoletti, E., and Van Dingenen, R.: Ozone
pollution will compromise efforts to increase global wheat production, Glob.
Change Biol., 24, 3560–3574, https://doi.org/10.1111/gcb.14157,
2018. a
Murphy, A. H.: Skill Scores Based on the Mean Square Error and Their
Relationships to the Correlation Coefficient, Mon. Weather Rev., 116,
2417–2424, https://doi.org/10.1175/1520-0493(1988)116<2417:SSBOTM>2.0.CO;2,
1988. a, b, c, d
Murphy, A. H. and Winkler, R. L.: A General Framework for Forecast
Verification, Mon. Weather Rev., 115, 1330–1338,
https://doi.org/10.1175/1520-0493(1987)115<1330:AGFFFV>2.0.CO;2,
1987. a, b, c, d
Murphy, A. H., Brown, B. G., and Chen, Y.-S.: Diagnostic Verification of
Temperature Forecasts, Weather Forecast., 4, 485–501,
https://doi.org/10.1175/1520-0434(1989)004<0485:DVOTF>2.0.CO;2,
1989. a, b
Olszyna, K., Luria, M., and Meagher, J.: The correlation of temperature and
rural ozone levels in southeastern USA, Atmos. Environ., 31, 3011–3022, https://doi.org/10.1016/S1352-2310(97)00097-6,
1997. a
Pawlak, I. and Jarosławski, J.: Forecasting of Surface Ozone
Concentration by Using Artificial Neural Networks in Rural and
Urban Areas in Central Poland, Atmosphere, 10, 52,
https://doi.org/10.3390/atmos10020052,
2019. a
Prybutok, V. R., Yi, J., and Mitchell, D.: Comparison of neural network models
with ARIMA and regression models for prediction of Houston's daily maximum
ozone concentrations, Eur. J. Oper. Res., 122, 31–40, https://doi.org/10.1016/S0377-2217(99)00069-7,
2000. a
Rasp, S. and Lerch, S.: Neural Networks for Postprocessing Ensemble
Weather Forecasts, Mon. Weather Rev., 146, 3885–3900,
https://doi.org/10.1175/MWR-D-18-0187.1,
2018. a
Sayeed, A., Choi, Y., Eslami, E., Lops, Y., Roy, A., and Jung, J.: Using a deep
convolutional neural network to predict 2017 ozone concentrations, 24 hours
in advance, Neural Networks, 121, 396–408,
https://doi.org/10.1016/j.neunet.2019.09.033,
2020. a, b, c, d
Schmidhuber, J.: Deep learning in neural networks: An overview, Neural
Networks, 61, 85–117, https://doi.org/10.1016/j.neunet.2014.09.003,
2015. a
Schultz, M. G., Schröder, S., Lyapina, O., Cooper, O., Galbally, I.,
Petropavlovskikh, I., Von Schneidemesser, E., Tanimoto, H., Elshorbany, Y.,
Naja, M., Seguel, R., Dauert, U., Eckhardt, P., Feigenspahn, S., Fiebig, M.,
Hjellbrekke, A.-G., Hong, Y.-D., Christian Kjeld, P., Koide, H., Lear, G.,
Tarasick, D., Ueno, M., Wallasch, M., Baumgardner, D., Chuang, M.-T.,
Gillett, R., Lee, M., Molloy, S., Moolla, R., Wang, T., Sharps, K., Adame,
J. A., Ancellet, G., Apadula, F., Artaxo, P., Barlasina, M., Bogucka, M.,
Bonasoni, P., Chang, L., Colomb, A., Cuevas, E., Cupeiro, M., Degorska, A.,
Ding, A., Fröhlich, M., Frolova, M., Gadhavi, H., Gheusi, F., Gilge, S.,
Gonzalez, M. Y., Gros, V., Hamad, S. H., Helmig, D., Henriques, D.,
Hermansen, O., Holla, R., Huber, J., Im, U., Jaffe, D. A., Komala, N.,
Kubistin, D., Lam, K.-S., Laurila, T., Lee, H., Levy, I., Mazzoleni, C.,
Mazzoleni, L., McClure-Begley, A., Mohamad, M., Murovic, M., Navarro-Comas,
M., Nicodim, F., Parrish, D., Read, K. A., Reid, N., Ries, L., Saxena, P.,
Schwab, J. J., Scorgie, Y., Senik, I., Simmonds, P., Sinha, V., Skorokhod,
A., Spain, G., Spangl, W., Spoor, R., Springston, S. R., Steer, K.,
Steinbacher, M., Suharguniyawan, E., Torre, P., Trickl, T., Weili, L.,
Weller, R., Xu, X., Xue, L., and Zhiqiang, M.: Tropospheric Ozone Assessment
Report: Database and Metrics Data of Global Surface Ozone Observations,
Elementa, 5, 58, https://doi.org/10.1525/elementa.244,
2017. a, b
Seabold, S. and Perktold, J.: Statsmodels: Econometric and statistical
modeling with python, in: Proceedings of the 9th Python in Science Conference, 28 June–3 July,
Austin, Texas, 92–96, https://doi.org/10.25080/Majora-92bf1922-011, 2010. a
Seinfeld, J. H. and Pandis, S. N.: Atmospheric Chemistry and Physics: From Air
Pollution to Climate Change, Wiley, Hoboken, New
Jersey, USA, 2016. a
Seltzer, K. M., Shindell, D. T., Kasibhatla, P., and Malley, C. S.: Magnitude, trends, and impacts of ambient long-term ozone exposure in the United States from 2000 to 2015, Atmos. Chem. Phys., 20, 1757–1775, https://doi.org/10.5194/acp-20-1757-2020, 2020. a, b
Silva, S. J., Heald, C. L., Ravela, S., Mammarella, I., and Munger, J. W.: A
Deep Learning Parameterization for Ozone Dry Deposition
Velocities, Geophys. Res. Lett., 46, 983–989,
https://doi.org/10.1029/2018GL081049,
2019. a
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. a
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D.,
Erhan, D., Vanhoucke, V., and Rabinovich, A.: Going deeper with convolutions,
in: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), Boston, MA, USA, 7–12 June 2015,
1–9,
https://doi.org/10.1109/CVPR.2015.7298594,
2015. a, b, c, d
Thompson, M. L., Reynolds, J., Cox, L. H., Guttorp, P., and Sampson, P. D.: A
review of statistical methods for the meteorological adjustment of
tropospheric ozone, Atmos. Environ., 35, 617–630,
https://doi.org/10.1016/S1352-2310(00)00261-2,
2001. a
US Environmental Protection Agency: Technical Assistance Document for
the Reporting of Daily Air Quality – the Air Quality Index
(AQI), available at:
https://www.airnow.gov/sites/default/files/2018-05/aqi-technical-assistance-document-may2016.pdf (last access: 18 December 2020),
2016. a
Vautard, R.: Evaluation of the meteorological forcing used for the Air
Quality Model Evaluation International Initiative (AQMEII) air
quality simulations, Atmos. Environ., 53, 15–37,
https://doi.org/10.1016/j.atmosenv.2011.10.065,
2012. a
von Kuhlmann, R., Lawrence, M. G., Crutzen, P. J., and Rasch, P. J.: A model
for studies of tropospheric ozone and nonmethane hydrocarbons: Model
description and ozone results, J. Geophys. Res.-Atmos.,
108,
D9,
https://doi.org/10.1029/2002JD002893,
2003. a
Wang, Y., Jacob, D. J., and Logan, J. A.: Global simulation of tropospheric
O3-NOx-hydrocarbon chemistry: 1. Model formulation, J. Geophys.
Res.-Atmospheres, 103, 10713–10725, https://doi.org/10.1029/98JD00158,
1998a. a
Wang, Y., Logan, J. A., and Jacob, D. J.: Global simulation of tropospheric
O3-NOx-hydrocarbon chemistry: 2. Model evaluation and global ozone budget,
J. Geophys. Res.-Atmos., 103, 10727–10755,
https://doi.org/10.1029/98JD00157,
1998b. a
WHO: Health risks of air pollution in Europe – HRAPIE project,
Recommendations for concentration-response functions for cost-benefit
analysis of particulate matter, ozone and nitrogen dioxide, Technical Report, WHO
Regional Office for Europe, Copenhagen,
Denmark, available at:
http://www.euro.who.int/__data/assets/pdf_file/0006/238956/Health_risks_air_pollution_HRAPIE_project.pdf?ua=1, (last access: 18 December 2020),
2013. a
Yan, Y., Pozzer, A., Ojha, N., Lin, J., and Lelieveld, J.: Analysis of European ozone trends in the period 1995–2014, Atmos. Chem. Phys., 18, 5589–5605, https://doi.org/10.5194/acp-18-5589-2018, 2018.
a
Zhang, Q., Lam, J. C., Li, V. O., and Han, Y.: Deep-AIR: A Hybrid
CNN-LSTM Framework for Fine-Grained Air Pollution Forecast,
arXiv [preprint], arXiv:2001.11957,
2020. a, b
Short summary
With IntelliO3-ts v1.0, we present an artificial neural network as a new forecasting model for daily aggregated near-surface ozone concentrations with a lead time of up to 4 d. We used measurement and reanalysis data from more than 300 German monitoring stations to train, fine tune, and test the model. We show that the model outperforms standard reference models like persistence models and demonstrate that IntelliO3-ts outperforms climatological reference models for the first 2 d.
With IntelliO3-ts v1.0, we present an artificial neural network as a new forecasting model for...