The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Forecasting air quality time series using deep learning
Open accessAbstract
This paper presents one of the first applications of deep learning (DL) techniques to predict air pollution time series. Air quality management relies extensively on time series data captured at air monitoring stations as the basis of identifying population exposure to airborne pollutants and determining compliance with local ambient air standards. In this paper, 8 hr averaged surface ozone (O3) concentrations were predicted using deep learning consisting of a recurrent neural network (RNN) with long short-term memory (LSTM). Hourly air quality and meteorological data were used to train and forecast values up to 72 hours with low error rates. The LSTM was able to forecast the duration of continuous O3 exceedances as well. Prior to training the network, the dataset was reviewed for missing data and outliers. Missing data were imputed using a novel technique that averaged gaps less than eight time steps with incremental steps based on first-order differences of neighboring time periods. Data were then used to train decision trees to evaluate input feature importance over different time prediction horizons. The number of features used to train the LSTM model was reduced from 25 features to 5 features, resulting in improved accuracy as measured by Mean Absolute Error (MAE). Parameter sensitivity analysis identified look-back nodes associated with the RNN proved to be a significant source of error if not aligned with the prediction horizon. Overall, MAE's less than 2 were calculated for predictions out to 72 hours.Implications: Novel deep learning techniques were used to train an 8-hour averaged ozone forecast model. Missing data and outliers within the captured data set were replaced using a new imputation method that generated calculated values closer to the expected value based on the time and season. Decision trees were used to identify input variables with the greatest importance. The methods presented in this paper allow air managers to forecast long range air pollution concentration while only monitoring key parameters and without transforming the data set in its entirety, thus allowing real time inputs and continuous prediction.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
(2014) · Cited by 33,419
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 20,825
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
(2016) · Cited by 11,679
Proceedings of the 24th international conference on Machine learning
(2007) · doi:10.1145/1273496 · Cited by 11,630
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“RNNs have been used in many time-series applications, including speech recognition (Graves, Mohamed, and Hinton 2013), electricity load forecasting (Walid and Alamsyah 2017), and air pollution (Fan et al. 2017; Gomez et al. 2003).”
MethodChai, T., & Draxler, R. R. (2014) · Geoscientific Model Development · doi:10.5194/gmd-7-1247-2014 · Cited by 8,761 · cited 1×
“MAE and RMSE are widely used measures of continuous variables, with RMSE criticized for overbiasing toward large errors (Chai and Draxler 2014; Willmott and Matsuura 2005).”
Method(2010) · Cited by 8,261
Willmott, C., & Matsuura, K. (2005) · Climate Research · doi:10.3354/cr030079 · Cited by 7,958 · cited 1×
“MAE and RMSE are widely used measures of continuous variables, with RMSE criticized for overbiasing toward large errors (Chai and Draxler 2014; Willmott and Matsuura 2005).”
MethodOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310
(2013) · Cited by 3,740
Gardner, M. W., & Dorling, S. R. (1998) · Atmospheric Environment · doi:10.1016/s1352-2310(97)00447-0 · Cited by 3,324
Generating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894
Recurrent Neural Networks for Multivariate Time Series with Missing Values
Che, Z., Purushotham, S., Cho, K., Sontag, D., & Liu, Y. (2018) · Scientific Reports · doi:10.1038/s41598-018-24271-9 · Cited by 2,370
Classification and regression trees
Loh, W. (2011) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.8 · Cited by 2,285
Practical Recommendations for Gradient-Based Training of Deep Architectures
Bengio, Y. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_26 · Cited by 2,259 · cited 1×
“Previous models using ANNs could assume that some historical essence of the data was incorporated into the weights during updating as long as the training data were fed in temporal order and not shuffled as most categorical applications are (Bengio 2012).”
MethodIncorporating Nesterov Momentum into Adam
Dozat, T. (2016) · Cited by 1,595
Static Analysis of Shape in TensorFlow Programs
The Theano Development Team, Al‐Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., et al. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2020.15 · Cited by 1,589
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
Gal, Y., & Ghahramani, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.05287 · Cited by 766
What controls tropospheric ozone?
Lelieveld, J., & Dentener, F. J. (2000) · Journal of Geophysical Research: Atmospheres · doi:10.1029/1999jd901011 · Cited by 731
Raschka, S. (2015) · Cited by 731
Methods for imputation of missing values in air quality data sets
Junninen, H., Niska, H., Tuppurainen, K., Ruuskanen, J., & Kolehmainen, M. (2004) · Atmospheric Environment · doi:10.1016/j.atmosenv.2004.02.026 · Cited by 662
A large atomic chlorine source inferred from mid-continental reactive nitrogen chemistry
Thornton, J. A., Kercher, J. P., Riedel, T. P., Wagner, N. L., Cozic, J., Holloway, J. S., Dubé, W. P., Wolfe, G. M., Quinn, P. K., Middlebrook, A. M., et al. (2010) · Nature · doi:10.1038/nature08905 · Cited by 652
Nighttime radical observations and chemistry
Brown, S. S., & Stutz, J. (2012) · Chemical Society Reviews · doi:10.1039/c2cs35181a · Cited by 637
Exploring Sparsity in Recurrent Neural NetworksPreprint
Narang, S., Elsen, E., Diamos, G., & Sengupta, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.05119 · Cited by 337
Malley, C. S., Henze, D. K., Kuylenstierna, J. C. I., Vallack, H. W., Davila, Y., Anenberg, S. C., Turner, M. C., & Ashmore, M. R. (2017) · Environmental Health Perspectives · doi:10.1289/ehp1390 · Cited by 305 · cited 1×
“More than 21,000 premature deaths in Europe are attributed annually to O 3 exposure (Amann et al. 2008), with more than 1.1 million deaths worldwide — more than 20% of all deaths attributed to respiratory diseases (Malley et al. 2017).”
BackgroundInfluentialRecursive neural network model for analysis and forecast of PM10 and PM2.5
Biancofiore, F., Busilacchio, M., Verdecchia, M., Tomassetti, B., Aruffo, E., Bianco, S., Di Tommaso, S., Colangeli, C., Rosatelli, G., & Di Carlo, P. (2017) · Atmospheric Pollution Research · doi:10.1016/j.apr.2016.12.014 · Cited by 305
Atmospheric Chemistry of Tropospheric Ozone Formation: Scientific and Regulatory Implications
Finlayson-Pitts, B. J., & Pitts, J. N. (1993) · Air & Waste · doi:10.1080/1073161x.1993.10467187 · Cited by 244
Imputation of missing data in time series for air pollutants
Junger, W. L., & Ponce de Leon, A. (2015) · Atmospheric Environment · doi:10.1016/j.atmosenv.2014.11.049 · Cited by 241
Voukantsis, D., Karatzas, K., Kukkonen, J., Räsänen, T., Karppinen, A., & Kolehmainen, M. (2011) · Science of The Total Environment · doi:10.1016/j.scitotenv.2010.12.039 · Cited by 240
Identifying pollution sources and predicting urban air quality using ensemble learning methods
Singh, K. P., Gupta, S., & Rai, P. (2013) · Atmospheric Environment · doi:10.1016/j.atmosenv.2013.08.023 · Cited by 224
ALALAWI, S., ABDULWAHAB, S., & BAKHEIT, C. (2008) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2006.08.007 · Cited by 200
A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN
Fan, J., Li, Q., Hou, J., Feng, X., Karimian, H., & Lin, S. (2017) · ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-annals-iv-4-w2-15-2017 · Cited by 181
The Mechanisms of Reactions Influencing Atmospheric Ozone
Calvert, J. G., Orlando, J. J., Stockwell, W. R., & Wallington, T. J. (2015) · Oxford University Press eBooks · doi:10.1093/oso/9780190233020.001.0001 · Cited by 176
Linear and nonlinear modeling approaches for urban air quality prediction
Singh, K. P., Gupta, S., Kumar, A., & Shukla, S. P. (2012) · Science of The Total Environment · doi:10.1016/j.scitotenv.2012.03.076 · Cited by 174
Health risks of ozone from long-range transboundary air pollution.
Amann, M. C. (2008) · HAL · Cited by 170
Elangasinghe, A., Singhal, N., Dirks, K. N., Salmond, J., & Samarasinghe, S. (2014) · Atmospheric Environment · doi:10.1016/j.atmosenv.2014.04.051 · Cited by 154
Yu, F., Zhang, W., Sun, D., & Zhang, L. (2011) · Atmospheric Environment · doi:10.1016/j.atmosenv.2011.01.022 · Cited by 145
A novel hybrid forecasting model for PM10 and SO2 daily concentrations
Wang, P., Liu, Y., Qin, Z., & Zhang, G. (2014) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2014.10.078 · Cited by 144
Decision tree approach for classification and dimensionality reduction of electronic nose data
Cho, J. H., & Kurup, P. (2011) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2011.08.027 · Cited by 142
Arhami, M., Kamali, N., & Rajabi, M. M. (2013) · Environmental Science and Pollution Research · doi:10.1007/s11356-012-1451-6 · Cited by 139
Cooper, O. R., Stohl, A., Trainer, M., Thompson, A. M., Witte, J. C., Oltmans, S. J., Morris, G. A., Pickering, K., Crawford, J. H., Chen, G., et al. (2006) · Journal of Geophysical Research Atmospheres · doi:10.1029/2006jd007306 · Cited by 128
de Oña, J., & Garrido, C. (2014) · Neural Computing and Applications · doi:10.1007/s00521-014-1573-5 · Cited by 124
The effects of ozone action day public advisories on train ridership in Chicago
Welch, E. W., Xiaohua, G., & Kramer, L. (2005) · Transportation Research Part D Transport and Environment · doi:10.1016/j.trd.2005.06.002 · Cited by 43
Wang, Y., Ma, X., & Joyce, M. J. (2016) · Renewable Energy · doi:10.1016/j.renene.2016.06.006 · Cited by 39
Detection of outliers in functional time series
Raña, P., Aneiros, G., & Fernández, J. M. V. (2015) · Environmetrics · doi:10.1002/env.2327 · Cited by 30
Ozone in the troposphere: Measurements, climatology, budget, and trends
Tarasick, D. W., & Slater, R. (2008) · ATMOSPHERE-OCEAN · doi:10.3137/ao.460105 · Cited by 29
Forecasting of ozone pollution using artificial neural networks
Ettouney, R. S., Mjalli, F. S., Zaki, J. G., El-Rifai, M. A., & ETTOUNEY, H. M. (2009) · Management of Environmental Quality An International Journal · doi:10.1108/14777830910990843 · Cited by 23
Local Maximum Ozone Concentration Prediction Using Soft Computing Methodologies
Gómez, P., Àngela Nebot, B., Ribeiro, S., Alquézar, R., Mugica, F., & Wotawa, F. (2003) · Systems Analysis Modelling Simulation · doi:10.1080/0232929031000081244 · Cited by 22
Ground-level ozone prediction using multilayer perceptron trained with an innovative hybrid approach
Wang, D., & Lu, J. W. Z. (2006) · Ecological Modelling · doi:10.1016/j.ecolmodel.2006.05.031 · Cited by 15
Achcar, J. A., Rodrigues, E. R., & Tzintzun, G. (2011) · Brazilian Journal of Probability and Statistics · doi:10.1214/10-bjps116 · Cited by 13
Mapping air quality zones for coastal urban centers
Freeman, B. S., Gharabaghi, B., Thé, J. V. G., Munshed, M., Faisal, S., Abdullah, M. M., & Aseed, A. A. (2016) · Journal of the Air & Waste Management Association · doi:10.1080/10962247.2016.1265025 · Cited by 11
Self-citationModeling the Time Between Ozone Exceedances
Rodrigues, E. R., & Achcar, J. A. (2012) · SpringerBriefs in mathematics · doi:10.1007/978-1-4614-4645-3_4 · Cited by 2
Cited by
Deep learning in environmental remote sensing: Achievements and challenges
Yuan, Q., Shen, H., Li, T., Li, Z., Li, S., Jiang, Y., Xu, H., Tan, W., Yang, Q., Wang, J., et al. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.111716 · Cited by 1,697
Deep Learning for Time Series Forecasting: A Survey
Torres, J. F., Hadjout, D., Sebaa, A., Martínez-Álvarez, F., & Troncoso, A. (2021) · Big Data · doi:10.1089/big.2020.0159 · Cited by 818
Transductive LSTM for time-series prediction: An application to weather forecasting
Karevan, Z., & Suykens, J. A. K. (2020) · Neural Networks · doi:10.1016/j.neunet.2019.12.030 · Cited by 578
Nguyen, H. D., Tran, K. P., Thomassey, S., & Hamad, M. (2021) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2020.102282 · Cited by 494
A review of artificial neural network models for ambient air pollution prediction
Cabaneros, S. M., Calautit, J. K., & Hughes, B. R. (2019) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2019.06.014 · Cited by 459
Metadata
- Authors
- Freeman, B. S., Taylor, G., Gharabaghi, B., & Thé, J.
- Venue
- Journal of the Air & Waste Management Association
- Publisher
- Informa UK Limited
- Published
- 2018-05-24
- Volume
- 68
- Issue
- 8
- Pages
- 866-886
- ISSN
- 1047-3289 (ISSN-L)
- 1096-2247
- 2162-2906
- OpenAlex
- W2803892188
- Cited by
- 319
- References
- 56
- FWCI
- 13.07
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.