Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication

Journal of Exposure Science & Environmental Epidemiology volume 31, pages 170–176 (2021)Cite this article

Abstract

Background

Wildland fire (wildfire; bushfire) pollution contributes to poor air quality, a risk factor for premature death. The frequency and intensity of wildfires are expected to increase; improved tools for estimating exposure to fire smoke are vital. New-generation satellite-based sensors produce high-resolution spectral images, providing real-time information of surface features during wildfire episodes. Because of the vast size of such data, new automated methods for processing information are required.

Objective

We present a deep fully convolutional neural network (FCN) for predicting fire smoke in satellite imagery in near-real time (NRT).

Methods

The FCN identifies fire smoke using output from operational smoke identification methods as training data, leveraging validated smoke products in a framework that can be operationalized in NRT. We demonstrate this for a fire episode in Australia; the algorithm is applicable to any geographic region.

Results

The algorithm has high classification accuracy (99.5% of pixels correctly classified on average) and precision (average intersection over union = 57.6%).

Significance

The FCN algorithm has high potential as an exposure-assessment tool, capable of providing critical information to fire managers, health and environmental agencies, and the general public to prevent the health risks associated with exposure to hazardous smoke from wildland fires in NRT.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Satellite imagery and target data.
Fig. 2: Deep fully convolutional network architecture.
Fig. 3: FCN input and output.

Similar content being viewed by others

References

  1. Naeher LP, Brauer M, Lipsett M, Zelikoff JT, Simpson CD, Koenig JQ, et al. Woodsmoke health effects: a review. Inhalation Toxicol. 2007;19:67–106.

    Article  CAS  Google Scholar 

  2. Wettstein ZS, Hoshiko S, Fahimi J, Harrison RJ, Cascio WE, Rappold AG. Cardiovascular and cerebrovascular emergency department visits associated with wildfire smoke exposure in California in 2015. J Am Heart Assoc. 2018;7:e007492.

    Article  Google Scholar 

  3. Rappold AG, Stone SL, Cascio WE, Neas LM, Kilaru VJ, Carraway MS, et al. Peat bog wildfire smoke exposure in rural North Carolina is associated with cardiopulmonary emergency department visits assessed through syndromic surveillance. Environmental Health Perspect. 2011;119:1415–20.

    Article  Google Scholar 

  4. Reid CE, Brauer M, Johnston FH, Jerrett M, Balmes JR, Elliott CT. Critical review of health impacts of wildfire smoke exposure. Environ Health Perspect. 2016;124:1334–43.

    Article  Google Scholar 

  5. Johnston FH, Henderson SB, Chen Y, Randerson JT, Marlier M, DeFries RS, et al. Estimated global mortality attributable to smoke from landscape fires. Environ Health Perspect. 2012;120:695–701.

    Article  Google Scholar 

  6. Fann N, Alman B, Broome RA, Morgan GG, Johnston FH, Pouliot G, et al. The health impacts and economic value of wildland fire episodes in the. Sci Total Environ. 2018;610-611:802–9.

    Article  CAS  Google Scholar 

  7. U.S. Environmental Protection Agency. AirNow. https://airnow.gov/. last accessed on 07/13/2020.

  8. EPA Victoria. EPA AirWatch—Environment Protection Authority Victoria. https://www.epa.vic.gov.au/EPAAirWatch/. last accessed on 07/13/2020.

  9. Qin Y, Steven ADL, Schroeder T, McVicar TR, Huang J, Cope M, et al. Cloud cover in the australian region: development and validation of a cloud masking, classification and optical depth retrieval algorithm for the advanced Himawari imager. Front Environ Sci. 2019;7:20.

    Article  Google Scholar 

  10. Mazzoni D, Garay MJ, Davies R, Nelson D. An operational MISR pixel classifier using support vector machines. Remote Sens Environ. 2007;107:149–58.

    Article  Google Scholar 

  11. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2015;3431–40.

  12. Iglovikov V, Accord T, Mushinskiy S, Aerostate VO. Satellite imagery feature detection using deep convolutional neural network: a kaggle competition. ArXiv. 2017; arXiv:1706.06169.

  13. Marmanis D, Wegner JD, Galliani S, Schindler K, Datcu M, Stilla U. Semantic segmentation of aerial images with an ensemble of CNNS. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume III-3, 2016, pp. 473–80.

  14. Zhang L, Zhang L, Kumar V. Deep learning for remote sensing. Data IEEE Geosci Remote Sens Mag. 2016;4:22–40.

    Article  Google Scholar 

  15. Henry C, Majid Azimi S, Merkle N. Road segmentation in SAR satellite images with deep fully-convolutional neural networks. ArXiv. 2018; arXiv:1802.01445. https://doi.org/10.1109/LGRS.2018.2864342.

  16. Huang H, Deng J, Lan Y, Yang A, Deng X, Zhang L. A fully convolutional network for weed mapping of unmanned aerial vehicle (UAV) imagery. PLoS ONE 2018;13:e0196302. https://doi.org/10.1371/journal.pone.0196302.

  17. Li R, Liu W, Yang L, Sun S, Hu W, Zhang F, et al. DeepUNet: a deep fully convolutional network for pixel-level sea-land segmentation. ArXiv. 2017; arXiv:1709.00201.

  18. Rizaldy A, Persello C, Gevaert CM, Oude Elberink SJ. Fully convolutional networks for ground classification from lidar point clouds. In 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy (2 ed., Vol. 4, pp. 231–238). (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. IV-2). Riva Del Garda: International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-annals-IV-2-231-2018.

  19. Metorological Science Center (MSC) of the Japan Meteorological Agency (JMA). JMA/MSC: Himawari-8/9 imager (AHI). http://www.data.jma.go.jp/mscweb/en/himawari89/space_segment/spsg_ahi.html. Last accessed 07/13/2020.

  20. National Aeronautics and Space Administration (NASA). Active Fire Data—Earthdata. https://earthdata.nasa.gov/earth-observation-data/near-real-time/firms/active-fire-data. Last Accessed 07/13/2020.

  21. Qin Y, Mitchell R, Forgan BW. Characterizing the aerosol and surface reflectance over australia using AATSR. IEEE Trans Geosci Remote Sens. 2015;53:6163–82.

    Article  Google Scholar 

  22. Broome RA, Johnston FH, Horsley J, Morgan GG. A rapid assessment of the impact of hazard reduction burning around Sydney. Med J Aust. 2016;205:407–8.

    Article  Google Scholar 

  23. Horsley JA, Broome RA, Johnston FH, Cope M, Morgan GG. Health burden associated with fire smoke in Sydney, 2001-2013. Med J Aust. 2018;208:309–10.

    Article  Google Scholar 

Download references

Acknowledgements

This research is being supported by funding from the Joint Fire Science Program. Ivan Hannigan was supported by funding from The Centre for Air Pollution, Energy and Health Research (www.car-cre.org.au, an Australian National Health and Medical Research Council funded Centre for Research Excellence, APP1030259), and by funding from the United States Department of the Interior and the United States Fire Service through the Joint Fire Science Program (ID: 14-1-04-9).

Author information

Authors and Affiliations

  1. Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA

    Alexandra Larsen

  2. The University of Sydney, University Centre for Rural Health, School of Public Health, Sydney, NSW, Australia

    Ivan Hanigan & Geoffrey Morgan

  3. Centre for Air Pollution, Energy and Health Research (CAR), Woolcock Institute of Medical Research, Sydney, NSW, Australia

    Ivan Hanigan & Geoffrey Morgan

  4. Centre for Research and Action in Public Health, University of Canberra, Canberra, ACT, Australia

    Ivan Hanigan

  5. Department of Statistics, North Carolina State University, Raleigh, NC, USA

    Brian J. Reich

  6. Oceans and Atmosphere Research, Commonwealth Science and Industrial Research Organisation, Victoria, Australia

    Yi Qin & Martin Cope

  7. U.S. Environmental Protection Agency, Center for Public Health and Environmental Assessment, Office of Research and Development, Research Triangle Park, NC, USA

    Ana G. Rappold

Authors
  1. Alexandra Larsen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ivan Hanigan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Brian J. Reich
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yi Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Martin Cope
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Geoffrey Morgan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ana G. Rappold
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ana G. Rappold.

Ethics declarations

Conflict of interest

The research described in this article has been reviewed by the Center for Public Health and Environmental Assessment, U.S. Environmental Protection Agency and approved for publication. Approval does not signify that the contents necessarily reflect the views and the policies of the Agency, nor does mention of trade names of commercial products constitute endorsement or recommendation for use. The authors declare that they have no conflict of interest.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Larsen, A., Hanigan, I., Reich, B.J. et al. A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication. J Expo Sci Environ Epidemiol 31, 170–176 (2021). https://doi.org/10.1038/s41370-020-0246-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41370-020-0246-y

Keywords

This article is cited by

Search

Advanced search

Quick links