Random Forest Spatial-Temporal and State Space Models to Assess the Impact of Bushfire-Induced Aerosol Events on Ozone Depletion in Australia
Source abstract
Abstract
Serious concerns exist that the increasing frequency of fires may delay the recovery of ozone given increasing temperatures due to climate change. Australian bushfires from September 2019 to February 2020 were catastrophic. A random forest spatial-temporal (RF sp) analysis using satellite data to detect an association between Australian bushfires and stratosphere ozone on the local depletion of ozone in the vicinity of fires in three regions of Australia (Pacific Ocean, Victoria, NSW) has shown a significant reduction in ozone attributable to aerosols from fires. By intervention analysis, increases in aerosols in all three regions were shown to have a significant and ongoing impact 1–5 days later on reducing ozone (p < 0.0001). Intervention analysis also gave similar periods of aerosol exceedance to those found by Hidden Markov models (HMMs). HMMs established a significant and quantifiable decline in ozone due to bushfire-induced aerosols, with significant lags of 10–25 days between times of aerosol exceedance and subsequent ozone level decline in all three regions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Quality and Health Impacts · Atmospheric chemistry and aerosols · Atmospheric and Environmental Gas Dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mathematical Sciences, School of Science, Royal Melbourne Institute of Technology (RMIT), Melbourne, VIC 3000, Australia
Department of Mathematical Sciences, Royal Melbourne Institute of Technology (RMIT), Melbourne, VIC 3000, Australia
School of Computer Science and Information Technology, Royal Melbourne Institute of Technology (RMIT), Melbourne, VIC 3000, Australia
References (78)
Show source-provided references
1. Binskin, M., Bennett, A., and Macintosh, A. (2020). The Royal Commission into National Natural Disaster Arrangements Report, Final Report.
2. Australian Institute of Health and Welfare (2022, June 22). Australian Bushfires 2019–20: Exploring the Short-Term Health Impacts, Available online: https://www.aihw.gov.au/reports/environment-and-health/short-term-health-impacts-2019-20-bushfires/related-material.
3. WWF (2022, May 30). Australian Bushfire Fund Final Report; WWF: April 2022, 15 pages. Available online: https://www.worldwildlife.org/publications/australia-bushfire-fund-final-report#:~:text=The%20scale%20of%20Australia’s%20bushfires,forests%20and%20wildlife%20was%20immense.
4. Lee, M. (2021, July 20). Australia’s Bushfires Could Drive More Than 700 Animal Species to Extinction. Check the Numbers for Yourself. The Conversation. Available online: https://theconversation.com/australias-bushfires-could-drive-more-than-700-animal-species-to-extinction-check-the-numbers-for-yourself-129773.
5. Ecological consequences of Australia’s “Black Summer” bushfires: Managing for recovery10.1002/ieam.4496 ↗
6. Impact of 2019–2020 mega-fires on Australian fauna habitat10.1038/s41559-020-1251-1 ↗
7. Impacts of the 2019–2020 bushfires on New South Wales biodiversity: A rapid assessment of distribution data for selected invertebrate taxa10.3853/j.1835-4211.32.2020.1768 ↗
8. Shukla, P.R., Skea, J., Calvo Buendia, E., Masson-Delmotte, V., Portner, H.-O., Roberts, D.C., Zhai, P., Slade, R., Connors, S., and van Diemen, R. (2022). Climate Change and Land: IPCC Special Report on Climate Change, Desertification, Land Degradation, Sustainable Land Management, Food Security, and Greenhouse Gas Fluxes in Terrestrial Ecosystems, Cambridge Universiyt Press.
9. Impacts of aerosol direct effects on tropospheric ozone through changes in atmospheric dynamics and photolysis rates10.5194/acp-17-9869-2017 ↗
10. A study of the effect of aerosols on surface ozone through meteorology feedbacks over China10.5194/acp-21-5705-2021 ↗
11. Individual aerosol particles from biomass burning in southern Africa: 2, Compositions and aging of inorganic particles10.1029/2002JD002310 ↗
12. Soot and sulfate aerosol particles in the remote marine troposphere10.1029/1999JD900208 ↗
13. Air quality and health impact of 2019–20 Black Summer megafires and COVID-19 lockdown in Melbourne and Sydney, Australia10.1016/j.envpol.2021.116498 ↗
14. Some personal reflections on the present and future of Australia’s fauna in an increasingly fire-prone continent10.1111/emr.12403 ↗
15. Persistent Stratospheric Warming Due to 2019–2020 Australian Wildfire Smoke10.1029/2021GL092609 ↗
16. Australia’s Black Summer pyrocumulonimbus super outbreak reveals potential for increasingly extreme stratospheric smoke events10.1038/s41612-021-00192-9 ↗
17. Prolonged and Pervasive Perturbations in the Composition of the Southern Hemisphere Midlatitude Lower Stratosphere From the Australian New Year’s Fires10.1029/2021GL096270 ↗
18. depmixS4: An R Package for Hidden Markov Models10.18637/jss.v036.i07 ↗
19. Chlorine activation and enhanced ozone depletion induced by wildfire aerosol10.1038/s41586-022-05683-0 ↗
20. Wildfire smoke destroys stratospheric ozone10.1126/science.abm5611 ↗
21. Black carbon lofts wildfire smoke high into the stratosphere to form a persistent plume10.1126/science.aax1748 ↗
22. Mersmann, K., Stein, T., Carlowicz, M., and Allen, J. (2022, April 09). Ozone Hole Is Smallest Since 1988. NASA Earth Observatory, Available online: https://earthobservatory.nasa.gov/images/91212/ozone-hole-is-smallest-since-1988.
23. New spatial analyses of Australian wildfires highlight the need for new fire, resource, and conservation policies10.1073/pnas.2002269117 ↗
24. 2019–2020 Australian bushfire air particulate pollution and impact on the South Pacific Ocean10.1038/s41598-021-91547-y ↗
25. On the stratospheric chemistry of midlatitude wildfire smoke10.1073/pnas.2117325119 ↗
26. How wildfires deplete ozone in the stratosphere10.1038/d41586-023-00598-w ↗
27. Random forest as a generic framework for predictive modeling of spatial and spatiotemporal variables10.7717/peerj.5518 ↗
28. Shumway, R.H., Stoffer, D.S., and Stoffer, D.S. (2017). Time Series Analysis and Its Applications, Springer.10.1007/978-3-319-52452-8 ↗
29. Lopo, A.B., Spyrides, M.H.C., Lucio, P.S., and Sigró, J. (2014). UV Index Modeling by Autoregressive Distributed Lag (ADL Model). Atmos. Clim. Sci.10.4236/acs.2014.42033 ↗
30. Global increase in UV irradiance during the past 30 years (1979–2008) estimated from satellite data10.1029/2009JD012219 ↗
31. Changes in cloud and aerosol cover (1980–2006) from reflectivity time series using SeaWiFS, N7-TOMS, EP-TOMS, SBUV-2, and OMI radiance data10.1029/2007JD009508 ↗
32. Large climate-induced changes in ultraviolet index and stratosphere-to-troposphere ozone flux10.1038/ngeo604 ↗
33. Douglass, A., Fioletov, V., Godin-Beekmann, S., Müller, R., Stolarski, R.S., Webb, A., Arola, A., Burkholder, J.B., Burrows, J.P., and Chipperfield, M.P. (2010). Scientific Assessment of Ozone Depletion: 2010, Chapter 2—Stratospheric Ozone and Surface Ultraviolet Radiation. Global Ozone Research and Monitoring Project—Report No. 52, World Meteorological Organization.
34. Jaross, G. (2022, June 14). OMPS-NPP L3 NM Ozone (O3) Total Column 1.0 Deg Grid Daily V2. Distributed by Greenbelt, MD, USA, Goddard Earth Sciences Data and Information Services Center (GES DISC). 2017. Digital Science Data, Available online: https://disc.gsfc.nasa.gov/datacollection/OMPS_NPP_NMTO3_L3_DAILY_2.html.
35. McPeters, R.D., Bhartia, P.K., Krueger, A.J., and Herman, J.R. (1998). Earth Probe Total Ozone Mapping Spectrometer (TOMS) Data Product User’s Guide.
36. Atmospheric impacts of the 2010 Russian wildfires: Integrating modeling and measurements of an extreme air pollution episode in the Moscow region10.5194/acp-11-10031-2011 ↗
37. Changepoint: An R Package for Changepoint Analysis10.18637/jss.v058.i03 ↗
38. Random forests10.1023/A:1010933404324 ↗
39. Wikle, C.K., Zammit-Mangion, A., and Cressie, N. (2019). Spatio-Temporal Statistics with R, Chapman and Hall/CRC.10.1201/9781351769723 ↗
40. Newer classification and regression tree techniques: Bagging and random forests for ecological prediction10.1007/s10021-005-0054-1 ↗
41. A random forest guided tour10.1007/s11749-016-0481-7 ↗
42. Comments on: A random forest guided tour10.1007/s11749-016-0485-3 ↗
43. Wong, S., Flegg, J.A., Golding, N., and Kandanaarachchi, S. (2023). Comparison of new computational methods for geostatistical modeling of malaria. arXiv.10.1186/s12936-023-04760-7 ↗
44. The R Journal: Classification and regression by randomForest
45. Ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R10.18637/jss.v077.i01 ↗
46. Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective. Machine Learning: A Probabilistic Perspective, MIT Press.
47. Spatial Multivariate Trees for Big Data Bayesian Regression
48. A tutorial guide to geostatistics: Computing and modeling variograms and kriging10.1016/j.catena.2013.09.006 ↗
49. FRK: An R Package for Spatial and Spatio-Temporal Prediction with Large Datasets
50. Sainsbury-Dale, M., Zammit-Mangion, A., and Cressie, N. (2022). Modelling big, heterogeneous, non-Gaussian spatial and spatiotemporal data using FRK. arXiv.
51. Quantile Regression Forests
52. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference and Prediction, Springer. [2nd ed.].10.1007/978-0-387-84858-7 ↗
53. Spatiotemporal lagging of predictors improves machine learning estimates of atmosphere–forest CO2 exchange10.5194/bg-20-897-2023 ↗
54. The Maximum Likelihood Method for Testing Changes in the Parameters of Normal Observations10.1214/aos/1176349143 ↗
55. An application of the maximum likelihood test to the change-point problem10.1016/0304-4149(94)90154-6 ↗
56. A method for cluster analysis10.2307/2528096 ↗
57. Chen, J., and Gupta, A.K. (2012). Parametric Statistical Change Point Analysis with Applications to Genetics, Medicine, and Finance, Birkhäuser Boston. [2nd ed.].10.1007/978-0-8176-4801-5 ↗
58. Wild binary segmentation for multiple change-point detection10.1214/14-AOS1245 ↗
59. Statistical Inference for Probabilistic Functions of Finite State Markov Chains10.1214/aoms/1177699147 ↗
60. Zucchini, W., MacDonald, I.L., and Langrock, R. (2016). Hidden Markov Models for Time Series—An Introduction Using R, Chapman and Hall/CRC Press. [2nd ed.].10.1201/b20790 ↗
61. Hidden Markov Item Response Theory Models for Responses and Response Times10.1080/00273171.2016.1192983 ↗
62. An introduction to hidden Markov models10.1109/MASSP.1986.1165342 ↗
63. High-order Hidden Markov Model for trend prediction in financial time series10.1016/j.physa.2018.10.053 ↗
64. A hidden Markov model for earthquake prediction10.1007/s00477-017-1457-1 ↗
65. Hidden Markov Models and their Applications in Biological Sequence Analysis10.2174/138920209789177575 ↗
66. Reynolds, D. (2015). Encyclopedia of Biometrics, Springer.
67. Alghamdi, R. (2016). Hidden Markov Models (HMMs) and Security Applications. Int. J. Adv. Comput. Sci. Appl., 7.10.14569/IJACSA.2016.070205 ↗
68. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm10.1109/TIT.1967.1054010 ↗
69. Prediction of ozone levels using a Hidden Markov Model (HMM) with Gamma distribution10.1016/j.atmosenv.2012.08.008 ↗
70. Prediction of 8 h-average ozone concentration using a supervised hidden Markov model combined with generalized linear models10.1016/j.atmosenv.2013.09.014 ↗
71. Hyndman, R.J., and Athanasopoulos, G. (2021). Forecasting: Principles and Practice, OTexts. [3rd ed.].
72. Uncovering ecological state dynamics with hidden Markov models10.1111/ele.13610 ↗
73. Intervention analysis with applications to economic and environmental problems10.1080/01621459.1975.10480264 ↗
74. Chan, K.S., and Cryer, J.D. (2008). Time Series Analysis with Applications in R, Springer.
75. Zeileis, A. (2024, October 10). dynlm: Dynamic Linear Regression, Package Version 0.3-6. Available online: https://CRAN.R-project.org/package=dynlm.
76. dLagM: An R package for distributed lag models and ARDL bounds testing10.1371/journal.pone.0228812 ↗
77. Selective review of offline change-point detection methods10.1016/j.sigpro.2019.107299 ↗
78. Rao, A.R., Wang, Q., Wang, H., Khorasgani, H., and Gupta, C. (2020, January 6–9). Spatio-Temporal Functional Neural Networks. Proceedings of the 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), Sydney, Australia.10.1109/DSAA49011.2020.00020 ↗