A marginal modelling approach for predicting wildfire extremes across the contiguous United States. (English) Zbl 07685226
Summary: This paper details a methodology proposed for the EVA 2021 conference data challenge. The aim of this challenge was to predict the number and size of wildfires over the contiguous US between 1993 and 2015, with more importance placed on extreme events. In the data set provided, over 14% of both wildfire count and burnt area observations are missing; the objective of the data challenge was to estimate a range of marginal probabilities from the distribution functions of these missing observations. To enable this prediction, we make the assumption that the marginal distribution of a missing observation can be informed using non-missing data from neighbouring locations. In our method, we select spatial neighbourhoods for each missing observation and fit marginal models to non-missing observations in these regions. For the wildfire counts, we assume the compiled data sets follow a zero-inflated negative binomial distribution, while for burnt area values, we model the bulk and tail of each compiled data set using non-parametric and parametric techniques, respectively. Cross validation is used to select tuning parameters, and the resulting predictions are shown to significantly outperform the benchmark method proposed in the challenge outline. We conclude with a discussion of our modelling framework, and evaluate ways in which it could be extended.
MSC:
| 62-XX | Statistics |
References:
| [1] | Wong, SD; Broader, JC; Shaheen, SA, Review of California wildfire evacuations from 2017 to 2019 (2020), Technical report, UC Office of the President: University of California Institute of Transportation Studies, Technical report, UC Office of the President |
| [2] | Jones, M.W., Smith, A., Betts, R., Canadell, J.G., Prentice, I.C., Le Quéré, C.: Climate change increases risk of wildfires. ScienceBrief Review (2020) |
| [3] | Zhuang, Y.; Fu, R.; Santer, BD; Dickinson, RE; Hall, A., Quantifying contributions of natural variability and anthropogenic forcings on increased fire weather risk over the western United States, Proc. Natl. Acad. Sci., 118, 45, 2111875118 (2021) · doi:10.1073/pnas.2111875118 |
| [4] | Opitz, T.: Editorial: EVA 2021 Data Competition on spatio-temporal prediction of wildfire activity in the United States. Extremes (to appear) (2022) |
| [5] | Coles, SG; Heffernan, JE; Tawn, JA, Dependence measures for extreme value analyses, Extremes, 2, 4, 339-365 (1999) · Zbl 0972.62030 · doi:10.1023/A:1009963131610 |
| [6] | Preisler, HK; Brillinger, DR; Burgan, RE; Benoit, J., Probability based models for estimation of wildfire risk, Int. J. Wildland Fire, 13, 2, 133-142 (2004) · doi:10.1071/WF02061 |
| [7] | Wuebbles, D.J., Fahey, D.W., Hibbard, K.A., Arnold, J.R., DeAngelo, B., Doherty, S., Easterling, D.R., Edmonds, J., Edmonds, T., Hall, T., et al.: Climate science special report: Fourth national climate assessment, volume I. Technical report, U.S. Global Change Research Program, Washington, DC, USA (2017). doi:10.7930/J0J964J6 |
| [8] | Holden, ZA; Swanson, A.; Luce, CH; Jolly, WM; Maneta, M.; Oyler, JW; Warren, DA; Parsons, R.; Affleck, D., Decreasing fire season precipitation increased recent western US forest wildfire activity, Proc. Natl. Acad. Sci., 115, 36, 8349-8357 (2018) · doi:10.1073/pnas.1802316115 |
| [9] | Son, R., Kim, H., Wang, S.-Y., Jeong, J.-H., Woo, S.-H., Jeong, J.-Y., Lee, B.-D., Kim, S.H., LaPlante, M., Kwon, C.-G., Yoon, J.-H.: Changes in fire weather climatology under \(1.5^\circ C\) and \(2.0^\circ C\) warming. Environ. Res. Lett. 16(3), 034058 (2021) |
| [10] | Krawchuk, MA; Moritz, MA; Parisien, M-A; Van Dorn, J.; Hayhoe, K., Global pyrogeography: the current and future distribution of wildfire, PloS one, 4, 4, 5102 (2009) · doi:10.1371/journal.pone.0005102 |
| [11] | Sá, ACL; Turkman, MAA; Pereira, JMC, Exploring fire incidence in Portugal using generalized additive models for location, scale and shape (gamlss), Model. Earth Syst. Environ., 4, 1, 199-220 (2018) · doi:10.1007/s40808-017-0409-6 |
| [12] | Ziel, RH; Bieniek, PA; Bhatt, US; Strader, H.; Rupp, TS; York, A., A comparison of fire weather indices with MODIS fire days for the natural regions of Alaska, Forests, 11, 5, 516 (2020) · doi:10.3390/f11050516 |
| [13] | Cohen, J.D., Deeming, J.E.: The National Fire-Danger Rating System: basic Equations (1985). https://www.fs.usda.gov/research/treesearch/27298 |
| [14] | Koh, J.; Pimont, F.; Dupuy, J-L; Opitz, T., Spatiotemporal wildfire modeling through point processes with moderate and extreme marks, The Annals of Applied Statistics, 17, 1, 560-582 (2023) · Zbl 07656989 · doi:10.1214/22-AOAS1642 |
| [15] | Sharples, JJ; McRae, RHD; Weber, RO; Gill, AM, A simple index for assessing fire danger rating, Environ. Model. Softw., 24, 6, 764-774 (2009) · doi:10.1016/j.envsoft.2008.11.004 |
| [16] | Richards, J., Huser, R.: A unifying partially-interpretable framework for neural network-based extreme quantile regression. arXiv preprint: 2208.07581 (2022) |
| [17] | Ivek, T., Vlah, D.: Reconstruction of incomplete wildfire data using deep generative models. Extremes (2023). doi:10.1007/s10687-022-00459-1 · Zbl 07685220 |
| [18] | Cisneros, D., Gong, Y., Yadav, R., Hazra, A., Huser, R.: A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizes. Extremes (2023). doi:10.1007/s10687-022-00460-8 · Zbl 07685222 |
| [19] | Koh, J.: Gradient boosting with extreme-value theory for wildfire prediction. Extremes (2023). doi:10.1007/s10687-022-00454-6 · Zbl 07685221 |
| [20] | Kelly, K.; Šavrič, B., Area and volume computation of longitude-latitude grids and three-dimensional meshes, Trans. GIS, 25, 1, 6-24 (2021) · doi:10.1111/tgis.12636 |
| [21] | Budic, L.; Didenko, G.; Dormann, CF, Squares of different sizes: effect of geographical projection on model parameter estimates in species distribution modeling, Ecol. Evol., 6, 1, 202-211 (2016) · doi:10.1002/ece3.1838 |
| [22] | Hijmans, R.J.: Geosphere: Spherical Trigonometry. (2019). R package version 1.5-10. https://CRAN.R-project.org/package=geosphere |
| [23] | Joseph, M.B., Rossi, M.W., Mietkiewicz, N.P., Mahood, A.L., Cattau, M.E., St. Denis, L.A., Nagy, R.C., Iglesias, V., Abatzoglou, J.T., Balch, J.K.: Spatiotemporal prediction of wildfire size extremes with Bayesian finite sample maxima. Ecol. Appl. 29(6), 01898 (2019) |
| [24] | Richards, J.; Tawn, JA; Brown, S., Modelling extremes of spatial aggregates of precipitation using conditional methods, Ann. Appl. Stat., 16, 4, 2693-2713 (2022) · Zbl 1498.62291 · doi:10.1214/22-AOAS1609 |
| [25] | Balkema, AA; de Haan, L., Residual life time at great age, Ann. Probab., 2, 5, 792-804 (1974) · Zbl 0295.60014 · doi:10.1214/aop/1176996548 |
| [26] | Pickands, J., Statistical inference using extreme order statistics, Ann. Stat., 3, 1, 119-131 (1975) · Zbl 0312.62038 |
| [27] | Coles, SG, An Introduction to Statistical Modeling of Extreme Values (2001), London: Springer, London · Zbl 0980.62043 · doi:10.1007/978-1-4471-3675-0 |
| [28] | Stephenson, AG; Saunders, K.; Tafakori, L., The MELBS team winning entry for the EVA2017 competition for spatiotemporal prediction of extreme rainfall using generalized extreme value quantiles, Extremes, 21, 477-484 (2018) · Zbl 1404.62134 · doi:10.1007/s10687-018-0321-0 |
| [29] | Wood, SN, Generalized Additive Models: An Introduction with R (2017), Boca Raton: CRC Press, Boca Raton · Zbl 1368.62004 · doi:10.1201/9781315370279 |
| [30] | Youngman, B.D.: Generalized additive models for exceedances of high thresholds with an application to return level estimation for U.S. wind gusts. J. Am. Stat. Assoc. 114(528), 1865-1879 (2019) · Zbl 1428.62202 |
| [31] | Zhang, Y.; Lim, S.; Sharples, JJ, Wildfire occurrence patterns in ecoregions of New South Wales and Australian Capital Territory, Australia, Nat. Hazards, 87, 415-435 (2017) · doi:10.1007/s11069-017-2770-1 |
| [32] | Rodríguez-Pérez, JR; Ordóñez, C.; Roca-Pardiñas, J.; Vecín-Arias, D.; Castedo-Dorado, F., Evaluating lightning-caused fire occurrence using spatial generalized additive models: a case study in central Spain, Risk Anal., 40, 7, 1418-1437 (2020) · doi:10.1111/risa.13488 |
| [33] | Hitz, AS; Davis, RA; Samorodnitsky, G., Discrete extremes. arXiv pre-print, 1707, 05033 (2017) |
| [34] | Rokach, L., Maimon, O.: Clustering methods. In: Data Mining and Knowledge Discovery Handbook, pp. 321-352. Springer, New York (2005) · Zbl 1087.68029 |
| [35] | Duane, A.; Castellnou, M.; Brotons, L., Towards a comprehensive look at global drivers of novel extreme wildfire events, Climatic Change, 165, 43 (2021) · doi:10.1007/s10584-021-03066-4 |
| [36] | Crockett, J.L., Westerling, A.L.: Greater temperature and precipitation extremes intensify Western U.S. droughts, wildfire severity, and Sierra Nevada tree mortality. J. Clim. 31(1), 341-354 (2018) |
| [37] | Rodrigues, M.; Costafreda-Aumedes, S.; Comas, C.; Vega-García, C., Spatial stratification of wildfire drivers towards enhanced definition of large-fire regime zoning and fire seasons, Sci. Total Environ., 689, 634-644 (2019) · doi:10.1016/j.scitotenv.2019.06.467 |
| [38] | Rodrigues, M.; González-Hidalgo, JC; Peña-Angulo, D.; Jiménez-Ruano, A., Identifying wildfire-prone atmospheric circulation weather types on mainland Spain, Agric. For. Meteorol., 264, 92-103 (2019) · doi:10.1016/j.agrformet.2018.10.005 |
| [39] | Rahimi, S.; Sharifi, Z.; Mastrolonardo, G., Comparative study of the effects of wildfire and cultivation on topsoil properties in the Zagros forest, Iran, Eurasian Soil Sci., 53, 1655-1668 (2020) · doi:10.1134/S1064229320110113 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
