Abstract
Fire has been an integral part of the Earth for millennia. Several recent wildfires have exhibited an unprecedented spatial and temporal extent and their control is beyond national firefighting capabilities. Prescribed or controlled burning treatments are debated as a potential measure for ameliorating the spread and intensity of wildfires. Machine learning analysis using random forests was performed in a spatio-temporal data set comprising a large number of savanna fires across 22 years. Results indicate that fire return interval was not an important predictor of fire spread rate or fire intensity, having a feature importance of 3.5%, among eight other predictor variables. Manipulating burn seasonality showed a feature importance of 6% or less regarding fire spread rate or fire intensity. While manipulated fire return interval and seasonality moderated both fire spread rate and intensity, their overall effects were low in comparison with meteorological (hydrological and climatic) variables. The variables with the highest feature importance regarding fire spread rate resulted in fuel moisture with 21%, relative humidity with 15%, wind speed with 14%, and last years’ rainfall with 14%. The variables with the highest feature importance regarding. Fire intensity included fuel load with 21.5%, fuel moisture with 16.5%, relative humidity with 12.5%, air temperature with 12.5%, and rainfall with 12.5%, Predicting fire spread rate and intensity has been a poor endeavour thus far and we show that more data of the variables already monitored would not result in higher predictive accuracy.
Similar content being viewed by others
References
Andersen AN, Braithwaite RW, Cook GD, Corbett LK, Williams RJ, Douglas MM, Gill AM, Setterfield SA, Muller WJ (1998) Fire research for conservation management in tropical savannas: introducing the Kapalga fire experiment. Aust J Ecol 23:95–110
Arora VK, Melton JR (2018) Reduction in global area burned and wildfire emissions since 1930s enhances carbon uptake by land. Nat Commun 9:1326
Baeza MJ, De Luıs M, Raventós J, Escarré A (2002) Factors influencing fire behaviour in shrublands of different stand ages and the implications for using prescribed burning to reduce wildfire risk. J Environ Manag 65(2):199–208
Bessie WC, Johnson EA (1995) The relative importance of fuels and weather on fire behavior in subalpine forests. Ecology 76:747–762
Boivin J, Ng S (2006) Are more data always better for factor analysis? J Econ 132:169–194
Bowman DMJS, Perry GLW, Higgins SI, Johnson CN, Fuhlendorf SD, Murphy BP (2016) Pyrodiversity is the coupling of biodiversity and fire regimes in food webs. Philos Trans R Soc B Biol Sci 371:20150169
Bransby D, Tainton N (1977) The disc pasture meter: possible applications in grazing management. Proc Annu Congr Grassl Soc South Afr 12:115–118
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Breiman L (2001) Random forests. Machine Learn 45(1):5–32
Breiman L (2017) Classification and regression trees. Routledge, Abingdon
Brown C, Johnstone J (2011) How does increased fire frequency affect carbon loss from fire? A case study in the northern boreal forest. Int J Wildland Fire 20:829–837
Brown KS, Marean CW, Herries AI, Jacobs Z, Tribolo C, Braun D, Roberts DL, Meyer MC, Bernatchez J (2009) Fire as an engineering tool of early modern humans. Science 325:859–862
Byram GM (1959) Combustion of forest fuels. In: Davis KP (ed) Forest fire: control and use. McGraw-Hill, New York, pp 61–89
Chen Y, Randerson JT, Coffield SR, Foufoula-Georgiou E, Smyth P, Graff CA, Morton DC, Andela N, van der Werf GR, Giglio L, Ott LE (2020) Forecasting global fire emissions on subseasonal to seasonal (S2S) time scales. J Adv Model Earth Syst 12:2019MS001955
Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT, Way GP, Ferrero E, Agapow P-M, Zietz M, Hoffman MM, Xie W, Rosen GL, Lengerich BJ, Israeli J, Lanchantin J, Woloszynek S, Carpenter AE, Shrikumar A, Xu J, Cofer EM, Lavender CA, Turaga SC, Alexandari AM, Lu Z, Harris DJ, DeCaprio D, Qi Y, Kundaje A, Peng Y, Wiley LK, Segler MHS, Boca SM, Swamidass SJ, Huang A, Gitter A, Greene CS (2018) Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interface 15:20170387
Coffield SR, Graff CA, Chen Y, Smyth P, Foufoula-Georgiou E, Randerson JT (2019) Machine learning to predict final fire size at the time of ignition. Int J Wildland Fire 28:861–873
Cruz MG, Alexander ME, Sullivan AL, Gould JS, Kilinc M (2018) Assessing improvements in models used to operationally predict wildland fire rate of spread. Environ Model Softw 105:54–63
Daliakopoulos IN, Katsanevakis S, Moustakas A (2017) Spatial downscaling of alien species presences using machine learning. Front Earth Sci 5:60
Di Virgilio G, Evans JP, Blake SA, Armstrong M, Dowdy AJ, Sharples J, McRae R (2019) Climate change increases the potential for extreme wildfires. Geophys Res Lett 46:8517–8526
Espinosa J, Palheiro P, Loureiro C, Ascoli D, Esposito A, Fernandes PM (2019) Fire-severity mitigation by prescribed burning assessed from fire-treatment encounters in maritime pine stands. Can J For Res 49:205–211
Evans MR, Moustakas A (2016) A comparison between data requirements and availability for calibrating predictive ecological models for lowland UK woodlands: learning new tricks from old trees. Ecol Evol 6:4812–4822
Evans MR, Benton TG, Grimm V, Lessells CM, O’Malley MA, Moustakas A, Weisberg M (2014) Data availability and model complexity, generality, and utility: a reply to Lonergan. Trends Ecol Evol 29:302–303
Fernandes PM, Botelho HS (2003) A review of prescribed burning effectiveness in fire hazard reduction. Int J Wildland Fire 12:117–128
Fernández-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133–3181
Fisher JL, Loneragan WA, Dixon K, Delaney J, Veneklaas EJ (2009) Altered vegetation structure and composition linked to fire frequency and plant invasion in a biodiverse woodland. Biol Conserv 142:2270–2281
Flannigan MD, Krawchuk MA, de Groot WJ, Wotton BM, Gowman LM (2009) Implications of changing climate for global wildland fire. Int J Wildland Fire 18:483–507
Francos M, Stefanuto E, Úbeda X, Pereira P (2019) Long-term impact of prescribed fire on soil chemical properties in a wildland-urban interface. Northeastern Iberian Peninsula. Sci Total Environ 689:305–311
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
García-Llamas P, Suárez-Seoane S, Taboada A, Fernández-Manso A, Quintano C, Fernández-García V, Fernández-Guisuraga JM, Marcos E, Calvo L (2019) Environmental drivers of fire severity in extreme fire events that affect Mediterranean pine forest ecosystems. For Ecol Manag 433:24–32
Govender N, Trollope WSW, Van Wilgen BW (2006) The effect of fire season, fire frequency, rainfall and management on fire intensity in savanna vegetation in South Africa. J Appl Ecol 43:748–758
Hansen BB, Grøtan V, Aanes R, Sæther B-E, Stien A, Fuglei E, Ims RA, Yoccoz NG, Pedersen ÅØ (2013) Climate events synchronize the dynamics of a resident vertebrate community in the high arctic. Science 339:313–315
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Data mining, inference and prediction. Springer, New York
Hengst GE, Dawson JO (1994) Bark properties and fire resistance of selected tree species from the central hardwood region of North America. Can J For Res 24:688–696
Hesseln H (2000) The economics of prescribed burning: a research review. For Sci 46:322–334
Higgins SI, Bond WJ, February EC, Bronn A, Euston-Brown DI, Enslin B, Govender N, Rademan L, O’Regan S, Potgieter AL (2007) Effects of four decades of fire manipulation on woody vegetation structure in savanna. Ecology 88:1119–1125
James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning. Springer, New York
Jetz W, McGeoch MA, Guralnick R, Ferrier S, Beck J, Costello MJ, Fernandez M, Geller GN, Keil P, Merow C, Meyer C, Muller-Karger FE, Pereira HM, Regan EC, Schmeller DS, Turak E (2019) Essential biodiversity variables for mapping and monitoring species populations. Nat Ecol Evol 3:539–551
Jones MW, Santín C, van der Werf GR, Doerr SH (2019) Global fire emissions buffered by the production of pyrogenic carbon. Nat Geosci 12:742–747
Keeley JE, Fotheringham C, Morais M (1999) Reexamining fire suppression impacts on brushland fire regimes. Science 284:1829–1832
Kell DB, Oliver SG (2004) Here is the evidence, now what is the hypothesis? The complementary roles of inductive and hypothesis-driven science in the post-genomic era. BioEssays 26:99–105
Keyantash, J. N. C. f. A. R. S. E. 2018. The Climate Data Guide: Standardized Precipitation Index (SPI). https://climatedataguide.ucar.edu/climate-data/standardized-precipitation-index-spi. Last modified 08 Mar 2018
Kochanski AK, Fournier A, Mandel J (2018) Experimental design of a prescribed burn instrumentation. Atmosphere 9:296
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2:18–22
Lino S, Sillero N, Torres J, Santos X, Álvares F (2019) The role of fire on wolf distribution and breeding-site selection: Insights from a generalist carnivore occurring in a fire-prone landscape. Landsc Urb Plan 183:111–121
Lonergan M (2014) Data availability constrains model complexity, generality, and utility: a response to Evans et al. Trends Ecol Evol 29(6):301–302
Lucas-Borja M, Plaza-Álvarez P, Gonzalez-Romero J, Sagra J, Alfaro-Sánchez R, Zema DA, Moya D, de Las Heras J (2019) Short-term effects of prescribed burning in Mediterranean pine plantations on surface runoff, soil erosion and water quality of runoff. Sci Total Environ 674:615–622
Madadgar S, Sadegh M, Chiang F, Ragno E, AghaKouchak A (2020) Quantifying increased fire risk in California in response to different levels of warming and drying. Stoch Env Res Risk Assess 34:2023–2031
McDaniel J, Kennard D, Fuentes A (2005) Smokey the tapir: traditional fire knowledge and fire prevention campaigns in lowland Bolivia. Soc Natl Resour 18:921–931
Merino A, Jiménez E, Fernández C, Fontúrbel MT, Campo J, Vega JA (2019) Soil organic matter and phosphorus dynamics after low intensity prescribed burning in forests and Shrubland. J Environ Manag 234:214–225
Moustakas A (2015) Fire acting as an increasing spatial autocorrelation force: implications for pattern formation and ecological facilitation. Ecol Complex 21:142–149
Moustakas A (2017) Spatio-temporal data mining in ecological and veterinary epidemiology. Stoch Env Res Risk Assess 31:829–834
Moustakas A, Wiegand K, Meyer KM, Ward D, Sankaran M (2010) perspective: learning new tricks from old trees—revisiting the savanna question. Front Biogeogr. https://doi.org/10.21425/F5FBG12335
Moustakas A, Evans MR, Daliakopoulos IN, Markonis Y (2018) Abrupt events and population synchrony in the dynamics of Bovine Tuberculosis. Nat Commun 9:2821
Moustakas A, Daliakopoulos IN, Benton TG (2019) Data-driven competitive facilitative tree interactions and their implications on nature-based solutions. Sci Total Environ 651:2269–2280
Ng J, North MP, Arditti AJ, Cooper MR, Lutz JA (2020) Topographic variation in tree group and gap structure in Sierra Nevada mixed-conifer forests with active fire regimes. For Ecol Manag 472:118220
Nikolopoulos EI, Destro E, Bhuiyan MAE, Borga M, Anagnostou EN (2018) Evaluation of predictive models for post-fire debris flow occurrence in the western United States. Natl Hazards Earth Syst Sci 18:2331–2343
Nishino T (2019) Physics-based urban fire spread simulation coupled with stochastic occurrence of spot fires. Stoch Env Res Risk Assess 33:451–463
North M, Collins BM, Stephens S (2012) Using fire to increase the scale, benefits, and future maintenance of fuels treatments. J For 110:392–401
O’Connor CD, Garfin GM, Falk DA, Swetnam TW (2011) Human pyrogeography: a new synergy of fire, climate and people is reshaping ecosystems across the globe. Geogr Compass 5:329–350
Padarian J, Minasny B, McBratney A (2019) Transfer learning to localise a continental soil vis-NIR calibration model. Geoderma 340:279–288
Papacharalampous G, Tyralis H, Koutsoyiannis D (2019) Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes. Stoch Env Res Risk Assess 33:481–514
Pausas JG, Ribeiro E (2013) The global fire–productivity relationship. Glob Ecol Biogeogr 22:728–736
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825–2830
Penman TD, Christie FJ, Andersen A, Bradstock RA, Cary G, Henderson MK, Price O, Tran C, Wardle GM, Williams RJ (2011) Prescribed burning: how can it work to conserve the things we value? Int J Wildland Fire 20:721–733
Platt JR (1964) Strong Inference: certain systematic methods of scientific thinking may produce much more rapid progress than others. Science 146:347–353
Poudyal NC, Johnson-Gaither C, Goodrick S, Bowker JM, Gan J (2012) Locating spatial variation in the association between wildland fire risk and social vulnerability across six Southern States. Environ Manag 49:623–635
Qayum A, Ahmad F, Arya R, Singh RK (2020) Predictive modeling of forest fire using geospatial tools and strategic allocation of resources: eForestFire. Stoch Env Res Risk Assess 34:2259–2275
Randerson, J. T., G. R. van der Werf, L. Giglio, G. J. Collatz, and P. S. Kasibhatla (2018) Global fire emissions database, version 4, (GFEDv4). ORNL DAAC, Oak Ridge, Tennessee, USA. https://daac.ornl.gov/VEGETATION/guides/fire_emissions_v4.html
Ravi V, Vaughan JK, Wolcott MP, Lamb BK (2019) Impacts of prescribed fires and benefits from their reduction for air quality, health, and visibility in the Pacific Northwest of the United States. J Air Waste Manag Assoc 69:289–304
San-Miguel I, Coops NC, Chavardès RD, Andison DW, Pickell PD (2020) What controls fire spatial patterns? Predictability of fire characteristics in the Canadian boreal plains ecozone. Ecosphere 11:e02985
Schapire RE, Freund Y, Bartlett P, Lee WS (1998) Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat 26:1651–1686
Schilling EG (1973) A systematic approach to the analysis of means: part I. Analysis of treatment effects. J Qual Technol 5:93–108
Scholes R, Archer S (1997) Tree-grass interactions in savannas. Annu Rev Ecol Syst 28:517–544
Schwilk DW, Ackerly DD (2001) Flammability and serotiny as strategies: correlated evolution in pines. Oikos 94:326–336
Scornet E, Biau G, Vert J-P (2015) Consistency of random forests. Ann Stat 43:1716–1741
Sheppard LW, Bell JR, Harrington R, Reuman DC (2015) Changes in large-scale climate alter spatial synchrony of aphid pests. Nat Clim Change 6:610
Sheuyange A, Oba G, Weladji RB (2005) Effects of anthropogenic fire history on savanna vegetation in northeastern Namibia. J Environ Manag 75:189–198
Tàbara D, Saurí D, Cerdan R (2003) Forest fire risk management and public participation in changing socioenvironmental conditions: a case study in a Mediterranean Region. Risk Anal 23:249–260
Taufik M, Torfs PJJF, Uijlenhoet R, Jones PD, Murdiyarso D, Van Lanen HAJ (2017) Amplification of wildfire area burnt by hydrological drought in the humid tropics. Nat Clim Change 7:428–431
Tilman D, Reich P, Phillips H, Menton M, Patel A, Vos E, Peterson D, Knops J (2000) Fire suppression and ecosystem carbon storage. Ecology 81:2680–2685
Trollope W, Potgieter A (1986) Estimating grass fuel loads with a disc pasture meter in the Kruger National Park. J Grassl Soc South Afr 3:148–152
Van de Vijver C, Poot P, Prins H (1999) Causes of increased nutrient concentrations in post-fire regrowth in an East African savanna. Plant Soil 214:173–185
Van der Werf GR, Randerson JT, Collatz GJ, Giglio L (2003) Carbon emissions from fires in tropical and subtropical ecosystems. Glob Change Biol 9:547–562
van Helden P (2013) Data-driven hypotheses. Embo Rep 14:104–104
van Wilgen BW, Govender N, Biggs HC, Ntsala D, Funda XN (2004) Response of savanna fire regimes to changing fire-management policies in a large African national park. Conserv Biol 18(6):1533–1540
Volkova L, Weston CJ (2019) Effect of thinning and burning fuel reduction treatments on forest carbon and bushfire fuel hazard in Eucalyptus sieberi forests of South-Eastern Australia. Sci Total Environ 694:133708
Wager S, Hastie T, Efron B (2014) Confidence intervals for random forests: the Jackknife and the infinitesimal Jackknife. J Mach Learn Res 15:1625–1651
Watts AC, Samburova V (2020) Criteria-based identification of important fuels for Wildland fire emission research. Atmosphere 11:640
Zhao Q, Hastie T (2019) Causal interpretations of black-box models. J Bus Econ Stat 39:1–10
Zhu S, Luo X, Yuan X, Xu Z (2020) An improved long short-term memory network for streamflow forecasting in the upper Yangtze River. Stoch Environ Res Risk Assess 34(9):1313–1329
Acknowledgements
We thank Petros Lymberakis and Dimitris Kontakos for comments and suggestions, and the KNP scientific services for providing us with the data. AM acknowledges funding from the EU COST Action ‘Fire Links’ CA18135, Fire in the Earth System: Science and Society. Comments from two anonymous reviewers considerably improved an earlier manuscript draft.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Moustakas, A., Davlias, O. Minimal effect of prescribed burning on fire spread rate and intensity in savanna ecosystems. Stoch Environ Res Risk Assess 35, 849–860 (2021). https://doi.org/10.1007/s00477-021-01977-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-021-01977-3