International Journal of Wildland Fire International Journal of Wildland Fire Society
Journal of the International Association of Wildland Fire
RESEARCH ARTICLE

An empirical machine learning method for predicting potential fire control locations for pre-fire planning and operational fire management

Christopher D. O’ Connor A B , David E. Calkin A and Matthew P. Thompson A
+ Author Affiliations
- Author Affiliations

A US Department of Agriculture Forest Service, Rocky Mountain Research Station, Forestry Sciences Laboratory, 800 East Beckwith Avenue, Missoula, MT 59801, USA.

B Corresponding author. Email: christopheroconnor@fs.fed.us

International Journal of Wildland Fire 26(7) 587-597 https://doi.org/10.1071/WF16135
Submitted: 23 July 2016  Accepted: 17 January 2017   Published: 13 February 2017

Abstract

During active fire incidents, decisions regarding where and how to safely and effectively deploy resources to meet management objectives are often made under rapidly evolving conditions, with limited time to assess management strategies or for development of backup plans if initial efforts prove unsuccessful. Under all but the most extreme fire weather conditions, topography and fuels are significant factors affecting potential fire spread and burn severity. We leverage these relationships to quantify the effects of topography, fuel characteristics, road networks and fire suppression effort on the perimeter locations of 238 large fires, and develop a predictive model of potential fire control locations spanning a range of fuel types, topographic features and natural and anthropogenic barriers to fire spread, on a 34 000 km2 landscape in southern Idaho and northern Nevada. The boosted logistic regression model correctly classified final fire perimeter locations on an independent dataset with 69% accuracy without consideration of weather conditions on individual fires. The resulting fire control probability surface has potential for reducing unnecessary exposure for fire responders, coordinating pre-fire planning for operational fire response, and as a network of locations to incorporate into spatial fire planning to better align fire operations with land management objectives.

Additional keywords: boosted regression, fire responder safety, MaxEnt, operational decision support, pre-fire planning, risk analysis, spatial analysis.


References

Abatzoglou JT, Williams AP (2016) Impact of anthropogenic climate change on wildfire across western US forests. Proceedings of the National Academy of Sciences of the United States of America 113, 11770–11775.
Impact of anthropogenic climate change on wildfire across western US forests.CrossRef | 1:CAS:528:DC%2BC28Xhs1elur3K&md5=31fba046ed9ce3f66e307429597a31b7CAS | open url image1

Anderson DH (1989) A mathematical model for fire containment. Canadian Journal of Forest Research 19, 997–1003.
A mathematical model for fire containment.CrossRef | open url image1

Beier P, Brost B (2010) Use of land facets to plan for climate change: conserving the arenas, not the actors. Conservation Biology 24, 701–710.
Use of land facets to plan for climate change: conserving the arenas, not the actors.CrossRef | open url image1

Bradshaw L (2013) FireFamily Plus 4.1. USDA Forest Service, Rocky Mountain Research Station, Fire Sciences Laboratory, Missoula, MT, USA. Available at http://www.firelab.org/project/firefamilyplus [Verified 24 January 2017]

Bradstock RA, Hammill KA, Collins L, Price O (2010) Effects of weather, fuel and terrain on fire severity in topographically diverse landscapes of south-eastern Australia. Landscape Ecology 25, 607–619.
Effects of weather, fuel and terrain on fire severity in topographically diverse landscapes of south-eastern Australia.CrossRef | open url image1

Broyles G (2011) Fireline production rates. USDA Forest Service, Fire management report 1151–1805. National Technology & Development Program. San Dimas Technology and Development Center (San Dimas, CA). Available at https://www.fs.fed.us/t-d/pubs//pdf/11511805.pdf [Verified 30 January 2017]

Calkin DE, Thompson MP, Finney MA, Hyde KD (2011) A real-time risk assessment tool supporting wildland fire decision making. Journal of Forestry 109, 274–280.

De’ath G (2007) Boosted trees for ecological modeling and prediction. Ecology 88, 243–251.
Boosted trees for ecological modeling and prediction.CrossRef | open url image1

Dillon G, Morgan P, Holden Z (2011a) Mapping the potential for high severity wildfire in the western United States. Fire Management Today 71, 25–28.

Dillon GK, Holden ZA, Morgan P, Crimmins MA, Heyerdahl EK, Luce CH (2011b) Both topography and climate affected forest and woodland burn severity in two regions of the western US, 1984 to 2006. Ecosphere 2, 130
Both topography and climate affected forest and woodland burn severity in two regions of the western US, 1984 to 2006.CrossRef | open url image1

Dillon GK, Menakis J, Fay F (2015) Wildland fire potential: a tool for assessing wildfire risk and fuels management needs. In ‘Proceedings of the large wildland fires conference’, 19–23 May 2014, Missoula, MT. (Eds RE Keane, M Jolly, R Parsons, K Riley) USDA Forest Service, Rocky Mountain Research Station, Proceedings RMRS-P-73, pp. 60–76. (Fort Collins, CO)

Dormann CF, Elith J, Bacher S, Buchmann C, Carl G, Carré G, Marquéz J. R. G., Gruber B, Lafourcade B, Leitão PJ (2013) Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography 36, 27–46.
Collinearity: a review of methods to deal with it and a simulation study evaluating their performance.CrossRef | open url image1

DRI (2015) Desert Research Institute Remote Automatic Weather Station data, Trail Gulch Weather Station. Weather dates 2–30 July 2007. Available at http://www.raws.dri.edu/cgi-bin/rawMAIN.pl?idITRA [Verified 24 January 2017]

Duff TJ, Tolhurst KG (2015) Operational wildfire suppression modelling: a review evaluating development, state of the art and future directions. International Journal of Wildland Fire 24, 735–748.
Operational wildfire suppression modelling: a review evaluating development, state of the art and future directions.CrossRef | open url image1

Dunn CJ, Thompson MP, Calkin DE A framework for developing safe and efficient large-fire incident response strategies and tactics for a new fire management paradigm. International Journal of Wildland Fire

Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. Journal of Animal Ecology 77, 802–813.
A working guide to boosted regression trees.CrossRef | 1:STN:280:DC%2BD1cvgsFOqsQ%3D%3D&md5=dfa7bed10cb48d9db999ac09eb00b369CAS | open url image1

Elith J, Phillips SJ, Hastie T, Dudík M, Chee YE, Yates CJ (2011) A statistical explanation of MaxEnt for ecologists. Diversity & Distributions 17, 43–57.
A statistical explanation of MaxEnt for ecologists.CrossRef | open url image1

ESRI (2015) ‘ArcMap 10.2.’ (ESRI Inc. Redlands, CA)

Finney MA (2004) FARSITE: Fire area simulator: model development and evaluation. USDA Forest Service, Rocky Mountain Research Station, Research Paper RMRS-RP-4 Revised. (Fort Colliins, CO) Available at https://www.fs.fed.us/rm/pubs/rmrs_rp004.pdf [Verified 30 January 2017].

Finney MA (2006) An overview of FlamMap fire modeling capabilities. In ‘Fuels management – how to measure success: conference proceedings’, 28–30 March 2006, Portland, OR. (Eds PL Andrews, B Butler) USDA Forest Service, Rocky Mountain Research Station, Proceedings RMRS-P-41. (Fort Collins, CO).

Finney M, Grenfell IC, McHugh CW (2009) Modeling containment of large wildfires using generalized linear mixed-model analysis. Forest Science 55, 249–255.

Finney MA, Grenfell IC, McHugh CW, Seli RC, Trethewey D, Stratton RD, Brittain S (2011a) A method for ensemble wildland fire simulation. Environmental Modeling and Assessment 16, 153–167.
A method for ensemble wildland fire simulation.CrossRef | open url image1

Finney MA, McHugh CW, Grenfell IC, Riley KL, Short KC (2011b) A simulation of probabilistic wildfire risk components for the continental United States. Stochastic Environmental Research and Risk Assessment 25, 973–1000.
A simulation of probabilistic wildfire risk components for the continental United States.CrossRef | open url image1

Finney MA, Brittain S, Seli RC, McHugh CW, Gangi L (2015) FlamMap: Fire Mapping and Analysis System (Version 5.0). USDA Forest Service, Rocky Mountain Research Station. (Missoula, MT) Available from https://www.firelab.org/document/flammap-software [Verified 24 January 2017]

Fried JS, Fried BD (1996) Simulating wildfire containment with realistic tactics. Forest Science 42, 267–281.

Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Annals of Statistics 28, 337–407.
Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors).CrossRef | open url image1

GeoMac (2016) Geospatial multi-agency coordination. USGS Geosciences & Environmental Change Science Center (Lakewood, CO). Available at http://www.geomac.gov/ [Verified 14 June 2016]

Haas JR, Calkin DE, Thompson MP (2013) A national approach for integrating wildfire simulation modeling into wildland–urban interface risk assessments within the United States. Landscape and Urban Planning 119, 44–53.
A national approach for integrating wildfire simulation modeling into wildland–urban interface risk assessments within the United States.CrossRef | open url image1

Harris L, Taylor AH (2015) Topography, fuels, and fire exclusion drive fire severity of the Rim Fire in an old-growth mixed-conifer forest, Yosemite National Park, USA. Ecosystems 18, 1192–1208.
Topography, fuels, and fire exclusion drive fire severity of the Rim Fire in an old-growth mixed-conifer forest, Yosemite National Park, USA.CrossRef | open url image1

Holsinger L, Parks SA, Miller C (2016) Weather, fuels, and topography impede wildland fire spread in western US landscapes. Forest Ecology and Management 380, 59–69.
Weather, fuels, and topography impede wildland fire spread in western US landscapes.CrossRef | open url image1

Iniguez JM, Swetnam TW, Yool SR (2008) Topography affected landscape fire history patterns in southern Arizona, USA. Forest Ecology and Management 256, 295–303.
Topography affected landscape fire history patterns in southern Arizona, USA.CrossRef | open url image1

Jenness J, Brost B, Beier P (2013) ‘Land Facet CorridorDesigner manual.’ (Jenness Enterprises: Flagstaff, AZ). Available at http://www.corridordesign.org/ [Verified 24 January 2017]

Kane VR, Cansler CA, Povak NA, Kane JT, McGaughey RJ, Lutz JA, Churchill DJ, North MP (2015) Mixed severity fire effects within the Rim Fire: relative importance of local climate, fire weather, topography, and forest structure. Forest Ecology and Management 358, 62–79.
Mixed severity fire effects within the Rim Fire: relative importance of local climate, fire weather, topography, and forest structure.CrossRef | open url image1

Keane RE, Morgan PM, Dillon GK, Sikkink PG, Karau EC, Holden ZA, Drury SA (2013) A fire severity mapping system for real-time fire management applications and long-term planning: the FIRESEV project. Final report January 2013. Project Number JFSP-09–1-07–4. JFSP Research Project Reports, Paper 18. (Joint Fire Sciences Program: Boise, ID)

LANDFIRE (2010) Digital Elevation Model, LANDFIRE 1.2.0. US Department of the Interior, Geological Survey. Available at http://www.landfire.gov/viewer/ [Verified 26 October 2015].

LANDFIRE (2012) 40 Scott & Burgan (2005) Fire Behavior Fuel Models, Slope, Aspect, Existing Vegetation Type, and Biophysical Settings layers, LANDFIRE 1.3.0. US Department of the Interior, Geological Survey. Available at http://www.landfire.gov/viewer/ [Verified 26 October 2015].

Lobo JM, Jiménez-Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Global Ecology and Biogeography 17, 145–151.
AUC: a misleading measure of the performance of predictive distribution models.CrossRef | open url image1

Majka D, Jenness J, Beier P (2007) CorridorDesigner: ArcGIS tools for designing and evaluating corridors. (CorridorDesigner: Minneapolis, MN) Available at http://www.corridordesign.org/ [Verified 24 January 2017]

Margolis EQ, Balmat J (2009) Fire history and fire–climate relationships along a fire regime gradient in the Santa Fe Municipal Watershed, NM, USA. Forest Ecology and Management 258, 2416–2430.
Fire history and fire–climate relationships along a fire regime gradient in the Santa Fe Municipal Watershed, NM, USA.CrossRef | open url image1

Merow C, Smith MJ, Silander JA (2013) A practical guide to MaxEnt for modeling species’ distributions: what it does, and why inputs and settings matter. Ecography 36, 1058–1069.
A practical guide to MaxEnt for modeling species’ distributions: what it does, and why inputs and settings matter.CrossRef | open url image1

Merow C, Smith MJ, Edwards TC, Guisan A, McMahon SM, Normand S, Thuiller W, Wüest RO, Zimmermann NE, Elith J (2014) What do we gain from simplicity versus complexity in species distribution models? Ecography 37, 1267–1281.
What do we gain from simplicity versus complexity in species distribution models?CrossRef | open url image1

Mitsopoulos I, Mallinis G, Zibtsev S, Yavuz M, Saglam B, Kucuk O, Bogomolov V, Borsuk A, Zaimes G (2016) An integrated approach for mapping fire suppression difficulty in three different ecosystems of Eastern Europe. Journal of Spatial Science
An integrated approach for mapping fire suppression difficulty in three different ecosystems of Eastern Europe.CrossRef | open url image1

MTBS (2014) Monitoring Trends in Burn Severity. USDA Forest Service Remote Sensing Applications Center. Salt Lake City, UT. Available at http://www.mtbs.gov/dataaccess.html [Verified 20 October 2015]

Narayanaraj G, Wimberly MC (2011) Influences of forest roads on the spatial pattern of wildfire boundaries. International Journal of Wildland Fire 20, 792–803.
Influences of forest roads on the spatial pattern of wildfire boundaries.CrossRef | open url image1

Narayanaraj G, Wimberly MC (2012) Influences of forest roads on the spatial patterns of human- and lightning-caused wildfire ignitions. Applied Geography (Sevenoaks, England) 32, 878–888.
Influences of forest roads on the spatial patterns of human- and lightning-caused wildfire ignitions.CrossRef | open url image1

Noonan-Wright EK, Opperman TS, Finney MA, Zimmerman GT, Seli RC, Elenz LM, Calkin DE, Fiedler JR (2011) Developing the US wildland fire decision support system. Journal of Combustion 2011, 168473
Developing the US wildland fire decision support system.CrossRef | open url image1

National Wildfire Coordinating Group (2004) Fireline handbook. NWCG Handbook 3. National Interagency Fire Center, PMS 410–1, NFES 0065. (Boise, ID).

O’Connor CD, Falk DA, Lynch AM, Swetnam TW (2014) Fire severity, size, and climate associations diverge from historical precedent along an ecological gradient in the Pinaleño Mountains, Arizona, USA. Forest Ecology and Management 329, 264–278.
Fire severity, size, and climate associations diverge from historical precedent along an ecological gradient in the Pinaleño Mountains, Arizona, USA.CrossRef | open url image1

Parks SA, Parisien M-A, Miller C (2012) Spatial bottom-up controls on fire likelihood vary across western North America. Ecosphere 3, 12
Spatial bottom-up controls on fire likelihood vary across western North America.CrossRef | open url image1

Parks SA, Parisien M-A, Miller C, Dobrowski SZ (2014) Fire activity and severity in the western US vary along proxy gradients representing fuel amount and fuel moisture. PLoS One 9, e99699
Fire activity and severity in the western US vary along proxy gradients representing fuel amount and fuel moisture.CrossRef | open url image1

Parks SA, Holsinger LM, Miller C, Nelson CR (2015) Wildland fire as a self-regulating mechanism: the role of previous burns and weather in limiting fire progression. Ecological Applications 25, 1478–1492.
Wildland fire as a self-regulating mechanism: the role of previous burns and weather in limiting fire progression.CrossRef | open url image1

Petrovic N, Carlson J (2012) A decision-making framework for wildfire suppression. International Journal of Wildland Fire 21, 927–937.
A decision-making framework for wildfire suppression.CrossRef | open url image1

Phillips SJ (2015) ‘A brief tutorial on MaxEnt.’ (AT&T Research: Florham, NJ).

Phillips SJ, Anderson RP, Schapire RE (2006) Maximum entropy modeling of species geographic distributions. Ecological Modelling 190, 231–259.
Maximum entropy modeling of species geographic distributions.CrossRef | open url image1

Podur JJ, Martell DL (2007) A simulation model of the growth and suppression of large forest fires in Ontario. International Journal of Wildland Fire 16, 285–294.
A simulation model of the growth and suppression of large forest fires in Ontario.CrossRef | open url image1

Preisler HK, Brillinger DR, Burgan RE, Benoit J (2004) Probability based models for estimation of wildfire risk. International Journal of Wildland Fire 13, 133–142.
Probability based models for estimation of wildfire risk.CrossRef | open url image1

Price OF, Borah R, Maier SW (2014) Role of weather and fuel in stopping fire spread in tropical savannas. Austral Ecology 39, 135–144.
Role of weather and fuel in stopping fire spread in tropical savannas.CrossRef | open url image1

R Core Team (2015). R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. Available from http://www.R-project.org/ [Verified 19 January 2017]

Ridgeway G (2015) Generalized boosted models: A guide to the gbm package. Available at https://cran.r-project.org/web/packages/gbm/gbm.pdf [Verified 24 January 2017]

Riley KL, Abatzoglou JT, Grenfell IC, Klene AE, Heinsch FA (2013) The relationship of large fire occurrence with drought and fire danger indices in the western USA, 1984–2008: the role of temporal scale. International Journal of Wildland Fire 22, 894–909.
The relationship of large fire occurrence with drought and fire danger indices in the western USA, 1984–2008: the role of temporal scale.CrossRef | open url image1

Rodríguez y Silva F, Martínez J. R. M, González-Cabán A (2014) A methodology for determining operational priorities for prevention and suppression of wildland fires. International Journal of Wildland Fire 23, 544–554.
A methodology for determining operational priorities for prevention and suppression of wildland fires.CrossRef | open url image1

Scott JH, Burgan RE (2005) Standard fire behavior fuel models: a comprehensive set for use with Rothermel’s surface fire spread model. USDA Forest Service, Rocky Mountain Research Station, General Technical Report No. RMRS-GTR-153. (Fort Collins, CO).

Scott JH, Thompson MP, Calkin DE (2013) A wildfire risk assessment framework for land and resource management. USDA Forest Service, Rocky Mountain Research Station, General Technical Report No. RMRS-GTR-315. (Fort Collins, CO).

Short KC (2015) Sources and implications of bias and uncertainty in a century of US wildfire activity data. International Journal of Wildland Fire 24, 883–891.

Thompson MP, Stonesifer CS, Seli RC, Hovorka M (2013) Developing standardized strategic response categories for fire management units. Fire Management Today 73, 18–24.

Thompson MP, Haas JR, Gilbertson-Day JW, Scott JH, Langowski P, Bowne E, Calkin DE (2015) Development and application of a geospatial wildfire exposure and risk calculation tool. Environmental Modelling & Software 63, 61–72.
Development and application of a geospatial wildfire exposure and risk calculation tool.CrossRef | open url image1

Thompson MP, Bowden P, Brough A, Scott JH, Gilbertson-Day J, Taylor A, Anderson J, Haas JR (2016a) Application of wildfire risk assessment results to wildfire response planning in the Southern Sierra Nevada, California, USA. Forests 7, 64
Application of wildfire risk assessment results to wildfire response planning in the Southern Sierra Nevada, California, USA.CrossRef | open url image1

Thompson MP, Freeborn P, Rieck JD, Calkin DE, Gilbertson-Day JW, Cochrane MA, Hand MS (2016b) Quantifying the influence of previously burned areas on suppression effectiveness and avoided exposure: a case study of the Las Conchas Fire. International Journal of Wildland Fire 25, 167–181.
Quantifying the influence of previously burned areas on suppression effectiveness and avoided exposure: a case study of the Las Conchas Fire.CrossRef | open url image1

Tidwell TL (2016) Chief’s letter of intent – 2016 wildland fire. File Code 5100. USDA Forest Service, Washington Office, 5 April 2016 (Washington, DC).

US Census Bureau (2015) ‘TIGER/Line 2015 Roads.’ Available at ftp://ftp2.census.gov/geo/tiger/TIGER2015/ROADS/ [Verified 18 November 2015].

USGS (2015) ‘USGS National Hydrography Dataset.’ Available at http://viewer.nationalmap.gov/basic/?howTo=true [Verified 18 November 2015].

Ward G, Hastie T, Barry S, Elith J, Leathwick JR (2009) Presence-only data and the EM algorithm. Biometrics 65, 554–563.
Presence-only data and the EM algorithm.CrossRef | open url image1

Weiss AD (2001) Topographic position and landforms analysis. Conference poster for ‘21st Annual ESRI International User Conference’, 9–13 July 2001, San Diego, CA. Available at http://www.jennessent.com/arcview/TPI_Weiss_poster.htm [Verified 24 January 2017]

Wu Z, He HS, Liang Y, Cai L, Lewis BJ (2013) Determining relative contributions of vegetation and topography to burn severity from LANDSAT imagery. Environmental Management 52, 821–836.
Determining relative contributions of vegetation and topography to burn severity from LANDSAT imagery.CrossRef | open url image1



Supplementary MaterialSupplementary Material (454 KB) Export Citation Cited By (1)