Ensemble lightning prediction models for the province of Alberta, Canada
Karen D. Blouin A B E , Mike D. Flannigan A B , Xianli Wang A B C and Bohdan Kochtubajda D
+ Author Affiliations
- Author Affiliations
A Department of Renewable Resources, University of Alberta, 751 General Services Building, Edmonton, AB T6G 2H1, Canada.
B Western Partnership for Wildland Fire Science, 751 General Services Building, Edmonton, AB T6G 2H1, Canada.
C Present address: Great Lakes Forestry Centre, Canadian Forest Service, Natural Resources Canada, 1219 Queen Street East, Sault Ste. Marie, ON P6A 2E5, Canada.
D Environment and Climate Change Canada, Meteorological Service of Canada, 9250-49th Street NW, Edmonton, AB T6B 1K5, Canada.
E Corresponding author: Email: karen.blouin@ualberta.ca
International Journal of Wildland Fire 25(4) 421-432 https://doi.org/10.1071/WF15111
Submitted: 6 June 2015 Accepted: 9 December 2015 Published: 3 March 2016
Abstract
Lightning is a major cause of wildland fires in Canada. During an average year in the province of Alberta, 330 000 cloud-to-ground lightning strikes occur. These strikes are responsible for igniting 45% of reported wildfires (~450 fires) and 71% of area burned (~105 000 ha). Lightning-caused wildland fires in remote areas have large suppression costs and a greater chance of escaping initial attack when compared with human-caused fires, which are often located close to infrastructure and suppression resources. In this study, geographic and temporal covariates were paired with meteorological reanalysis and radiosonde observations to generate a series of 6-h and 24-h lightning prediction models valid from April to October. These models, based on cloud-to-ground lightning from the Canadian Lightning Detection Network, were developed and validated for the province of Alberta, Canada. The ensemble forecasts produced from these models were most accurate in the Rocky Mountain and Foothills Natural Regions, achieving hits rates of 85%. The Showalter index, latitude, elevation, longitude, Julian day and convective available potential energy were found to be highly important predictors. Random forest classification is introduced as a viable modelling method to generate lightning forecasts.
Additional keywords: CLDN, cloud-to-ground lightning, Random Forest, RandomForest, wildfire.
References
Alberta Government (2015) Historical wildfire database (1961–2014). Available at http://wildfire.alberta.ca/wildfire-maps/historical-wildfire-information/historical-wildfire-database.aspx [Verified 11 September 2015]Anderson K (1991) Models to predict lightning occurrence and frequency over Alberta. MSc. thesis, University of Alberta, Edmonton.
Anderson K (2002) A model to predict lightning-caused fire occurrences. International Journal of Wildland Fire 11, 163–172.
| A model to predict lightning-caused fire occurrences.Crossref | GoogleScholarGoogle Scholar |
Berger K (1967) Novel observations on lightning discharges – results of research on Mount San Salvatore. Journal of the Franklin Institute 283, 478–525.
| Novel observations on lightning discharges – results of research on Mount San Salvatore.Crossref | GoogleScholarGoogle Scholar |
Beverly JL, Flannigan MD, Stocks BJ, Bothwell P (2011) The association between northern hemisphere climate patterns and interannual variability in Canadian wildfire activity. Canadian Journal of Forest Research 41, 2193–2201.
| The association between northern hemisphere climate patterns and interannual variability in Canadian wildfire activity.Crossref | GoogleScholarGoogle Scholar |
Blouin K (2014) Lightning prediction models for the province of Alberta, Canada. MSc thesis, University of Alberta, Canada.
Bolton D (1980) The computation of equivalent potential temperature. Monthly Weather Review 108, 1046–1053.
| The computation of equivalent potential temperature.Crossref | GoogleScholarGoogle Scholar |
Breiman L (2001) Random forests. Machine Learning 45, 5–32.
| Random forests.Crossref | GoogleScholarGoogle Scholar |
Burrows WR (2002) Statistical models for lightning prediction using Canadian Lightning Detection Network observations. In ‘16th conference on probability and statistics in the atmospheric sciences’, 13–17 January 2002, Orlando, FL. pp. 120–125. (American Meteorological Society: Boston, MA)
Burrows WR (2008) Dynamical-statistical models for lightning prediction to 48-hours over Canada and the United States. In ‘20th international lightning detection conference’, 21–23 April 2008, Tucson, AZ.
Burrows WR, Kochtubajda B (2010) A decade of cloud‐to‐ground lightning in Canada: 1999–2008. Part 1: Flash density and occurrence. Atmosphere-ocean 48, 177–194.
| A decade of cloud‐to‐ground lightning in Canada: 1999–2008. Part 1: Flash density and occurrence.Crossref | GoogleScholarGoogle Scholar |
Burrows WR, King P, Lewis PJ, Kochtubajda B, Snyder B, Turcotte V (2002) Lightning occurrence patterns over Canada and adjacent United States from Lightning Detection Network observations. Atmosphere–ocean 40, 59–80.
| Lightning occurrence patterns over Canada and adjacent United States from Lightning Detection Network observations.Crossref | GoogleScholarGoogle Scholar |
Burrows WR, Price C, Wilson LJ (2005) Warm-season lightning probability prediction for Canada and the northern United States. Weather and Forecasting 20, 971–988.
| Warm-season lightning probability prediction for Canada and the northern United States.Crossref | GoogleScholarGoogle Scholar |
Chen C, Liaw A, Breiman L (2004) Using random forest to learn imbalance data. Department of Statistics, University of California. (Berkeley, CA)
Clodman S, Chisholm W (1996) Lightning flash climatology in the southern Great Lakes region. Atmosphere-ocean 34, 345–377.
| Lightning flash climatology in the southern Great Lakes region.Crossref | GoogleScholarGoogle Scholar |
Côté J, Gravel S, Méthot A, Patoine A, Roch M, Staniforth A (1998) The operational CMC-MRB global environmental multiscale (GEM) model. Part I: Design considerations and formulation. Monthly Weather Review 126, 1373–1395.
| The operational CMC-MRB global environmental multiscale (GEM) model. Part I: Design considerations and formulation.Crossref | GoogleScholarGoogle Scholar |
Crozier CL, Herscovitch HN, Scott JW (1988) Some observations and characteristics of lightning ground discharges in southern Ontario. Atmosphere–ocean 26, 399–436.
| Some observations and characteristics of lightning ground discharges in southern Ontario.Crossref | GoogleScholarGoogle Scholar |
Cummins KL, Murphy MJ (2009) An overview of lightning locating systems: history, techniques, and data uses, with an in-depth look at the US NLDN. IEEE Transactions on Electromagnetic Compatibility 51, 499–518.
| An overview of lightning locating systems: history, techniques, and data uses, with an in-depth look at the US NLDN.Crossref | GoogleScholarGoogle Scholar |
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT (2007) Random forests for classification in ecology. Ecology 88, 2783–2792.
| Random forests for classification in ecology.Crossref | GoogleScholarGoogle Scholar | 18051647PubMed |
de Groot WJ, Cantin AS, Flannigan MD, Soja AJ, Gowman LM, Newbery A (2013) A comparison of Canadian and Russian boreal forest fire regimes. Forest Ecology and Management 294, 23–34.
| A comparison of Canadian and Russian boreal forest fire regimes.Crossref | GoogleScholarGoogle Scholar |
Dormann CF, Elith J, Bacher S, Buchmann C, Carl G, Carré G, García Marquéz JR, Gruber B, Lafourcade B, Leitão PJ, Münkemüller T, McClean C, Osborne PE, Reineking B, Schröder B, Skidmore AK, Zurell D, Lautenbach S (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 | GoogleScholarGoogle Scholar |
Dupilka ML, Reuter GW (2011) Composite soundings associated with severe and tornadic thunderstorms in central Alberta. Atmosphere-ocean 49, 269–278.
| Composite soundings associated with severe and tornadic thunderstorms in central Alberta.Crossref | GoogleScholarGoogle Scholar |
Flannigan MD, Wotton BM (1991) Lightning-ignited forest fires in north-western Ontario. Canadian Journal of Forest Research 21, 277–287.
| Lightning-ignited forest fires in north-western Ontario.Crossref | GoogleScholarGoogle Scholar |
Flannigan MD, Krawchuk MA, de Groot WJ, Wotton BM, Gowman LM (2009a) Implications of changing climate for global wildland fire. International Journal of Wildland Fire 18, 483–507.
| Implications of changing climate for global wildland fire.Crossref | GoogleScholarGoogle Scholar |
Flannigan MD, Stocks BJ, Turetsky M, Wotton BM (2009b) Impacts of climate change on fire activity and fire management in the circumboreal forest. Global Change Biology 15, 549–560.
| Impacts of climate change on fire activity and fire management in the circumboreal forest.Crossref | GoogleScholarGoogle Scholar |
Forestry Canada Fire Danger Group (1992) Development and structure of the Canadian Forest Fire Behavior Prediction System. Fire Danger Group and Science and Sustainable Development Directorate, Information Report ST-X-3. (Ottawa, ON)
Fuquay DM, Baughman RG, Taylor AR, Hawe RG (1967) Characteristics of 7 lightning discharges that caused forest fires. Journal of Geophysical Research 72, 6371–6373.
| Characteristics of 7 lightning discharges that caused forest fires.Crossref | GoogleScholarGoogle Scholar |
Fuquay DM, Taylor AR, Hawe RG, Schmid CW (1972) Lightning discharges that caused forest fires. Journal of Geophysical Research 77, 2156–2158.
| Lightning discharges that caused forest fires.Crossref | GoogleScholarGoogle Scholar |
Fuquay DM, Baughman RG, Latham DJ (1979) A model for predicting lightning fire ignition in wildland fuels. USDA Forest Service, Intermountain Forest and Range Experiment Station, Research Paper INT-217. (Ogden, UT)
Furrer R, Nychka D, Sain S (2013) fields: Tools for spatial data. R package version 6.9.1. Available at http:/CRAN.R-project.org/package=fields [Verified 14 October 2013]
Haines D (1988) A lower-atmosphere severity index for wildland fires. National Weather Digest 13, 23–27.
Hanuta I, LaDochy S (1989) Thunderstorm climatology based on lightning detector data, Manitoba, Canada. Physical Geography 10, 101–119.
Hothorn T, Hornik K, Strobl C, Zeileis A (2013) party: a laboratory for recursive partytioning. Available at http://cran.r-project.org/web/packages/party/vignettes/party.pdf [Verified 14 October 2013]
Johari D, Abdul Rahman TK, Musirin I (2007) Artificial neural network based technique for lightning prediction. In ‘5th student conference on research and development SCOReD 2007’, 11–12 December 2007, Selangor, Malaysia. pp. 1–5.
Kalnay E, Kanamitsu M, Kistler R, Collins W, Deaven D, Gandin L, Iredell M, Saha S, White G, Woollen J, Zhu Y, Chelliah M, Ebisuzaki W, Higgins W, Janowiak J, Mo KC, Ropelewki C, Wang J, Leetmaa A, Reynolds R, Jenne R, Joseph D (1996) The NCEP/NCAR 40-year reanalysis project. Bulletin of the American Meteorological Society 77, 437–471.
| The NCEP/NCAR 40-year reanalysis project.Crossref | GoogleScholarGoogle Scholar |
Kanamitsu M, Ebisuzaki W, Woollen J, Yang S, Hnilo JJ, Fiorino M, Potter GL (2002) NCEP–DOE AMIP-II Reanalysis (R-2). Bulletin of the American Meteorological Society 83, 1631–1643.
| NCEP–DOE AMIP-II Reanalysis (R-2).Crossref | GoogleScholarGoogle Scholar |
Kochtubajda B, Burrows WR (2010) A decade of cloud‐to‐ground lightning in Canada: 1999–2008. Part 2: Polarity, multiplicity and first‐stroke peak current. Atmosphere–ocean 48, 195–209.
| A decade of cloud‐to‐ground lightning in Canada: 1999–2008. Part 2: Polarity, multiplicity and first‐stroke peak current.Crossref | GoogleScholarGoogle Scholar |
Krause A, Kloster S, Wilkenskejeld S, Paeth H (2014) The sensitivity of global wildfires to simulated past, present, and future lightning frequency. Journal of Geophysical Research. Biogeosciences 119, 312–322.
| The sensitivity of global wildfires to simulated past, present, and future lightning frequency.Crossref | GoogleScholarGoogle Scholar |
Krawchuk MA, Cumming SG, Flannigan MD, Wein RW (2006) Biotic and abiotic regulation of lightning fire initiation in the mixedwood boreal forest. Ecology 87, 458–468.
| Biotic and abiotic regulation of lightning fire initiation in the mixedwood boreal forest.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BD283jtVWrtA%3D%3D&md5=38815a2b9dee51d3d7b7e2796a3dea27CAS | 16637370PubMed |
Kubat M, Matwin S (1997) Addressing the curse of imbalanced training sets: one-sided selection. In ‘Machine learning: proceedings of the fourteenth international conference (ICML’97)’, 8–13 July 1997, San Francisco, CA. (Ed. D Fisher) pp. 179–186. (Morgan Kaufmann Publishers: Burlington, MA)
Kuhn M (2013) caret: Classification and regression training. R package version 6.0–21. Available at http://CRAN.R-project.org/package=caret [Verified 14 October 2013]
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2, 18–22.
Mazany RA, Businger S, Gutman SI, Roeder W (2002) A lightning prediction index that utilizes GPS integrated precipitable water vapor. Weather and Forecasting 17, 1034–1047.
| A lightning prediction index that utilizes GPS integrated precipitable water vapor.Crossref | GoogleScholarGoogle Scholar |
Mbogga MS, Wang X, Hamann A (2010) Bioclimate envelope model predictions for natural resource management: dealing with uncertainty. Journal of Applied Ecology 47, 731–740.
| Bioclimate envelope model predictions for natural resource management: dealing with uncertainty.Crossref | GoogleScholarGoogle Scholar |
Mills B, Unrau D, Parkinson C, Jones B, Yessis J, Spring K, Pentelow L (2008) Assessment of lightning-related fatality and injury risk in Canada. Natural Hazards 47, 157–183.
| Assessment of lightning-related fatality and injury risk in Canada.Crossref | GoogleScholarGoogle Scholar |
Nash CH, Johnson EA (1996) Synoptic climatology of lightning-caused forest fires in subalpine and boreal forests. Canadian Journal of Forest Research 26, 1859–1874.
| Synoptic climatology of lightning-caused forest fires in subalpine and boreal forests.Crossref | GoogleScholarGoogle Scholar |
Natural Regions Committee (2006) ‘Natural regions and subregions of Alberta.’ Available at http://www.environment.gov.ab.ca/info/library/8031.pdf [Verified 19 January 2015]
Orville RE, Huffines GR, Burrows WR, Holle RL, Cummins KL (2002) The North American Lightning Detection Network (NALDN) – first results: 1998–2000. Monthly Weather Review 130, 2098–2109.
| The North American Lightning Detection Network (NALDN) – first results: 1998–2000.Crossref | GoogleScholarGoogle Scholar |
Phillips DW (1990) ‘The Climates of Canada.’ (Canadian Government Publishing Centre: Ottawa, ON)
Romps DM, Seeley JT, Vollaro D, Molinari J (2014) Projected increase in lightning strikes in the United States due to global warming. Science 346, 851–854.
| Projected increase in lightning strikes in the United States due to global warming.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC2cXhvV2nt7fK&md5=db61c181c8795a8778393141b5c3bdffCAS | 25395536PubMed |
Rorig ML, Ferguson SA (1999) Characteristics of lightning and wildland fire ignition in the Pacific Northwest. Journal of Applied Meteorology 38, 1565–1575.
| Characteristics of lightning and wildland fire ignition in the Pacific Northwest.Crossref | GoogleScholarGoogle Scholar |
Segal M (2004) Machine learning benchmarks and random forest regression. (Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA) Available at http://escholarship.org/uc/item/35x3v9t4 [Verified 8 Decmeber 2013]
Showalter AK (1947) A stability index for forecasting thunderstorms. Bulletin of the American Meteorological Society 34, 250–252.
Stamp RM (2009) Alberta: climate. Available at http://www.thecanadianencyclopedia.com/en/article/alberta/ [Verified 16 October 2015]
Stanski HR, Wilson LJ, Burrows WR (1989) Survey of common verification methods in meteorology. World Weather Watch Technical Report 8, WMO/TD 358, World Meteorological Organization, Geneva.
Statistics Canada (2005) Land and freshwater area, by province and territory. Available at http://www.statcan.gc.ca/tables-tableaux/sum-som/l01/cst01/phys01-eng.htm [Verified 18 January 2012]
Stocks BJ, Mason JA., Todd JB, Bosch EM, Wotton BM, Amiro BD, Flannigan MD, Hirsch KG, Logan KA, Martell DL, Skinner WR (2002) Large forest fires in Canada, 1959–1997. Journal of Geophysical Research 107, 8149
| Large forest fires in Canada, 1959–1997.Crossref | GoogleScholarGoogle Scholar |
Stralberg D, Matsuoka SM, Hamann A, Bayne EM, Sólymos P, Schmiegelow FKA, Wang X, Cumming SG, Song SJ (2015) Projecting boreal bird responses to climate change: the signal exceeds the noise. Journal of Applied Ecology 25, 52–69.
| Projecting boreal bird responses to climate change: the signal exceeds the noise.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BC287htlKmug%3D%3D&md5=9a62dfe3669593309da642ed1f9ae6b1CAS |
Strobl C, Boulesteix AL, Zeileis A, Hothorn T (2007) Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinformatics 8, 25
| Bias in random forest variable importance measures: illustrations, sources and a solution.Crossref | GoogleScholarGoogle Scholar | 17254353PubMed |
Strobl C, Boulesteix AL, Kneib T, Augustin T, Zeileis A (2008) Conditional variable importance for random forests. BMC Bioinformatics 9, 307
| Conditional variable importance for random forests.Crossref | GoogleScholarGoogle Scholar | 18620558PubMed |
Tait A, Henderson R, Turner R, Zheng XG (2006) Smoothing spline interpolation of daily rainfall for New Zealand using a climatological rainfall surface. International Journal of Climatology 26, 2097–2115.
| Smoothing spline interpolation of daily rainfall for New Zealand using a climatological rainfall surface.Crossref | GoogleScholarGoogle Scholar |
Tolosi L, Lengauer T (2011) Classification with correlated features: unreliability of feature ranking and solutions. Bioinformatics 27, 1986–1994.
| Classification with correlated features: unreliability of feature ranking and solutions.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC3MXoslyisbc%3D&md5=a3b2f8b7749fe6d58e4ee33c21ada581CAS | 21576180PubMed |
Van Wagner CE (1987) Development and structure of the Canadian Forest Fire Weather Index System. Canadian Forest Service, Technical Report 35. (Ottawa, ON)
Wang X, Thompson D, Marshall GA, Tymstra C, Carr R, Flannigan MD (2015) Increasing frequency of extreme fire weather in Canada with climate change. Climatic Change 130, 573–586.
| Increasing frequency of extreme fire weather in Canada with climate change.Crossref | GoogleScholarGoogle Scholar |
Wierzchowski J, Heathcott M, Flannigan MD (2002) Lightning and lightning fire, Central Cordillera, Canada. International Journal of Wildland Fire 11, 41–51.
| Lightning and lightning fire, Central Cordillera, Canada.Crossref | GoogleScholarGoogle Scholar |
Wotton BM, Stocks BJ (2006) Fire management in Canada: vulnerability and risk trends. In ‘Canadian wildland fire strategy: background, synthesis, analysis, and perspectives’. (Tech. Coords KG Hirsch, P Fuglem) pp. 49–55. (Northern Forestry Centre: Edmonton, AB)
Xiao YC, Ziebarth JP, Woodbury C, Bayer E, Rundell B, VanderZijp J (1996) The challenges of visualizing and modeling environmental data. In ‘IEEE visualization ’96 proceedings’, 27 October–1 November 1996, San Francisco, CA. pp. 413–416. (New York, NY)
