Deep cognitive imaging systems enable estimation of continental-scale fire incidence from climate data

Unplanned fire is a major control on the nature of terrestrial ecosystems and causes substantial losses of life and property. Given the substantial influence of climatic conditions on fire incidence, climate change is expected to substantially change fire regimes in many parts of the world. We wished to determine whether it was possible to develop a deep neural network process for accurately estimating continental fire incidence from publicly available climate data. We show that deep recurrent Elman neural network was the best performed out of ten artificial neural networks (ANN) based cognitive imaging systems for determining the relationship between fire incidence and climate. In a decennium data experiment using this ANN we show that it is possible to develop highly accurate estimations of fire incidence from monthly climatic data surfaces. Our estimations for the continent of Australia had over 90% global accuracy and a very low level of false negatives. The technique is thus appropriate for use in estimating the spatial consequences of climate scenarios on the monthly incidence of wildfire at the landscape scale.

[1]  W. Bond,et al.  Fire as a global 'herbivore': the ecology and evolution of flammable ecosystems. , 2005, Trends in ecology & evolution.

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Dianne Simmons.  Australia burning : fire ecology, policy and management issues , 2004 .

[4]  A. Gill,et al.  Landscape fires as social disasters: An overview of ‘the bushfire problem’ , 2005 .

[5]  Christopher I. Roos,et al.  Fire in the Earth System , 2009, Science.

[6]  David B. Lindenmayer,et al.  Australia Burning: Fire Ecology, Policy and Management Issues , 2003 .

[7]  R. Bradstock.  A biogeographic model of fire regimes in Australia: current and future implications , 2010 .

[8]  Christopher Lucas,et al.  Prediction of the probability of large fires in the Sydney region of south-eastern Australia using fire weather , 2009 .

[9]  S. Harrison,et al.  Late Quaternary fire regimes of Australasia , 2012 .

[10]  F. Joos,et al.  Climate and human influences on global biomass burning over the past two millennia , 2008 .

[11]  Jiaqiu Wang,et al.  Integrated Spatio‐temporal Data Mining for Forest Fire Prediction , 2008, Trans. GIS.

[12]  A. Belward,et al.  Characterizing interannual variations in global fire calendar using data from Earth observing satellites , 2005 .

[13]  Christopher Lucas,et al.  Changes in Australian fire weather between 1973 and 2010 , 2013 .

[14]  A. Gill,et al.  Bushfires 'down under': patterns and implications of contemporary Australian landscape burning , 2007 .

[15]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[16]  A. Gill,et al.  Spatial scale invariance of southern Australian forest fires mirrors the scaling behaviour of fire-driving weather events , 2008, Landscape Ecology.

[17]  Amparo Alonso-Betanzos,et al.  An intelligent system for forest fire risk prediction and fire fighting management in Galicia , 2003, Expert Syst. Appl..

[18]  J. Logan,et al.  Impacts of climate change from 2000 to 2050 on wildfire activity and carbonaceous aerosol concentrations in the western United States , 2009 .

[19]  M. Moritz,et al.  Environmental controls on the distribution of wildfire at multiple spatial scales , 2009 .

[20]  M. G. Ryan,et al.  Continued warming could transform Greater Yellowstone fire regimes by mid-21st century , 2011, Proceedings of the National Academy of Sciences.

[21]  David J. Lohman,et al.  The Burning Issue , 2007, Science.

[22]  J. Goldammer,et al.  Potential Impacts of Climate Change on Fire Regimes in the Tropics Based on Magicc and a GISS GCM-Derived Lightning Model , 1998 .

[23]  Ralph A. Wilson.  Observations of Extinction and Marginal Burning States in Free Burning Porous Fuel Beds , 1985 .