Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data

Predicting wildfire spread is critical for land management and disaster preparedness. To this end, we present ‘Next Day Wildfire Spread,’ a curated, large-scale, multivariate data set of historical wildfires aggregating nearly a decade of remotesensing data across the United States. In contrast to existing fire data sets based on Earth observation satellites, our data set combines 2D fire data with multiple explanatory variables (e.g., topography, vegetation, weather, drought index, population density) aligned over 2D regions, providing a feature-rich data set for machine learning. To demonstrate the usefulness of this data set, we implement a convolutional autoencoder that takes advantage of the spatial information of this data to predict wildfire spread. We compare the performance of the neural network with other machine learning models: logistic regression and random forest. This data set can be used as a benchmark for developing wildfire propagation models based on remote sensing data for a lead time of one day.

[1]  Corinne Lampin,et al.  A Review of the Main Driving Factors of Forest Fire Ignition Over Europe , 2013, Environmental Management.

[2]  Wang Li,et al.  Fire Risk Prediction Using Remote Sensed Products: A Case of Cambodia , 2017 .

[3]  A. Sullivan,et al.  Wildland surface fire spread modelling, 1990–2007. 2: Empirical and quasi-empirical models , 2007, 0706.4128.

[4]  David Radke,et al.  FireCast: Leveraging Deep Learning to Predict Wildfire Spread , 2019, IJCAI.

[5]  Sean A. Parks,et al.  High-severity fire: evaluating its key drivers and mapping its probability across western US forests , 2018 .

[6]  Cristina Vega-García,et al.  A multivariate analysis of biophysical factors and forest fires in Spain, 1991–2005 , 2012 .

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

[8]  E. Rigolot,et al.  Fuel-break assessment with an expert appraisement approach. , 2002 .

[9]  M. Moritz,et al.  Large wildfire trends in the western United States, 1984–2011 , 2014 .

[10]  Yuri Sousa Aurelio,et al.  Learning from Imbalanced Data Sets with Weighted Cross-Entropy Function , 2019, Neural Processing Letters.

[11]  R. Wein,et al.  Biotic and abiotic regulation of lightning fire initiation in the mixedwood boreal forest. , 2006, Ecology.

[12]  A. Sullivan.  Wildland surface fire spread modelling, 1990–2007. 3: Simulation and mathematical analogue models , 2009 .

[13]  Timothy J. Schmit,et al.  A Closer Look at the ABI on the GOES-R Series , 2017 .

[14]  J. Randerson,et al.  The Global Fire Atlas of individual fire size, duration, speed, and direction , 2018 .

[15]  Brian Y. Lattimer,et al.  Wildland Fire Spread Modeling Using Convolutional Neural Networks , 2019, Fire Technology.

[16]  Younes Oulad Sayad,et al.  Predictive modeling of wildfires: A new dataset and machine learning approach , 2019, Fire Safety Journal.

[17]  B. Malamud,et al.  Characterizing wildfire regimes in the United States. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Biswajeet Pradhan,et al.  A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area , 2017 .

[19]  Matthew P. Thompson,et al.  Application of Wildfire Risk Assessment Results to Wildfire Response Planning in the Southern Sierra Nevada, California, USA , 2016 .

[20]  T. Swetnam,et al.  Warming and Earlier Spring Increase Western U.S. Forest Wildfire Activity , 2006, Science.

[21]  Padhraic Smyth,et al.  Machine learning to predict final fire size at the time of ignition , 2019, International journal of wildland fire.

[22]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[23]  José Ramón Rodríguez-Pérez,et al.  Biophysical and lightning characteristics drive lightning-induced fire occurrence in the central plateau of the Iberian Peninsula , 2016 .

[24]  J. Randerson,et al.  Global fire emissions estimates during 1997–2016 , 2017 .

[25]  G. González,et al.  Fire weather and likelihood: characterizing climate space for fire occurrence and extent in Puerto Rico , 2017, Climatic Change.

[26]  Roger D. Peng,et al.  On the distribution of wildfire sizes , 2003 .

[27]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[28]  Christopher C. Schmidt,et al.  Early characterization of the active fire detection products derived from the next generation NPOESS/VIIRS and GOES-R/ABI instruments , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[29]  Bernard Zenko,et al.  Estimating the risk of fire outbreaks in the natural environment , 2012, Data Mining and Knowledge Discovery.

[30]  D. Brillinger,et al.  Risk assessment: a forest fire example , 2003 .

[31]  Qing Wang,et al.  Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data , 2020, ArXiv.

[32]  Nathaniel P. Robinson,et al.  Mean Composite Fire Severity Metrics Computed with Google Earth Engine Offer Improved Accuracy and Expanded Mapping Potential , 2018, Remote. Sens..

[33]  Mark Crowley,et al.  A review of machine learning applications in wildfire science and management , 2020, Environmental Reviews.

[34]  Saeed Jazebi,et al.  Review of Wildfire Management Techniques—Part II: Urgent Call for Investment in Research and Development of Preventative Solutions , 2020, IEEE Transactions on Power Delivery.

[35]  Jennifer K. Balch,et al.  Human-started wildfires expand the fire niche across the United States , 2017, Proceedings of the National Academy of Sciences.

[36]  Jagannath Aryal,et al.  Deep cognitive imaging systems enable estimation of continental-scale fire incidence from climate data , 2013, Scientific Reports.

[37]  J. San-Miguel-Ayanz,et al.  A global wildfire dataset for the analysis of fire regimes and fire behaviour , 2019, Scientific Data.

[38]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[39]  Yu Wei,et al.  Risk Management and Analytics in Wildfire Response , 2019, Current Forestry Reports.

[40]  J. Abatzoglou.  Development of gridded surface meteorological data for ecological applications and modelling , 2013 .

[41]  Imad H. Elhajj,et al.  Efficient forest fire occurrence prediction for developing countries using two weather parameters , 2011, Eng. Appl. Artif. Intell..

[42]  E. Marino,et al.  Forest fuel management for wildfire prevention in Spain: a quantitative SWOT analysis , 2014 .

[43]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[44]  Jaakko Kukkonen,et al.  Mortality due to Vegetation Fire–Originated PM2.5 Exposure in Europe—Assessment for the Years 2005 and 2008 , 2016, Environmental health perspectives.

[45]  Dimitar Ouzounov,et al.  Terra and Aqua MODIS products available from NASA GES DAAC , 2004 .

[46]  Sue A. Ferguson,et al.  Space-time modelling of lightning-caused ignitions in the Blue Mountains, Oregon , 2001 .

[47]  Philippe Ciais,et al.  FRY, a global database of fire patch functional traits derived from space-borne burned area products , 2018, Scientific Data.

[48]  Diane K. Davies,et al.  Fire Information for Resource Management System: Archiving and Distributing MODIS Active Fire Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[49]  Thomas A. Hennig,et al.  The Shuttle Radar Topography Mission , 2001, Digital Earth Moving.

[50]  James Bennett,et al.  The Netflix Prize , 2007 .

[51]  David E. Rupp,et al.  Seasonal Climate Variability and Change in the Pacific Northwest of the United States , 2014 .