{"type":"ScholarlyArticle","title":"FireCast: Leveraging Deep Learning to Predict Wildfire Spread","authors":[{"name":"David Radke","slug":"david-radke","given":"David","family":"Radke","affiliation":"School of Computer Science , University of Waterloo"},{"name":"Anna Hessler","slug":"anna-hessler","given":"Anna","family":"Hessler","affiliation":"Department of Mathematics and Computer Science , Colorado College"},{"name":"Dan Ellsworth","slug":"dan-ellsworth","given":"Dan","family":"Ellsworth","affiliation":"Department of Mathematics and Computer Science , Colorado College"}],"abstract":"Destructive wildfires result in billions of dollars in damage each year and are expected to increase in frequency, duration, and severity due to climate change. The current state-of-the-art wildfire spread models rely on mathematical growth predictions and physics-based models, which are difficult and computationally expensive to run. We present and evaluate a novel system, FireCast. FireCast combines artificial intelligence (AI) techniques with data collection strategies from geographic information systems (GIS). FireCast predicts which areas surrounding a burning wildfire have high-risk of near-future wildfire spread, based on historical fire data and using modest computational resources. FireCast is compared to a random prediction model and a commonly used wildfire spread model, Farsite, outperforming both with respect to total accuracy, recall, and F-score.","doi":"10.24963/ijcai.2019/636","url":"https://ijcai.org/proceedings/2019/636","pdf":"https://ijcai.org/proceedings/2019/0636.pdf","markdown":"https://ijcai.org/proceedings/2019/636.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/636","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning Applications","track":"Main track","number":636,"pages":{"first":4575,"last":4581},"keywords":["Machine Learning Applications: Applications of Supervised Learning","Machine Learning Applications: Big data ; Scalability","Machine Learning Applications: Environmental"],"videos":[],"references":[{"position":1,"raw":"[Barker, 2008] Terry Barker. The economics of avoiding dangerous climate change. an editorial essay on the stern review. Climatic Change, 89(3):173-194, Aug 2008.","title":"The economics of avoiding dangerous climate change. an editorial essay on the stern review","authors":"Terry Barker","year":"2008","venue":"Climatic Change","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Carlson and Ripley, 1997] Toby N. Carlson and David A. Ripley. On the relation between ndvi, fractional vegeta- tion cover, and leaf area index. Remote Sensing of Envi- ronment, 62(3):241-252, 1997.","title":"On the relation between ndvi, fractional vegetation cover, and leaf area index","authors":"Toby N Carlson, David A Ripley","year":"1997","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ding et al., 2018] Peng Ding, Ye Zhang, Ping Jia, and Xu- ling Chang. A comparison: Different dcnn models for in- telligent object detection in remote sensing images. Neural Processing Letters, Jun 2018.","title":"A comparison: Different dcnn models for intelligent object detection in remote sensing images","authors":"Peng Ding, Ye Zhang, Ping Jia, Xuling Chang","year":"2018","venue":"Neural Processing Letters","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Finney et al., ] Mark Finney, Isaac C. Grenfell, and Charles W. McHugh. Modeling containment of large wild- fires using generalized linear mixed-model analysis. Forest Science, 55(3):249-255.","title":"Modeling containment of large wildfires using generalized linear mixed-model analysis","authors":"Finney","year":null,"venue":"Forest Science","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Finney, 1994] Mark A. Finney. Farsite: a fire area simula- tor for fire managers. The Biswell symposium: fire issues and solutions in urban interface and wildland ecosystems, pages 55-56, Feb 1994.","title":"Farsite: a fire area simulator for fire managers","authors":"A Mark, Finney","year":"1994","venue":"The Biswell symposium: fire issues and solutions in urban interface and wildland ecosystems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Finney, 1998] Mark A. Finney. FARSITE: Fire Area Sim- ulator-Model Development and Evaluation. US Forest Service, Ogden, Utah, 1998.","title":"FARSITE: Fire Area Simulator-Model Development and Evaluation","authors":"A Mark, Finney","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Forghani et al., 2007] Alan Forghani, Bob Cachet, John Radke, Mark Finney, and Bret Butler. Applying fire spread simulation over two study sites in california lessons learned and future plans. IEEE Interantional Geosciences Remote Sensing Symposium, pages 3008-30013, 2007.","title":"Applying fire spread simulation over two study sites in california lessons learned and future plans","authors":"Alan Forghani, Bob Cachet, John Radke, Mark Finney, Bret Butler","year":"2007","venue":"IEEE Interantional Geosciences Remote Sensing Symposium","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Houtman et al., 2013] Rachel M. Houtman, Claire A. Montgomery, Aaron R. Gagnon, David E. Calkin, Thomas G. Dietterich, Sean McGregor, and Mark Crow- ley. Allowing a wildfire to burn: estimating the effect on future fire suppression costs. International Journal of Wildland Fire, 22:871-882, 2013.","title":"Allowing a wildfire to burn: estimating the effect on future fire suppression costs","authors":"Rachel M Houtman, Claire A Montgomery, Aaron R Gagnon, David E Calkin, Thomas G Dietterich, Sean Mcgregor, Mark Crowley","year":"2013","venue":"International Journal of Wildland Fire","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kocsis and Szepesvári, 2006] Levente Kocsis and Csaba Szepesvári. Bandit based monte-carlo planning. In Johannes Fürnkranz, Tobias Scheffer, and Myra Spiliopoulou, editors, Machine Learning: ECML 2006, pages 282-293, Berlin, Heidelberg, 2006. Springer Berlin Heidelberg.","title":"Bandit based monte-carlo planning","authors":"Szepesvári Kocsis, Levente Kocsis, Csaba Szepesvári","year":"2006","venue":"Machine Learning: ECML 2006","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kourtz and O'Regan, 1971] Peter Kourtz and William G. O'Regan. A model for a small forest fire...to simulate burned and burning areas for use in a detection model. For- est Science, 17(2):163-169, 1971.","title":"A model for a small forest fire...to simulate burned and burning areas for use in a detection model","authors":"O'regan ; Kourtz, Peter Kourtz, William G O'regan","year":"1971","venue":"Forest Science","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lauer et al., 2017] Christopher J. Lauer, Claire A. Mont- gomery, and Thomas G. Dietterich. Spatial interactions and optimal forest management on a fire-threatened land- scape. Forest Policy and Economics, 83:107-120, Oct 2017.","title":"Spatial interactions and optimal forest management on a fire-threatened landscape","authors":"J Christopher, Claire A Lauer, Thomas G Montgomery, Dietterich","year":"2017","venue":"Forest Policy and Economics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lin et al., 2019] Zhonghie Lin, High H. T. Liu, and Mike Wotton. Kalman filter-based large-scale wildfire monitor- ing with a system of uavs. IEEE Transactions on Industrial Electronics, 66(1):606-615, Jan 2019.","title":"Kalman filter-based large-scale wildfire monitoring with a system of uavs","authors":"Zhonghie Lin, H T High, Mike Liu, Wotton","year":"2019","venue":"IEEE Transactions on Industrial Electronics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Maggiori et al., 2017] Emmanuel Maggiori, Yuliya Tara- balka, Guillaume Charpiat, and Pierre Alliez. Convolu- tional neural networks for large-scale remote-sensing im- age classification. IEEE Transactions on Geoscience and Remote Sensing, 55(2):645-657, Feb 2017.","title":"Convolutional neural networks for large-scale remote-sensing image classification","authors":"Maggiori","year":"2017","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[O'Connor et al., 2016] Christopher D. O'Connor, Matthew P. Thompson, and Francisco Rodríguez y Silva. Getting ahead of the wildfire problem: quantifying and mapping management challenges and opportunities. Geosciences, 6(3):35, 2016.","title":"Getting ahead of the wildfire problem: quantifying and mapping management challenges and opportunities","authors":"D Christopher, Matthew P O'connor, Francisco Rodríguez Y Thompson, Silva","year":"2016","venue":"Geosciences","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Radke, 1995] John Radke. Modeling urban/wildland inter- face fire hazards within a geographic information system. Geographic Information Sciences, 1(1):9-21, 1995.","title":"John Radke. Modeling urban/wildland interface fire hazards within a geographic information system","authors":"Radke","year":"1995","venue":"Geographic Information Sciences","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Reidmiller et al., 2018] David R. Reidmiller, Christo- pher W. Avery, David R. Easterling, Kenneth E. Kunkel, Kristin L. M. Lewis, T. K. Maycock, and Bradley C. Stew- art (eds.). Impacts, Risks, and adaptation in the united States: Fouth National Climate Assessment, Volume II.","title":"Impacts, Risks, and adaptation in the united States: Fouth National Climate Assessment","authors":"David R Reidmiller, Christopher W Avery, David R","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Simard et al., 2003] Patrice Y. Simard, Dave Steinkraus, and John C. Platt. Best practices for convolutional neural networks applied to visual document analysis. Proc. Int. Conf. Document Anal. Recognit., 3:958-962, Aug 2003.","title":"Best practices for convolutional neural networks applied to visual document analysis","authors":"Patrice Y Simard, Dave Steinkraus, John C Platt","year":"2003","venue":"Proc. Int. Conf. Document Anal. Recognit","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Stephens et al., 2018] Scott L. Stephens, Brandon M. Collins, Christopher J. Fettig, Mark A. Finney, Chad M. Hoffman, Eric E. Knapp, Malcolm P. North, High Safford, and Rebecca B. Wayman. Drought, tree mortality, and wildfire in forests adapted to frequent fire. BioScience, 68(2):77-88, Feb 2018.","title":"Drought, tree mortality, and wildfire in forests adapted to frequent fire","authors":"L Scott, Brandon M Stephens, Christopher J Collins, Mark A Fettig, Chad M Finney, Eric E Hoffman, Malcolm P Knapp, High North, Rebecca B Safford, Wayman","year":"2018","venue":"BioScience","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Subramanian and Crowley, 2018] Sriram G. Subramanian and Mark Crowley. Combining mcts and a3c for prediction of spatially spreading processes in forest wildfire settings. Canadian AI, LNAI 10832:285-291, 2018.","title":"Combining mcts and a3c for prediction of spatially spreading processes in forest wildfire settings","authors":"G Sriram, Mark Subramanian, Crowley","year":"2018","venue":"Canadian AI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Séro-Guillaume et al., 2008] Olivier Séro-Guillaume, Sepehr Ramezani, Jonathan Margerit, and Didier Calogine. On large scale forest fires propagation models. Int. J. Thermal Science, 47(6):680-694, 2008.","title":"On large scale forest fires propagation models","authors":"Olivier Séro-Guillaume, Sepehr Ramezani, Jonathan Margerit, Didier Calogine","year":"2008","venue":"Int. J. Thermal Science","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Westerling et al., 2006] Anthony L. Westerling, Hugo G. Hidalgo, Daniel R. Cayan, and Thomas W. Swetnam. Warming and earlier spring increase western u.s. forest wildfire activity. Science, 313(5789):940-943, Aug 2006.","title":"Warming and earlier spring increase western u.s. forest wildfire activity","authors":"Anthony L Westerling, Hugo G Hidalgo, Daniel R Cayan, Thomas W Swetnam","year":"2006","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2016] Qingjie Zhang, Jiaolong Xu, Liang Xu, and Haifeng Guo. Deep convolutional neural networks for forest fire detection. In 2016 International Forum on Man- agement, Education and Information Technology Applica- tion. Atlantis Press, 2016.","title":"Deep convolutional neural networks for forest fire detection","authors":"Zhang","year":"2016","venue":"2016 International Forum on Management, Education and Information Technology Application","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}