Skip to main content
Erschienen in:

20.06.2023 | Manuscript

Predicting the Wildland Fire Spread Using a Mixed-Input CNN Model with Both Channel and Spatial Attention Mechanisms

verfasst von: Xingdong Li, Xinyu Wang, Shufa Sun, Yangwei Wang, Sanping Li, Dandan Li

Erschienen in: Fire Technology | Ausgabe 5/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The prediction of wildfire spreading is necessary for managing and fighting the forest fire. The traditional models require higher accuracy of the input parameters, which is impossible in real forest fires. The paper proposed a fire-spreading model based on the dynamic data of the fire field to improve its adaptability. The model is designed using a convolutional neural network with mixed-inputs and attention mechanisms (MI-AM-CNN). It predicts the burn map after a period of time through the multiple-channel image containing terrain variables and the current burn map, and the scalars containing climate variables. The channel and spatial attention modules are integrated to handle the advanced features that contain important fire variables information and strengthen the influence of important features on the prediction. Based on the FARSITE, a large number of data sets are generated for training, validating, and testing the models in the paper. The proposed model MI-AM-CNN is compared with the state-of-the-art neural network models. Quantitative results show that MI-AM-CNN has the highest performance in predicting effectiveness and efficiency, and it can be applied recursively to get the continuous predicted results. In addition, the prediction results of MI-AM-CNN on the historical fire data demonstrate the ability of its application in the real fire case. The MI-AM-CNN can be used as a predictive method in firefighting operations, and its predicted results can provide theoretical support for the forest fire spread prediction method based on artificial intelligence.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Chowdhury EH, Hassan QK (2015) Development of a new daily-scale forest fire danger forecasting system using remote sensing data. Remote Sens 7(3):2431–2448CrossRef Chowdhury EH, Hassan QK (2015) Development of a new daily-scale forest fire danger forecasting system using remote sensing data. Remote Sens 7(3):2431–2448CrossRef
2.
Zurück zum Zitat Zhong M, Fan W, Liu T et al (2003) Statistical analysis on current status of China forest fire safety. Fire Saf J 38(3):257–269CrossRef Zhong M, Fan W, Liu T et al (2003) Statistical analysis on current status of China forest fire safety. Fire Saf J 38(3):257–269CrossRef
3.
Zurück zum Zitat San José R, Pérez JL, González RM et al (2014) Analysis of fire behaviour simulations over Spain with WRF-FIRE. Int J Environ Pollut 55(1–4):148–156CrossRef San José R, Pérez JL, González RM et al (2014) Analysis of fire behaviour simulations over Spain with WRF-FIRE. Int J Environ Pollut 55(1–4):148–156CrossRef
4.
Zurück zum Zitat Guo F, Su Z, Wang G et al (2017) Understanding fire drivers and relative impacts in different Chinese forest ecosystems. Sci Total Environ 605:411–425CrossRef Guo F, Su Z, Wang G et al (2017) Understanding fire drivers and relative impacts in different Chinese forest ecosystems. Sci Total Environ 605:411–425CrossRef
5.
Zurück zum Zitat Sullivan AL (2007) A review of wildland fire spread modelling, 1990-present, 1: Physical and quasi-physical models. arXiv preprint arXiv:0706.3074 Sullivan AL (2007) A review of wildland fire spread modelling, 1990-present, 1: Physical and quasi-physical models. arXiv preprint arXiv:​0706.​3074
6.
Zurück zum Zitat Fons WL (1946) Analysis of fire spread in light forest fuels. J Agric Res 72(3):93–121 Fons WL (1946) Analysis of fire spread in light forest fuels. J Agric Res 72(3):93–121
7.
Zurück zum Zitat Albini FA (1985) A model for fire spread in wildland fuels by-radiation. Combust Sci Technol 42(5–6):229–258CrossRef Albini FA (1985) A model for fire spread in wildland fuels by-radiation. Combust Sci Technol 42(5–6):229–258CrossRef
8.
Zurück zum Zitat Linn R, Reisner J, Colman JJ et al (2002) Studying wildfire behavior using FIRETEC. Int J Wildland Fire 11(4):233–246CrossRef Linn R, Reisner J, Colman JJ et al (2002) Studying wildfire behavior using FIRETEC. Int J Wildland Fire 11(4):233–246CrossRef
9.
Zurück zum Zitat Mell W, Jenkins MA, Gould J et al (2007) A physics-based approach to modelling grassland fires. Int J Wildland Fire 16(1):1–22CrossRef Mell W, Jenkins MA, Gould J et al (2007) A physics-based approach to modelling grassland fires. Int J Wildland Fire 16(1):1–22CrossRef
10.
Zurück zum Zitat Choi SW (2009) Firestar: computerized adaptive testing simulation program for polytomous item response theory models. Appl Psychol Meas 33(8):644CrossRef Choi SW (2009) Firestar: computerized adaptive testing simulation program for polytomous item response theory models. Appl Psychol Meas 33(8):644CrossRef
11.
Zurück zum Zitat Sullivan AL (2009) Wildland surface fire spread modelling, 1990–2007: 2—empirical and quasi-empirical models. Int J Wildland Fire 18(4):369–386CrossRef Sullivan AL (2009) Wildland surface fire spread modelling, 1990–2007: 2—empirical and quasi-empirical models. Int J Wildland Fire 18(4):369–386CrossRef
12.
Zurück zum Zitat Wang X, Wotton BM, Cantin AS et al (2017) cffdrs: an R package for the Canadian forest fire danger rating system. Ecol Process 6(1):1–11CrossRef Wang X, Wotton BM, Cantin AS et al (2017) cffdrs: an R package for the Canadian forest fire danger rating system. Ecol Process 6(1):1–11CrossRef
13.
Zurück zum Zitat Leonard S (2009) Predicting sustained fire spread in Tasmanian native grasslands. Environ Manage 44:430–440CrossRef Leonard S (2009) Predicting sustained fire spread in Tasmanian native grasslands. Environ Manage 44:430–440CrossRef
14.
Zurück zum Zitat Rothermel RC (1972) A mathematical model for predicting fire spread in wildland fuels, vol 115. Intermountain Forest & Range Experiment Station, Forest Service, US Departmant of Agriculture Rothermel RC (1972) A mathematical model for predicting fire spread in wildland fuels, vol 115. Intermountain Forest & Range Experiment Station, Forest Service, US Departmant of Agriculture
15.
Zurück zum Zitat Scott JH (2005) Standard fire behavior fuel models: a comprehensive set for use with Rothermel’s surface fire spread model. US Department of Agriculture, Forest Service, Rocky Mountain Research StationCrossRef Scott JH (2005) Standard fire behavior fuel models: a comprehensive set for use with Rothermel’s surface fire spread model. US Department of Agriculture, Forest Service, Rocky Mountain Research StationCrossRef
16.
Zurück zum Zitat Aibin C, Fubo D, Guoxiong Z et al (2022) Simulation model of forest fire spread based on swarm intelligence. J Syst Simulation 34(7):1439 Aibin C, Fubo D, Guoxiong Z et al (2022) Simulation model of forest fire spread based on swarm intelligence. J Syst Simulation 34(7):1439
17.
Zurück zum Zitat Finney MA (1994) FARSITE: a fire area simulator for fire managers. In The proceedings of the Biswell symposium, Walnut Creek, p. 7 Finney MA (1994) FARSITE: a fire area simulator for fire managers. In The proceedings of the Biswell symposium, Walnut Creek, p. 7
18.
Zurück zum Zitat Richards GD (1990) An elliptical growth model of forest fire fronts and its numerical solution. Int J Numer Meth Eng 30(6):1163–1179MATHCrossRef Richards GD (1990) An elliptical growth model of forest fire fronts and its numerical solution. Int J Numer Meth Eng 30(6):1163–1179MATHCrossRef
19.
Zurück zum Zitat Andrews PL, Cruz MG, Rothermel RC (2013) Examination of the wind speed limit function in the Rothermel surface fire spread model. Int J Wildland Fire 22(7):959–969CrossRef Andrews PL, Cruz MG, Rothermel RC (2013) Examination of the wind speed limit function in the Rothermel surface fire spread model. Int J Wildland Fire 22(7):959–969CrossRef
20.
Zurück zum Zitat Andrews PL (2018) The Rothermel surface fire spread model and associated developments: a comprehensive explanation. United States Department of Agriculture, Forest Service, Rocky Mountain Research StationCrossRef Andrews PL (2018) The Rothermel surface fire spread model and associated developments: a comprehensive explanation. United States Department of Agriculture, Forest Service, Rocky Mountain Research StationCrossRef
21.
Zurück zum Zitat Li X, Zhang M, Zhang S et al (2022) Simulating forest fire spread with cellular automation driven by a LSTM based speed model. Fire 5(1):13CrossRef Li X, Zhang M, Zhang S et al (2022) Simulating forest fire spread with cellular automation driven by a LSTM based speed model. Fire 5(1):13CrossRef
22.
Zurück zum Zitat Castelli M, Vanneschi L, Popovič A (2015) Predicting burned areas of forest fires: an artificial intelligence approach. Fire Ecol 11(1):106–118CrossRef Castelli M, Vanneschi L, Popovič A (2015) Predicting burned areas of forest fires: an artificial intelligence approach. Fire Ecol 11(1):106–118CrossRef
23.
Zurück zum Zitat Abid F (2021) A survey of machine learning algorithms based forest fires prediction and detection systems. Fire Technol 57(2):559–590CrossRef Abid F (2021) A survey of machine learning algorithms based forest fires prediction and detection systems. Fire Technol 57(2):559–590CrossRef
24.
Zurück zum Zitat Mao W, Wang W, Dou Z et al (2018) Fire recognition based on multi-channel convolutional neural network. Fire Technol 54:531–554CrossRef Mao W, Wang W, Dou Z et al (2018) Fire recognition based on multi-channel convolutional neural network. Fire Technol 54:531–554CrossRef
25.
Zurück zum Zitat Jeon M, Choi HS, Lee J et al (2021) Multi-scale prediction for fire detection using convolutional neural network. Fire Technol 57(5):2533–2551CrossRef Jeon M, Choi HS, Lee J et al (2021) Multi-scale prediction for fire detection using convolutional neural network. Fire Technol 57(5):2533–2551CrossRef
26.
Zurück zum Zitat Saeed F, Paul A, Karthigaikumar P et al (2020) Convolutional neural network based early fire detection. Multimedia Tools App 79:9083–9099CrossRef Saeed F, Paul A, Karthigaikumar P et al (2020) Convolutional neural network based early fire detection. Multimedia Tools App 79:9083–9099CrossRef
27.
Zurück zum Zitat Allaire F, Mallet V, Filippi JB (2021) Emulation of wildland fire spread simulation using deep learning. Neural Netw 141:184–198CrossRef Allaire F, Mallet V, Filippi JB (2021) Emulation of wildland fire spread simulation using deep learning. Neural Netw 141:184–198CrossRef
28.
Zurück zum Zitat Wu Z, Wang B, Li M et al (2022) Simulation of forest fire spread based on artificial intelligence. Ecol Ind 136:108653CrossRef Wu Z, Wang B, Li M et al (2022) Simulation of forest fire spread based on artificial intelligence. Ecol Ind 136:108653CrossRef
29.
Zurück zum Zitat Hodges JL, Lattimer BY (2019) Wildland fire spread modeling using convolutional neural networks. Fire Technol 55:2115–2142CrossRef Hodges JL, Lattimer BY (2019) Wildland fire spread modeling using convolutional neural networks. Fire Technol 55:2115–2142CrossRef
30.
Zurück zum Zitat Woo S, Park J, Lee JY et al (2018) Cbam: convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pp 3–19 Woo S, Park J, Lee JY et al (2018) Cbam: convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pp 3–19
31.
Zurück zum Zitat Fu H, Song G, Wang Y (2021) Improved YOLOv4 marine target detection combined with CBAM. Symmetry 13(4):623CrossRef Fu H, Song G, Wang Y (2021) Improved YOLOv4 marine target detection combined with CBAM. Symmetry 13(4):623CrossRef
32.
Zurück zum Zitat Fu J, Liu J, Tian H et al (2019). Dual attention network for scene segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3146–3154 Fu J, Liu J, Tian H et al (2019). Dual attention network for scene segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3146–3154
33.
Zurück zum Zitat Liang Y, Li H, Guo B et al (2021) Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification. Inf Sci 548:295–312CrossRef Liang Y, Li H, Guo B et al (2021) Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification. Inf Sci 548:295–312CrossRef
34.
Zurück zum Zitat Li Z, Huang Y, Li X et al (2021) Wildland fire burned areas prediction using long short-term memory neural network with attention mechanism. Fire Technol 57:1–23CrossRef Li Z, Huang Y, Li X et al (2021) Wildland fire burned areas prediction using long short-term memory neural network with attention mechanism. Fire Technol 57:1–23CrossRef
35.
Zurück zum Zitat Ghali R, Akhloufi MA, Jmal M et al (2021) Wildfire segmentation using deep vision transformers. Remote Sensing 13(17):3527CrossRef Ghali R, Akhloufi MA, Jmal M et al (2021) Wildfire segmentation using deep vision transformers. Remote Sensing 13(17):3527CrossRef
36.
Zurück zum Zitat Guo MH, Xu TX, Liu JJ et al (2022) Attention mechanisms in computer vision: a survey. Comput Visual Media 8(3):331–368CrossRef Guo MH, Xu TX, Liu JJ et al (2022) Attention mechanisms in computer vision: a survey. Comput Visual Media 8(3):331–368CrossRef
37.
Zurück zum Zitat Anderson HE (1981) Aids to determining fuel models for estimating fire behavior, vol 122. US Department of Agriculture Forest Service, Intermountain Forest and Range Experiment Station Anderson HE (1981) Aids to determining fuel models for estimating fire behavior, vol 122. US Department of Agriculture Forest Service, Intermountain Forest and Range Experiment Station
38.
Zurück zum Zitat Kucuk O, Bilgili E, Fernandes PM (2015) Fuel modelling and potential fire behavior in Turkey. Šumarski List 139(11–12):553–560 Kucuk O, Bilgili E, Fernandes PM (2015) Fuel modelling and potential fire behavior in Turkey. Šumarski List 139(11–12):553–560
39.
Zurück zum Zitat Prasad R, Deo RC, Li Y et al (2019) Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach. CATENA 177:149–166CrossRef Prasad R, Deo RC, Li Y et al (2019) Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach. CATENA 177:149–166CrossRef
40.
Zurück zum Zitat Nelson JR (2000) Prediction of diurnal change in 10-h fuel stick moisture content. Can J For Res 30(7):1071–1087CrossRef Nelson JR (2000) Prediction of diurnal change in 10-h fuel stick moisture content. Can J For Res 30(7):1071–1087CrossRef
41.
Zurück zum Zitat Zhou MJ, Vacik H (2017) Comparisons of fuel stick moisture among forest cover types in eastern Austria. Aust J Forest Sci 134(4):301–321 Zhou MJ, Vacik H (2017) Comparisons of fuel stick moisture among forest cover types in eastern Austria. Aust J Forest Sci 134(4):301–321
42.
Zurück zum Zitat Boer MM, Nolan RH, De RescoDios V, Clarke H, Price OF, Bradstock RA (2017) Changing weather extremes call for early warning of potential for catastrophic fire. Earth’s Fut 5(12):1196–1202CrossRef Boer MM, Nolan RH, De RescoDios V, Clarke H, Price OF, Bradstock RA (2017) Changing weather extremes call for early warning of potential for catastrophic fire. Earth’s Fut 5(12):1196–1202CrossRef
43.
Zurück zum Zitat Mota PHS et al (2019) Forest fire hazard zoning in Mato Grosso state. Braz Land Use Policy 88:104206CrossRef Mota PHS et al (2019) Forest fire hazard zoning in Mato Grosso state. Braz Land Use Policy 88:104206CrossRef
44.
Zurück zum Zitat Silvani X, Morandini F, Dupuy JL (2012) Effects of slope on fire spread observed through video images and multiple-point thermal measurements. Exp Thermal Fluid Sci 41:99–111CrossRef Silvani X, Morandini F, Dupuy JL (2012) Effects of slope on fire spread observed through video images and multiple-point thermal measurements. Exp Thermal Fluid Sci 41:99–111CrossRef
45.
Zurück zum Zitat Seager R, Hooks A, Williams AP et al (2015) Climatology, variability, and trends in the US vapor pressure deficit, an important fire-related meteorological quantity. J Appl Meteorol Climatol 54(6):1121–1141CrossRef Seager R, Hooks A, Williams AP et al (2015) Climatology, variability, and trends in the US vapor pressure deficit, an important fire-related meteorological quantity. J Appl Meteorol Climatol 54(6):1121–1141CrossRef
46.
Zurück zum Zitat Jolly WM (2007) Sensitivity of a surface fire spread model and associated fire behaviour fuel models to changes in live fuel moisture. Int J Wildland Fire 16(4):503–509MathSciNetCrossRef Jolly WM (2007) Sensitivity of a surface fire spread model and associated fire behaviour fuel models to changes in live fuel moisture. Int J Wildland Fire 16(4):503–509MathSciNetCrossRef
47.
Zurück zum Zitat Clarke PJ, Knox KJE, Bradstock RA et al (2014) Vegetation, terrain and fire history shape the impact of extreme weather on fire severity and ecosystem response. J Veg Sci 25(4):1033–1044CrossRef Clarke PJ, Knox KJE, Bradstock RA et al (2014) Vegetation, terrain and fire history shape the impact of extreme weather on fire severity and ecosystem response. J Veg Sci 25(4):1033–1044CrossRef
48.
Zurück zum Zitat Abdelouahab K, Pelcat M, Berry F (2017) Why TanH is a hardware friendly activation function for CNNs. In Proceedings of the 11th international conference on distributed smart cameras, pp 199–201 Abdelouahab K, Pelcat M, Berry F (2017) Why TanH is a hardware friendly activation function for CNNs. In Proceedings of the 11th international conference on distributed smart cameras, pp 199–201
50.
Zurück zum Zitat Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958MathSciNetMATH Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958MathSciNetMATH
51.
Zurück zum Zitat Meyer GP (2021) An alternative probabilistic interpretation of the Huber loss. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5261–5269 Meyer GP (2021) An alternative probabilistic interpretation of the Huber loss. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5261–5269
53.
Zurück zum Zitat Burge J, Bonanni M, Ihme M et al (2020) Convolutional LSTM neural networks for modeling wildland fire dynamics. arXiv preprint arXiv:2012.06679 Burge J, Bonanni M, Ihme M et al (2020) Convolutional LSTM neural networks for modeling wildland fire dynamics. arXiv preprint arXiv:​2012.​06679
54.
Zurück zum Zitat Cheng B, Girshick R, Dollár P et al (2021) Boundary IOU: Improving object-centric image segmentation evaluation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15334–15342 Cheng B, Girshick R, Dollár P et al (2021) Boundary IOU: Improving object-centric image segmentation evaluation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15334–15342
55.
Zurück zum Zitat Srivas T, Artés T et al (2016) Wildfire spread prediction and assimilation for FARSITE using ensemble Kalman filtering. Procedia Comput Sci 80:897–908CrossRef Srivas T, Artés T et al (2016) Wildfire spread prediction and assimilation for FARSITE using ensemble Kalman filtering. Procedia Comput Sci 80:897–908CrossRef
Metadaten
Titel
Predicting the Wildland Fire Spread Using a Mixed-Input CNN Model with Both Channel and Spatial Attention Mechanisms
verfasst von
Xingdong Li
Xinyu Wang
Shufa Sun
Yangwei Wang
Sanping Li
Dandan Li
Publikationsdatum
20.06.2023
Verlag
Springer US
Erschienen in
Fire Technology / Ausgabe 5/2023
Print ISSN: 0015-2684
Elektronische ISSN: 1572-8099
DOI
https://doi.org/10.1007/s10694-023-01427-2

Weitere Artikel der Ausgabe 5/2023

Fire Technology 5/2023 Zur Ausgabe