Improving Wildfire Probability Modeling by Integrating Dynamic-Step Weather Variables over Northwestern Sichuan, China

Rui Chen; Binbin He; Xingwen Quan; Xiaoying Lai; Chunquan Fan

doi:10.1007/s13753-023-00476-z

Volume 14 Issue 2

Apr. 2023

Turn off MathJax

Article Contents

Article Navigation > International Journal of Disaster Risk Science > 2023 > 14(2): 313-325

Rui Chen, Binbin He, Xingwen Quan, Xiaoying Lai, Chunquan Fan. Improving Wildfire Probability Modeling by Integrating Dynamic-Step Weather Variables over Northwestern Sichuan, China[J]. International Journal of Disaster Risk Science, 2023, 14(2): 313-325. doi: 10.1007/s13753-023-00476-z

Citation:

Rui Chen, Binbin He, Xingwen Quan, Xiaoying Lai, Chunquan Fan. Improving Wildfire Probability Modeling by Integrating Dynamic-Step Weather Variables over Northwestern Sichuan, China[J]. International Journal of Disaster Risk Science, 2023, 14(2): 313-325. doi: 10.1007/s13753-023-00476-z

Citation:

Rui Chen, Binbin He, Xingwen Quan, Xiaoying Lai, Chunquan Fan. Improving Wildfire Probability Modeling by Integrating Dynamic-Step Weather Variables over Northwestern Sichuan, China[J]. International Journal of Disaster Risk Science, 2023, 14(2): 313-325. doi: 10.1007/s13753-023-00476-z

PDF

Improving Wildfire Probability Modeling by Integrating Dynamic-Step Weather Variables over Northwestern Sichuan, China

doi: 10.1007/s13753-023-00476-z

1. School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, 611731, China;
2. Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou, 313001, China

Funds:

(4) the National Catalogue Service for Geographic Information (NCSFGI, http://www.webmap.cn/main.do?method=index) providing the original dataset for this study

(3) the European Center for Medium-Range Weather Forecasts (ECMWF, http://apps.ecmwf.int) providing ERA5-land dataset

This work was supported by the National Natural Science Foundation of China (Contract no. U20A2090). The authors are grateful to the dataset providers:(1) the Land Processes Distributed Active Archive Center (LPDAAC) at the U.S. Geological Survey (USGS) Earth Resources Observation and Science Center (EROS) (http://lpdaac.usgs.gov) providing MODIS product

and (5) the Sichuan Forestry and Grassland Administration providing the forest resource survey data of Sichuan Province (2010-2020).

(2) the United States Geological Survey, USGS National Geospatial-Intelligence Agency, NGA providing the Global Multi-resolution Terrain Elevation Data 2010 and GMTED2010 digital elevation model (DEM)

Accepted Date: 2023-02-03

Available Online: 2023-04-28

Publish Date: 2023-03-20

Abstract

Abstract

Wildfire occurrence is attributed to the interaction of multiple factors including weather, fuel, topography, and human activities. Among them, weather variables, particularly the temporal characteristics of weather variables in a given period, are paramount in predicting the probability of wildfire occurrence. However, rainfall has a large influence on the temporal characteristics of weather variables if they are derived from a fixed period, introducing additional uncertainties in wildfire probability modeling. To solve the problem, this study employed the weather variables in continuous nonprecipitation days as the "dynamic-step" weather variables with which to improve wildfire probability modeling. Multisource data on weather, fuel, topography, infrastructure, and derived variables were used to model wildfire probability based on two machine learning methods-random forest (RF) and extreme gradient boosting (XGBoost). The results indicate that the accuracy of the wildfire probability models was improved by adding dynamic-step weather variables into the models. The variable importance analysis also verified the top contribution of these dynamic-step weather variables, indicating the effectiveness of the consideration of dynamic-step weather variables in wildfire probability modeling.
- Dynamic-step weather variables,
- Fuel variables,
- Machine learning,
- Sichuan,
- Wildfire probability prediction

FullText(HTML)

References(69)

References

[1]	Adab, H., K.D. Kanniah, and K. Solaimani. 2012. Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques. Natural Hazards 65(3):1723-1743.
[2]	Al-Fugara, A., A.N. Mabdeh, M. Ahmadlou, H.R. Pourghasemi, R. Al-Adamat, B. Pradhan, and A.R. Al-Shabeeb. 2021. Wildland fire susceptibility mapping using support vector regression and adaptive neuro-fuzzy inference system-based whale optimization algorithm and simulated annealing. ISPRS International Journal of Geo-Information 10(6):Article 382.
[3]	Arndt, N., H. Vacik, V. Koch, A. Arpaci, and H. Gossow. 2013. Modeling human-caused forest fire ignition for assessing forest fire danger in Austria. Iforest-Biogeosciences and Forestry 6(6):315-325.
[4]	Athmania, D., and H. Achour. 2014. External validation of the ASTER GDEM2, GMTED2010 and CGIAR-CSI-SRTM v.41 free access digital elevation models (DEMs) in Tunisia and Algeria. Remote Sensing 6(5):4600-4620.
[5]	Breiman, L. 2001. Random forests. Machine Learning 45(1):5-32.
[6]	Bui, D.T., N.-D. Hoang, and P. Samui. 2019. Spatial pattern analysis and prediction of forest fire using new machine learning approach of Multivariate Adaptive Regression Splines and Differential Flower Pollination optimization:A case study at Lao Cai province (Viet Nam). Journal of Environmental Management 237:476-487.
[7]	Cao, Y., M. Wang, and K. Liu. 2017. Wildfire susceptibility assessment in Southern China:A comparison of multiple methods. International Journal of Disaster Risk Science 8(2):164-181.
[8]	Carabajal, C.C., D.J. Harding, J.-P. Boy, J.J. Danielson, D.B. Gesch, and V.P. Suchdeo. 2011. Evaluation of the global multi-resolution terrain elevation data 2010 (GMTED2010) using ICESat geodetic control. In Proceedings of International Symposium on Lidar and Radar Mapping 2011:Technologies and Applications, 26-29 May 2011, Nanjing, China.
[9]	Carrasco, J., M. Acuna, A. Miranda, G. Alfaro, C. Pais, and A. Weintraub. 2021. Exploring the multidimensional effects of human activity and land cover on fire occurrence for territorial planning. Journal of Environmental Management 297:Article 113428.
[10]	Chen, T., and C. Guestrin. 2016. XGBoost:A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 13-17 August 2016, San Francisco, CA, USA.
[11]	Eskandari, S., M. Amiri, N. Sãdhasivam, and H.R. Pourghasemi. 2020. Comparison of new individual and hybrid machine learning algorithms for modeling and mapping fire hazard:A supplementary analysis of fire hazard in different counties of Golestan Province in Iran. Natural Hazards 104(1):305-327.
[12]	ESRI (Environmental Systems Research Institute). 2009. World imagery. https://www.arcgis.com/home/item.html?id=10df2279f9684e4a9f6a7f08febac2a9. Accessed 18 Mar 2021.
[13]	Fan, C., and B. He. 2021. A physics-guided deep learning model for 10-h dead fuel moisture content estimation. Forests 12(7):Article 933.
[14]	Gale, M.G., G.J. Cary, A.I.J.M. Van Dijk, and M. Yebra. 2021. Forest fire fuel through the lens of remote sensing:Review of approaches, challenges and future directions in the remote sensing of biotic determinants of fire behaviour. Remote Sensing of Environment 255:Article 112282.
[15]	Giglio, L., W. Schroeder, and C.O. Justice. 2016. The collection 6 MODIS active fire detection algorithm and fire products. Remote Sensing of Environment 178:31-41.
[16]	Goldarag, Y.J., A. Mohammadzadeh, and A.S. Ardakani. 2016. Fire risk assessment using neural network and logistic regression. Journal of the Indian Society of Remote Sensing 44(6):885-894.
[17]	Guo, F.T., S. Selvalakshmi, F.F. Lin, G.Y. Wang, W.H. Wang, Z.W. Su, and A.Q. Liu. 2016. Geospatial information on geographical and human factors improved anthropogenic fire occurrence modeling in the Chinese boreal forest. Canadian Journal of Forest Research 46(4):582-594.
[18]	Guo, F.T., Z.W. Su, M. Tigabu, X.J. Yang, F.F. Lin, H.L. Liang, and G.Y. Wang. 2017. Spatial modelling of fire drivers in urban-forest ecosystems in China. Forests 8(6):Article 180.
[19]	Hanley, J.A., and B.J. McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29-36.
[20]	Henderson-Sellers, B. 1984. A new formula for latent heat of vaporization of water as a function of temperature. Quarterly Journal of the Royal Meteorological Society 110(466):1186-1190.
[21]	Jaafari, A., D.M. Gholami, and E.K. Zenner. 2017. A Bayesian modeling of wildfire probability in the Zagros Mountains, Iran. Ecological Informatics 39:32-44.
[22]	Jaafari, A., D. Mafi-Gholami, B. Thai Pham, and D.T. Bui. 2019. Wildfire probability mapping:Bivariate vs. multivariate statistics. Remote Sensing 11(6):Article 618.
[23]	Jaafari, A., S.V.R. Termeh, and D.T. Bui. 2019. Genetic and firefly metaheuristic algorithms for an optimized neuro-fuzzy prediction modeling of wildfire probability. Journal of Environmental Management 243:358-369.
[24]	Jaafari, A., E.K. Zenner, M. Panahi, and H. Shahabi. 2019. Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability. Agricultural and Forest Meteorology 266:198-207.
[25]	Jain, P., S.C.P. Coogan, S.G. Subramanian, M. Crowley, S. Taylor, and M.D. Flannigan. 2020. A review of machine learning applications in wildfire science and management. Environmental Reviews 28(4):478-505.
[26]	Janiec, P., and S. Gadal. 2020. A comparison of two machine learning classification methods for remote sensing predictive modeling of the forest fire in the North-Eastern Siberia. Remote Sensing 12(24):Article 4157.
[27]	Jenks, G.F., and F.C. Caspall. 1971. Error on choroplethic maps:Definition, measurement, reduction. Annals of the Association of American Geographers 61(2):217-244.
[28]	Jiao, M., X. Quan, and J. Yao. 2022. Evaluation of four satellite-derived fire products in the fire-prone, cloudy, and mountainous area over subtropical China. IEEE Geoscience and Remote Sensing Letters 19:Article 6513405.
[29]	Jurdao, S., E. Chuvieco, and J.M. Arevalillo. 2012. Modelling fire ignition probability from satellite estimates of live fuel moisture content. Fire Ecology 8(1):77-97.
[30]	Kang, Y., E. Jang, J. Im, C. Kwon, and S. Kim. 2020. Developing a new hourly forest fire risk index based on catboost in South Korea. Applied Sciences 10(22):Article 8213.
[31]	Liu, X.-P., G.-Q. Zhang, J. Lu, and J.-Q. Zhang. 2019. Risk assessment using transfer learning for grassland fires. Agricultural and Forest Meteorology 269-270:102-111.
[32]	Luo, K.W., X.W. Quan, B.B. He, and M. Yebra. 2019. Effects of live fuel moisture content on wildfire occurrence in fire-prone regions over southwest China. Forests 10(10):Article 17.
[33]	Ma, J., X. Ding, J.C.P. Cheng, F. Jiang, Y. Tan, V.J.L. Gan, and Z. Wan. 2020. Identification of high impact factors of air quality on a national scale using big data and machine learning techniques. Journal of Cleaner Production 244:Article 118955.
[34]	Ma, W., Z. Feng, Z. Cheng, S. Chen, and F. Wang. 2020. Identifying forest fire driving factors and related impacts in China using random forest algorithm. Forests 11(5):Article 507.
[35]	Malik, A., M.R. Rao, N. Puppala, P. Koouri, V.A.K. Thota, Q. Liu, S. Chiao, and J. Gao. 2021. Data-driven wildfire risk prediction in northern California. Atmosphere 12(1):Article 109.
[36]	Mallinis, G., M. Petrila, I. Mitsopoulos, A. Lorent, S. Neagu, B. Apostol, V. Gancz, I. Popa, and J.G. Goldammer. 2019. Geospatial patterns and drivers of forest fire occurrence in Romania. Applied Spatial Analysis and Policy 12(4):773-795.
[37]	Miao, C., Q. Sun, A.G.L. Borthwick, and Q. Duan. 2016. Linkage between hourly precipitation events and atmospheric temperature changes over China during the warm season. Scientific Reports 6:Article 22543.
[38]	Milanovic, S., N. Markovic, D. Pamucar, L. Gigovic, P. Kostic, and S.D. Milanovic. 2021. Forest fire probability mapping in eastern Serbia:Logistic regression versus random forest method. Forests 12(1):Article 5.
[39]	Mitchell, R., and E. Frank. 2017. Accelerating the XGBoost algorithm using GPU computing. PeerJ Computer Science 3:Article e127.
[40]	National Forestry and Grassland Administration. 2011. Technical regulations for inventory for forest management planning and design (GB/T 26424-2010). https://std.samr.gov.cn/gb/search/gbDetailed?id=71F772D75FA1D3A7E05397BE0A0AB82A. Accessed 15 Mar 2021.
[41]	Nolan, R.H., C.J. Blackman, V.R. de Dios, B. Choat, B.E. Medlyn, X. Li, R.A. Bradstock, and M.M. Boer. 2020. Linking forest flammability and plant vulnerability to drought. Forests 11(7):Article 779.
[42]	Nolan, R.H., M.M. Boer, L. Collins, V.R. de Dios, H. Clarke, M. Jenkins, B. Kenny, and R.A. Bradstock. 2020. Causes and consequences of eastern Australia's 2019-20 season of mega-fires. Global Change Biology 26(3):1039-1041.
[43]	Nolan, R.H., V.R. de Dios, M.M. Boer, G. Caccamo, M.L. Goulden, and R.A. Bradstock. 2016. Predicting dead fine fuel moisture at regional scales using vapour pressure deficit from MODIS and gridded weather data. Remote Sensing of Environment 174:100-108.
[44]	Phelps, N., and D.G. Woolford. 2021. Comparing calibrated statistical and machine learning methods for wildland fire occurrence prediction:A case study of human-caused fires in Lac La Biche, Alberta, Canada. International Journal of Wildland Fire 30(11):850-870.
[45]	Piramuthu, S. 2008. Input data for decision trees. Expert Systems with Applications 34(2):1220-1226.
[46]	Pourtaghi, Z.S., H.R. Pourghasemi, and M. Rossi. 2015. Forest fire susceptibility mapping in the Minudasht forests, Golestan province, Iran. Environmental Earth Sciences 73(4):1515-1533.
[47]	Pyne, S.J., P.L. Andrews, and R.D. Laven. 1996. Introduction to wildland fire. New York:John Wiley and Sons.
[48]	Quan, X., B. He, and X. Li. 2015. A Bayesian network-based method to alleviate the ill-posed inverse problem:A case study on leaf area index and canopy water content retrieval. IEEE Transactions on Geoscience and Remote Sensing 53(12):6507-6517.
[49]	Quan, X., B. He, M. Yebra, C. Yin, Z. Liao, and X. Li. 2017. Retrieval of forest fuel moisture content using a coupled radiative transfer model. Environmental Modelling & Software 95:290-302.
[50]	Quan, X., Y. Li, B. He, G.J. Cary, and G. Lai. 2021. Application of Landsat ETM+ and OLI data for foliage fuel load monitoring using radiative transfer model and machine learning method. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14:5100-5110.
[51]	Quan, X., Q. Xie, B. He, K. Luo, and X. Liu. 2021. Integrating remotely sensed fuel variables into wildfire danger assessment for China. International Journal of Wildland Fire 30(10):807-821.
[52]	Quan, X., M. Yebra, D. Riaño, B. He, G. Lai, and X. Liu. 2021. Global fuel moisture content mapping from MODIS. International Journal of Applied Earth Observation and Geoinformation 101:Article 102354.
[53]	Resco de Dios, V., A.W. Fellows, R.H. Nolan, M.M. Boer, R.A. Bradstock, F. Domingo, and M.L. Goulden. 2015. A semi-mechanistic model for predicting the moisture content of fine litter. Agricultural and Forest Meteorology 203:64-73.
[54]	Semeraro, T., G. Mastroleo, R. Aretano, G. Facchinetti, G. Zurlini, and I. Petrosillo. 2016. GIS fuzzy expert system for the assessment of ecosystems vulnerability to fire in managing Mediterranean natural protected areas. Journal of Environmental Management 168:94-103.
[55]	Shabbir, A.H., J. Zhang, J.D. Johnston, S.A. Sarkodie, J.A. Lutz, and X. Liu. 2021. Correction:Predicting the influence of climate on grassland area burned in Xilingol, China with dynamic simulations of autoregressive distributed lag models. PLoS ONE 16(1):Article e0245828.
[56]	Sichuan Forestry and Grassland Administration. 2017. Forest management inventory data of Sichuan Province (2010-2020). https://sczpt.sclcpt.cn/web/square/detail/72/35018/102?aa=0.600835027683043. Accessed 1 Mar 2021.
[57]	Stefanidou, A., I.Z. Gitas, D. Stavrakoudis, and G. Eftychidis. 2019. Midterm fire danger prediction using satellite imagery and auxiliary thematic layers. Remote Sensing 11(23):Article 2786.
[58]	Su, Z., H. Hu, G. Wang, Y. Ma, X. Yang, and F. Guo. 2018. Using GIS and Random Forests to identify fire drivers in a forest city, Yichun, China. Geomatics, Natural Hazards and Risk 9(1):1207-1229.
[59]	Syphard, A.D., V.C. Radeloff, N.S. Keuler, R.S. Taylor, T.J. Hawbaker, S.I. Stewart, and M.K. Clayton. 2008. Predicting spatial patterns of fire on a southern California landscape. International Journal of Wildland Fire 17(5):602-613.
[60]	Trang, P.T., M.E. Andrew, T. Chu, and N.J. Enright. 2022. Forest fire and its key drivers in the tropical forests of northern Vietnam. International Journal of Wildland Fire 31(3):213-229.
[61]	USGS (United States Geological Survey). 2010. Global multi-resolution terrain elevation data 2010 (GMTED2010). https://www.usgs.gov/coastal-changes-and-impacts/gmted2010. Accessed 10 Jan 2021.
[62]	Verdu, F., J. Salas, and C. Vega-Garcia. 2012. A multivariate analysis of biophysical factors and forest fires in Spain, 1991-2005. International Journal of Wildland Fire 21(5):498-509.
[63]	Wang, S.S.-C., and Y. Wang. 2020. Quantifying the effects of environmental factors on wildfire burned area in the south central US using integrated machine learning techniques. Atmospheric Chemistry and Physics 20(18):11065-11087.
[64]	Yebra, M., E. Chuvieco, and D. Riano. 2008. Estimation of live fuel moisture content from MODIS images for fire risk assessment. Agricultural and Forest Meteorology 148(4):523-536.
[65]	Yebra, M., P.E. Dennison, E. Chuvieco, D. Riaño, P. Zylstra, E.R. Hunt, F.M. Danson, Y. Qi, and S. Jurdao. 2013. A global review of remote sensing of live fuel moisture content for fire danger assessment:Moving towards operational products. Remote Sensing of Environment 136:455-468.
[66]	Yebra, M., X. Quan, D. Riaño, P. Rozas Larraondo, A.I.J.M. van Dijk, and G.J. Cary. 2018. A fuel moisture content and flammability monitoring methodology for continental Australia based on optical remote sensing. Remote Sensing of Environment 212:260-272.
[67]	Zhang, G.L., M. Wang, and K. Liu. 2019. Forest fire susceptibility modeling using a convolutional neural network for Yunnan province of China. International Journal of Disaster Risk Science 10(3):386-403.
[68]	Zheng, Z., Y.H. Gao, Q.Y. Yang, B. Zou, Y.J. Xu, Y.Y. Chen, S.Q. Yang, Y.Q. Wang, and Z.W. Wang. 2020. Predicting forest fire risk based on mining rules with ant-miner algorithm in cloud-rich areas. Ecological Indicators 118:Article 106772.
[69]	Zong, X., X. Tian, and Y. Yin. 2020. Impacts of climate change on wildfires in central Asia. Forests 11(8):Article 802.