Evolution law of ignition driving factors for seasonal wildfires on the Mongolian Plateau and their future prediction

Abstract

Under the dual pressures of climate change and human activities, the frequency and intensity of global wildfires have significantly increased. While seasonal differences profoundly affect the intensity and spatial patterns of wildfire driving factors, past research has largely focused on annual scales, with insufficient attention paid to the dynamic changes and deeper impacts of driving factors in the seasonal dimension. Taking seasonal variations as the core entry point, this study integrated cross-border resources in the Sino-Mongolian border area, adopted satellite fire point data from 2001 to 2022, fused multi-source data including meteorological, topographic, vegetation, socioeconomic and anthropogenic activity data, incorporated meteorological data under three future climate scenarios, and compared the applicability of six models (Logistic Regression (LR), Gompit Regression (GR), Random Forest (RF), Boosted Regression Trees (BRT), XGBoost, and Support Vector Machine (SVM)) in wildfire prediction on the Mongolian Plateau. The results indicate that the Boosted Regression Trees model is the optimal model. Daily average relative humidity (Hum) and yearly average wind speed (Y_win) are the primary driving factors. The eastern provinces of Mongolia, Khovd Province, Selenge Province, and Hulunbuir City in China are identified as extremely high-risk areas for wildfires, with an increasing trend in wildfire incidents on the Mongolian Plateau in the future. This study improves the analysis of fire risk level zoning to accurately identify the spatial characteristics of high-risk areas and clarifies critical thresholds through the marginal benefit analysis of driving factors. Based on this, differentiated early warning systems can be initiated in conjunction with the specific conditions of high-risk areas, supported by targeted prevention and control measures, enhancing the foresight and effectiveness of wildfire risk management in cross-border regions.

Keywords

Mongolian Plateau / Seasonal classification / Driving factors / Model comparison / Fire risk zoning / Future projection

References

[1] Angerer J, Han GD, Fujisaki I, Havstad K. Climate change and ecosystems of Asia with emphasis on Inner Mongolia and Mongolia. Rangelands, 2008, 30(3): 46-51

[2] Bai Y, Li SG, Liu MH, Guo Q. Assessment of vegetation change on the Mongolian Plateau over three decades using different remote sensing products. J Environ Manag, 2022, 317: 115509

[3] Bao G, Bao YH, Qin ZH, Zhou Y, Shiirev A. Vegetation cover changes in Mongolian Plateau and its response to seasonal climate changes in recent 10 years. Sci Geogr Sin, 2013, 33(5): 613-621

[4] Bao YL, Shinoda M, Yi KP, Fu XM, Sun L, Nasanbat E, Li N, Xiang HL, Yang Y, DavdaiJavzmaa B, Nandintsetseg B. Satellite-based analysis of spatiotemporal wildfire pattern in the Mongolian Plateau. Remote Sens, 2023, 15(1): 190

[5] Bao G, Bao YL, Bao YH, Amarjargal, Hang YL (2014) Trends in spatiotemporal patterns of fire behavior on the Mongolian Plateau from 2001 to 2012. In: Information technology in risk analysis and crisis response–proceedings of the 6th annual meeting of the risk analysis professional committee of the China disaster prevention association. Hohhot, Inner Mongolia, pp 537–541

[6] Bergonse R, Oliveira S, Gonçalves A, Nunes S, da Câmara C, Zêzere JL. A combined structural and seasonal approach to assess wildfire susceptibility and hazard in summertime. Nat Hazards, 2021, 10632545-2573

[7] Cai QJ, Zeng AC, Su ZW, Guo FT. Analysis of driving factors for forest fire occurrence in Zhejiang Province based on the logistic regression model. J Northwest a&f Univ (Nat Sci Ed), 2020, 48: 102-109

[8] Chang Y, Zhu ZL, Bu RC, Chen HW, Feng YT, Li YH, Hu YM, Wang ZC. Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China. Landsc Ecol, 2013, 28(10): 1989-2004

[9] Chen PY, Zhao FJ, Shu LF, Wang MY. Fires and fire management on forest steppe in Mongolia. World for Res, 2014, 27(2): 66-69

[10] Ding Q, Feng XF. Analysis of forest fire changes using MODIS 14 data in the boreal forests of Eurasia: a case study of the European part of Russia. J Geo-Inf Sci, 2013, 15: 476-482

[11] Du JM, Bao G, Tong SQ, Wendurina M, Bao YH. Changes in vegetation cover in Mongolia from 1982 to 2015 and its relationship with climate change and human activities. Acta Pratacult Sin, 2021, 30: 1-13

[12] Ellis TM, Bowman DMJS, Jain P, Flannigan MD, Williamson GJ. Global increase in wildfire risk due to climate-driven declines in fuel moisture. Glob Chang Biol, 2022, 28(4): 1544-1559

[13] Ferreira LN, Vega-Oliveros DA, Zhao L, Cardoso MF, Macau EEN. Global fire season severity analysis and forecasting. Comput Geosci, 2020, 134: 104339

[14] Guo ZX, Fang WH, Tan J, Shi XW. A time-dependent stochastic grassland fire ignition probability model for Hulun Buir Grassland of China. Chin Geogr Sci, 2013, 23(4): 445-459

[15] Guo FT, Su ZW, Ma XQ, Song YH, Sun L, Hu HQ, Yang TT. Climatic and non-climatic factors driving lightning-induced fire in Tahe, Daxing’an mountain. Acta Ecol Sin, 2015, 35(19): 6439-6448

[16] Guo FT, Su ZW, Tigabu M, Yang XJ, Lin FF, Liang HL, Wang GY. Spatial modelling of fire drivers in urban-forest ecosystems in China. Forests, 2017, 8(6): 180

[17] Guo FT, Su ZW, Wang GY, Sun L, Tigabu M, Yang XJ, Hu HQ. Understanding fire drivers and relative impacts in different Chinese forest ecosystems. Sci Total Environ, 2017, 605: 411-425

[18] Hardtke LA, Blanco PD, del Valle HF, Metternicht GI, Sione WF. Semi-automated mapping of burned areas in semi-arid ecosystems using MODIS time-series imagery. Int J Appl Earth Obs Geoinf, 2015, 38: 25-35

[19] Hessl AE, Brown P, Byambasuren O, Cockrell S, Leland C, Cook E, Nachin B, Pederson N, Saladyga T, Suran B. Fire and climate in Mongolia (1532–2010 common era). Geophys Res Lett, 2016, 43(12): 6519-6527

[20] Huang X, Ding K, Liu JY, Wang ZL, Tang R, Xue L, Wang HK, Zhang Q, Tan ZM, Fu CB, Davis SJ, Andreae MO, Ding AJ. Smoke-weather interaction affects extreme wildfires in diverse coastal regions. Science, 2023, 379(6631): 457-461

[21] Ji CC, Yang HC, Li XS, Pei XJ, Li M, Yuan H, Cao YM, Chen BY, Qu SQ, Zhang N, Chun L, Shi LY, Sun FY. Forest wildfire risk assessment of Anning river valley in Sichuan Province based on driving factors with multi-source data. Forests, 2024, 15(9): 1523

[22] Jiao LL, Chang Y, Shen D, Hu YM, Li CL, Ma J. Using boosted regression trees to analyze the factors affecting the spatial distribution pattern of wildfire in China. Chin J Ecol, 2015, 3482288-2296

[23] Jolly WM, Cochrane MA, Freeborn PH, Holden ZA, Brown TJ, Williamson GJ, Bowman DMJS. Climate-induced variations in global wildfire danger from 1979 to 2013. Nat Commun, 2015, 6: 7537

[24] Kalantar B, Ueda N, Idrees MO, Janizadeh S, Ahmadi K, Shabani F. Forest fire susceptibility prediction based on machine learning models with resampling algorithms on remote sensing data. Remote Sens, 2020, 12(22): 3682

[25] Kennedy MC, Johnson MC. Fuel treatment prescriptions alter spatial patterns of fire severity around the wildland–urban interface during the Wallow Fire, Arizona, USA. For Ecol Manag, 2014, 318: 122-132

[26] Le Page Y, Oom D, Silva JMN, Jönsson P, Pereira JMC. Seasonality of vegetation fires as modified by human action: observing the deviation from eco-climatic fire regimes. Glob Ecol Biogeogr, 2010, 19(4): 575-588

[27] Leon JRR, Van Leeuwen WJD, Casady GM. Using MODIS-NDVI for the modeling of post-wildfire vegetation response as a function of environmental conditions and pre-fire restoration treatments. Remote Sens, 2012, 4(3): 598-621

[28] Li YH, Xu SX, Fan ZF, Zhang X, Yang XH, Wen S, Shi ZJ. Risk factors and prediction of the probability of wildfire occurrence in the China–Mongolia–Russia cross-border area. Remote Sens, 2023, 15(1): 42

[29] Lin W, Sun XB, Ren GY, Zhang JB. A review of seasonal division and change research. Prog Geogr, 2024, 434826-840

[30] Liu YQ, Stanturf J, Goodrick S. Trends in global wildfire potential in a changing climate. For Ecol Manag, 2010, 259(4): 685-697

[31] Liu J, Guo HY, Gan WW, Xu YX, Sun R. Spatiotemporal distribution pattern of forest fires and spatial heterogeneity of climate influencing factors in Panxi. J Southwest for Univ (Nat Sci Ed), 2023, 43: 106-117

[32] Lovreglio R, Leone V, Giaquinto P, Notarnicola A. Wildfire cause analysis: four case-studies in southern Italy. Iforest, 2010, 3(1): 8-15

[33] Lv ZT, Li SY, Fan JL, liu GJ, Wang HF, Meng XY. Natural restoration potential of vegetation in Mongolia. J des Res, 2021, 41: 192-201

[34] Lv QC, Chen ZY, Wu CY, Peñuelas J, Fan L, Su YX, Yang ZY, Li MC, Gao BB, Hu JQ, Zhang CQ, Fu YH, Wang Q. Increasing severity of large-scale fires prolongs recovery time of forests globally since 2001. Nat Ecol Evol, 2025, 9(6): 980-992

[35] Meihuan Y, Yawen L, Tao W, Juanle W, Pengfei L, Ting L, Jing H, Altansukh O, Davaasuren D. Characteristics of spatial and temporal vegetation index variability and its responses to temperature and precipitation in Mongolia. J Resour Ecol, 2024, 15(5): 1175

[36] Meng CC, Xu YL, Li QY, Ma YM, Feng Q, Ma WQ, Pan J, Li K. Analyses of observed features and future trend of extreme temperature events in inner Mongolia of China. Theor Appl Climatol, 2020, 1391577-597

[37] Miao LJ, Jiang C, He B, Liu Q, Zhu F, Cui XF. Response of vegetation coverage to climate change in Mongolian Plateau during recent 10 years. Acta Ecol Sin, 2014, 34(5): 1295-1301

[38] Minnich RA, Bahre CJ. Wildland fire and chaparral succession along the California Baja-California boundary. Int J Wildland Fire, 1995, 5(1): 13-24

[39] Moghim S, Mehrabi M. Wildfire assessment using machine learning algorithms in different regions. Fire Ecol, 2024, 20(1): 104

[40] Na L, Zhang JQ, Bao YL, Bao YB, Na RS, Tong SQ, Si AL. Himawari-8 satellite based dynamic monitoring of grassland fire in China-Mongolia border regions. Sensors, 2018, 181276

[41] O’Donnell AJ, Boer MM, McCaw WL, Grierson PF. Climatic anomalies drive wildfire occurrence and extent in semi-arid shrublands and woodlands of southwest Australia. Ecosphere, 2011, 211art127

[42] Oliveira S, Rocha J, Sá A. Wildfire risk modeling. Curr Opin Environ Sci Health, 2021, 23: 100274

[43] Padilla M, Vega-García C. On the comparative importance of fire danger rating indices and their integration with spatial and temporal variables for predicting daily human-caused fire occurrences in Spain. Int J Wildland Fire, 2011, 20146-58

[44] Qu ZP, Zheng SX, Bai YF. Spatiotemporal patterns and driving factors of grassland fire on Mongolian Plateau. Chin J Appl Ecol, 2010, 21(4): 807-813

[45] Rihan W, Zhao J, Zhang H, Guo X, Ying H, Deng G, Li H. Wildfires on the Mongolian Plateau: identifying drivers and spatial distributions to predict wildfire probability. Remote Sens, 2019, 11(20): 2361

[46] Rodrigues M, de la Riva J. An insight into machine-learning algorithms to model human-caused wildfire occurrence. Environ Model Softw, 2014, 57: 192-201

[47] Sayad YO, Mousannif H, Al Moatassime H. Predictive modeling of wildfires: a new dataset and machine learning approach. Fire Saf J, 2019, 104: 130-146

[48] Shu LF, Tian XR, Li H. Overview of the Global Forest Fire Situation. World for Res, 1998

[49] Strydom S, Savage MJ. A spatio-temporal analysis of fires in the Southern African Development Community region. Nat Hazards, 2018, 92(3): 1617-1632

[50] Su ZW, Zeng AC, Cai QJ, Hu HQ. Study on prediction model and driving factors of forest fire in Da Hinggan Mountains using Gompit regression method. J for Eng, 2019, 4(4): 135-142

[51] Sulova A, Jokar Arsanjani J. Exploratory analysis of driving force of wildfires in Australia: an application of machine learning within google earth engine. Remote Sens, 2021, 13(1): 10

[52] Sun QQ, Meyer WS, Koerber GR, Marschner P. Rapid recovery of net ecosystem production in a semi-arid woodland after a wildfire. Agric for Meteorol, 2020, 291: 108099

[53] Sun HC, Wang WJ, Liu ZH, Zou XH, Zhang ZX, Ying H, Dong YL, Yang R. The relative importance of driving factors of wildfire occurrence across climatic gradients in the Inner Mongolia, China. Ecol Indic, 2021, 131: 108249

[54] Tan N, A L, Bao YL, Gao YZ, Ao R. Spatiotemporal evolution characteristics of high-frequency grassland fire area in Mongolian Plateau based on a space-time cube. Pratacultural Sci, 2023, 40112763-2774

[55] Turco M, Llasat MC, von Hardenberg J, Provenzale A. Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula). Clim Change, 2013, 116(3): 665-678

[56] Turner D, Lewis M, Ostendorf B. Spatial indicators of fire risk in the arid and semi-arid zone of Australia. Ecol Indic, 2011, 11(1): 149-167

[57] Tymstra C, Flannigan MD, Armitage OB, Logan K. Impact of climate change on area burned in Alberta’s boreal forest. Int J Wildland Fire, 2007, 16(2): 153-160

[58] Unkelbach J, Behling H. The reconstruction of Holocene northwestern Mongolian fire history based on high-resolution multi-site macro-charcoal analyses. Front Earth Sci, 2022, 10: 959914

[59] Vilar del Hoyo L, Martín Isabel MP, Martínez Vega FJ. Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data. Eur J for Res, 2011, 130(6): 983-996

[60] Wang WQ, Zhao FJ, Wang YX, Huang XY, Ye JX. Seasonal differences in the spatial patterns of wildfire drivers and susceptibility in the southwest mountains of China. Sci Total Environ, 2023, 869: 161782

[61] Xu SX, Wu QQ, Qiao DX, Mu YL, Zhang X. Spatiotemporal patterns and influencing factors of wildfires in eastern Mongolia. J des Res, 2021, 41: 83-91

[62] Yue WT, Ren C, Liang YJ, Lin XQ, Yin AC, Liang JY. Wildfire risk assessment considering seasonal differences: a case study of Nanning, China. Forests, 2023, 14(8): 1616

[63] Zeng AC, Cai QJ, Su ZW, Guo XB, Jin QF, Guo FT. Seasonal variation and driving factors of forest fires in Zhejiang Province based on MODIS satellite fire points. Chin J Appl Ecol, 2020, 31: 399-406

[64] Zhang HJ, Qi PC, Guo GM. Improvement of fire danger modelling with geographically weighted logistic model. Int J Wildland Fire, 2014, 23(8): 1130-1146

[65] Zhang CB, Zhang Y, Li JL. Grassland productivity response to climate change in the Hulunbuir steppes of China. Sustainability, 2019, 11(23): 6760

[66] Zhang GD, Bao G, Yuan ZH, Wendorina. Impacts of diurnal-asymmetric warming on the vegetation green-up period over the Mongolian Plateau during 2001–2020. Arid Land Geogr, 2023, 46: 700-710

[67] Zhang GL, Wang M, Yang BL, Liu K. Current and future patterns of global wildfire based on deep neural networks. Earths Future, 2024, 12(2): e2023EF004088

[68] Zhang GZ, Zhang LY, Li X, Feng XH, Wang YR, Guo JC, Li PZ, Wei XD. Spatiotemporal evolution characteristics and driving mechanisms of wildfires in China under the context of climate change and human activities. Ecol Indic, 2025, 176: 113694

[69] Zhou PF, Wang YX. Analysis of driving factors of forest fire occurrence and forest fire prediction in Guangxi using machine learning algorithms. J Northeast for Univ, 2024, 52: 72-82

[70] Zhou Q, Zhang H, Wu ZW. Effects of forest fire prevention policies on probability and drivers of forest fires in the boreal forests of China during different periods. Remote Sens, 2022, 14225724

RIGHTS & PERMISSIONS

Northeast Forestry University