Enhancing Fire Susceptibility Mapping in Semnan Province: Integrating Machine Learning and Geospatial Analysis

Document Type : Original Research

Authors
A. A. Zolfaghari 1
M. Raeesi 2
Z. Sheikh 2
A. Soltani 2
S. Poodineh 2
M. Amiri 3
1 Associate professor, Faculty of Desert Studies, Semnan University, Semnan, Iran
2 Faculty of Desert Studies, Semnan University, Semnan, Iran
3 Associate professor, Faculty of Natural Resources, Semnan University, Semnan, Iran
10.22034/ECOPERSIA.13.1.13
Abstract
Aims: This study assesses the impacts of natural and human factors on fire occurrences, identifies key contributors to fire susceptibility maps, and employs machine learning algorithms (MLAs) to enhance the spatiotemporal patterns of fire susceptibility maps.

Materials & Methods: Data were collected from 110 fire locations and 110 non-fire points spanning from 2001 to 2022 at annual scale. Various auxiliary variables, including climate data, terrain features, Normalized Difference Vegetation Index (NDVI), and distance to roads, were analyzed to model fire susceptibility. The study employed multiple MLAs, including Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting Decision Trees (GBDT), to generate the fire susceptibility maps.

Findings: About 70% of fires occurred within 2 km of roads, indicating significant human influence. Grasslands had the highest fire rates, with over 25% of fires from 2001-2022 due to flammable fuels. The RF and mean models identified 0.4% and 1.31% of the area as very high susceptibility (38,800 km² and 12,600 km²), while the GBDT and SVM models identified 2.42% and 1.86% (234,700 km² and 180,000 km²). The very high susceptibility class, though small in percentage, covers large areas.

Conclusion: This research highlights the importance of integrating environmental and human factors for predicting fire events in arid regions and developing comprehensive fire susceptibility maps, critical for protecting vulnerable ecosystems. These outcomes provide valuable tools for fire management and mitigation strategies within vulnerable ecosystems. Moreover, developing targeted fire management strategies focused on high-risk areas, such as juniper and broadleaf forests must be a priority.
Keywords
Auxiliary variables
Climatic indicators
Juniper Forest
Distance to Road
Fire Susceptibility

Subjects

1. Marlon J., Bartlein P., Daniau A.L., Harrison S., Maezumi S., Power M. Global biomass burning: A synthesis and review of Holocene paleofire records and their controls. Quaternary Sci. Rev. 2013; 65:5–25. http://dx.doi.org/10.1016/j.quascirev.2012.11.029
2. You C., Yao T., Xu C. Environmental significance of levoglucosan records in a central Tibetan ice core. Sci. Bulletin. 2019; 64:122–127. https://doi.org/10.1016/j.scib.2018.12.016
3. Guo F., Su Z., Wang G., Sun L., Tigabu M., Yang X. Understanding fire drivers and relative impacts in different Chinese forest ecosystems. Sci. Total Environ. 2017; 605–606:411–425. https://doi.org/10.1016/j.scitotenv.2017.06.219
4. Sevinc V., Kucuk O., Goltas M.A. Bayesian network model for prediction and analysis of possible forest fire causes. For. Ecol. Manag. 2020; 457:117723. https://doi.org/10.1016/j.foreco.2019.117723
5. Su Z., Zheng L., Luo S., Tigabu M., Guo F. Modeling wildfire drivers in Chinese tropical forest ecosystems using global logistic regression and geographically weighted logistic regression. Nat. Hazards. 2021; 108(1):1317–1345. https://doi.org/10.1007/s11069-021-04733-6
6. Bowman D.M.J.S., Moreira-Muñoz A., Kolden C.A., Chávez R.O., Muñoz A.A., Salinas F. Human–environmental drivers and impacts of the globally extreme 2017 Chilean fires. Ambio. 2019; 48(4):350–362. https://doi.org/10.1007/s13280-018-1084-1
7. Forkel M., Dorigo W., Lasslop G., Teubner I., Chuvieco E., Thonicke K. Identifying required model structures to predict global fire activity from satellite and climate data. Geosci. Model Dev. Discuss. 2016; 1–35. https://doi.org/ 10.5194/gmd-2016-301
8. Eskandari S., Pourghasemi H.R., Tiefenbacher J.P. Relations of land cover, topography, and climate to fire occurrence in natural regions of Iran: Applying new data mining techniques for modeling and mapping fire danger. For. Ecol. Manag. 2020; 473:118338. https://doi.org/10.1016/j.foreco.2020.118338
9. Mallinis G., Mitsopoulos I., Chrysafi I. Evaluating and comparing Sentinel 2A and Landsat-8 Operational Land Imager (OLI) spectral indices for estimating fire severity in a Mediterranean pine ecosystem of Greece. GIScience & Remote Sensing. 2018; 55(1):1–18. http://dx.doi.org/10.1080/15481603.2017.1354803
10. Santos A.C. dos., Montenegro S. da. R., Ferreira M.C., Barradas A.C.S., Schmidt I.B. Managing fires in a changing world: Fuel and weather determine fire behavior and safety in the neotropical savannas. J. Environ. Manage. 2021; 289:112508. https://doi.org/10.1016/j.jenvman.2021.112508
11. Arabameri A., Pal. S., Costache R.D., Saha A., Rezaie F., Danesh A.l. Prediction of gully erosion susceptibility mapping using novel ensemble machine learning algorithms. Geomatics, Natural Hazards and Risk. 2021; 12:469–498. https://doi.org/10.1080/19475705.2021.1880977
12. Ahmed I.A., Talukdar S., Shahfahad Parvez A., Rihan Mohd., Baig M.R.I. Flood susceptibility modeling in the urban watershed of Guwahati using improved metaheuristic-based ensemble machine learning algorithms. Geocarto Int. 2022; 37(26):12238–12266. https://doi.org/10.1080/10106049.2022.2066200
13. Akıncı H.A., Akıncı H. Machine learning based forest fire susceptibility assessment of Manavgat district (Antalya), Turkey. Earth Sci. Inform. 2023; 16(1):397–414. https://doi.org/10.1007/s12145-023-00953-5
14. Alkan Akinci H., Akinci H., Zeybek M. Comparison of diverse machine learning algorithms for forest fire susceptibility mapping in Antalya, Türkiye. Adv. Space Res. 2024; 74(2):647–667. https://doi.org/10.1016/j.asr.2024.04.018
15. Novo A., Dutal H., Eskandari S. Fire susceptibility modeling and mapping in Mediterranean forests of Turkey: a comprehensive study based on fuel, climatic, topographic, and anthropogenic factors. Euro-Mediterr J. Environ. Integr. 2024; 9(2):655–679. https://doi.org/10.1007/s41207-024-00475-6
16. Tonini M., D’Andrea M., Biondi G., Degli Esposti S., Trucchia A., Fiorucci P. A Machine Learning-Based Approach for Wildfire Susceptibility Mapping. The Case Study of the Liguria Region in Italy. Geosciences. 2020; 10(3). https://doi.org/10.3390/geosciences10030105
17. Liu Z., Peng C., Timothy W., Candau J.N., Desrochers A., Kneeshaw D. Application of machine-learning methods in forest ecology: Recent progress and future challenges. Environ. Rev. 2018; 26(4): 339-350. https://doi.org/10.1139/er-2018-0034
18. Jahanbani M., Vahidnia M.H., Aghamohammadi H., Azizi Z. Flood susceptibility mapping through geoinformatics and ensemble learning methods, with an emphasis on the AdaBoost-Decision Tree algorithm, in Mazandaran, Iran. Earth Sci. Inform. 2024; 17(2):1433–1457. https://doi.org/10.1007/s12145-023-01213-2
19. Janizadeh S., Chandra Pal S., Saha A., Chowdhuri I., Ahmadi K., Mirzaei S. Mapping the spatial and temporal variability of flood hazard affected by climate and land-use changes in the future. J. Environ. Manage. 2021; 298:113551. https://doi.org/10.1016/j.jenvman.2021.113551
20. Mirzaei S., Vafakhah M., Pradhan B., Alavi S.J. Flood susceptibility assessment using extreme gradient boosting (EGB), Iran. Earth Sci. Inform. 2021; 14(1):51–67. https://doi.org/10.1007/s12145-020-00530-0
21. Yang D., Zhang T., Arabameri A., Santosh M., Saha U.D., Islam A. Flash-flood susceptibility mapping: a novel credal decision tree-based ensemble approache. Earth Sci. Inform. 2023; 16(4):3143–3161. https://doi.org/10.1007/s12145-023-01057-w
22. Pourghasemi H.R., Gayen A., Edalat M., Zarafshar M., Tiefenbacher J.P. Is multi-hazard mapping effective in assessing natural hazards and integrated watershed management? Geosci. Frontiers. 2020; 11(4):1203–1217. https://doi.org/10.1016/j.gsf.2019.10.008
23. Barreto J., Armenteras D. Open Data and Machine Learning to Model the Occurrence of Fire in the Ecoregion of “Llanos Colombo-Venezolanos.” Remote Sens. 2020; 12:3921. https://doi.org/10.3390/rs12233921
24. Tan C., Feng Z. Mapping Forest Fire Risk Zones Using Machine Learning Algorithms in Hunan Province, China. Sustainability. 2023; 15(7). https://doi.org/10.3390/su15076292
25. Chevitarese D.S., Szwarcman D., Silva R.G., Brazil E.V. Deep learning applied to seismic facies classification: A methodology for training. In: Saint Petersburg 2018. European Association of Geoscientists & Engineers; 2018:1–5. http://dx.doi.org/10.3997/2214-4609.201800237
26. Hu Z.X., Wang Y., Ge M.F., Liu J. Data-driven fault diagnosis method based on compressed sensing and improved multiscale network. IEEE Trans Ind Electron. 2019; 67(4):3216–3225. http://doi: 10.1109/TIE.2019.2912763
27. Qu S., Guan Z., Verschuur D., Chen Y. Automatic high-resolution microseismic event detection via supervised machine learning. Geophysical J. Int. 2020; 222:1881–1895. http://dx.doi.org/10.1093/gji/ggaa193
28. Smith R., Mukerji T., Lupo T. Correlating geologic and seismic data with unconventional resource production curves using machine learning. Geophysics. 2019; 84(2):O39–47. http://dx.doi.org/10.1190/geo2018-0202.1
29. Tse K.C., Chiu H.C., Tsang M.Y., Li Y., Lam E.Y. Unsupervised learning on scientific ocean drilling datasets from the South China Sea. Front. Earth Sci. 2019; 13:180–90. http://dx.doi.org/10.1007/s11707-018-0704-1
30. Zhang G., Wang Z., Chen Y. Deep learning for seismic lithology prediction. Geophysical J. Int. 2018; 215(2):1368–1387. http://dx.doi.org/10.1093/gji/ggy344.
31. Zhou K.B., Zhang Z.X., Liu J., Hu Z.X., Duan X.K., Xu Q. Anode effect prediction based on a singular value thresholding and extreme gradient boosting approach. Meas. Sci. Technol. 2019; 30(1):015104. http://dx.doi.org/10.1088/1361-6501/aaee5e
32. Barmpoutis P., Papaioannou P., Dimitropoulos K., Grammalidis N. A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing. Sensors. 2020; 20(22):6442. https://doi.org/10.3390/s20226442
33. Eskandari S., Chuvieco E. Fire danger assessment in Iran based on geospatial information. Int. J. Appl. Earth Observation and Geoinformation. 2015;1 (42):57–64. https://doi.org/10.1016/j.jag.2015.05.006
34. Sadeghi A., Ahmadi Nadoushan M., Ahmadi Sani N. Segment-level modeling of wildfire susceptibility in Iranian semi-arid oak forests: Unveiling the pivotal impact of human activities. Trees, Forests and People. 2024; 15:100496. https://doi.org/10.1016/j.tfp.2024.100496
35. Amiri M., Pourghasemi H.R. Chapter 25 - Predicting areas affected by forest fire based on a machine learning algorithm. In: Pourghasemi HR, editor. Computers in Earth and Environmental Sciences. Elsevier; 2022: 351–362. https://doi.org/10.1016/B978-0-323-89861-4.00004-X
36. Mayr M.J., Vanselow K.A., Samimi C. Fire regimes at the arid fringe: A 16-year remote sensing perspective (2000–2016) on the controls of fire activity in Namibia from spatial predictive models. Ecol. Indicators. 2018; 91:324–337. http://dx.doi.org/10.1016/j.ecolind.2018.04.022
37. Mandal P., Maiti A., Paul S., Bhattacharya S., Paul S. Mapping the multi-hazards risk index for coastal block of Sundarban, India using AHP and machine learning algorithms. Trop. Cyclone Res. Rev. 2022; 11(4):225–243. https://doi.org/10.1016/j.tcrr.2023.03.001
38. Raeesi M., Zolfaghari A., Rahimi M., Kaboli S.H. Estimation of Vegetation Changes Concerning Annual Rainfall and Temperature in Semnan Province. E.E.R. 2023; 13(4):56–82. http://magazine.hormozgan.ac.ir/article-1-809-en.html
39. Amini E., Zolfaghari A., Kaboli H., Rahimi M. Estimation of Rainfall Erosivity Map in Areas with Limited Number of Rainfall Station (Case study: Semnan Province). Iranian J. Soil and Water Res. 2022; 53(9):2027–2044. https://doi: 10.22059/ijswr.2022.343710.669279
40. Wu Z., Li M., Wang B., Quan Y., Liu J. Using artificial intelligence to estimate the probability of forest fires in Heilongjiang, northeast China. Remote Sens. 2021; 13(9):1813. https://doi.org/10.3390/rs13091813
41. Kopecký M., Macek M., Wild J. Topographic Wetness Index calculation guidelines based on measured soil moisture and plant species composition. Sci. Total Environ. 2021; 757:143785. https://doi.org/10.1016/j.scitotenv.2020.143785.
42. Qin Z., Zhu Y., Li W., Xu B. Mapping vegetation cover of grassland ecosystem for desertification monitoring in Hulun Buir of Inner Mongolia, China. Proc. SPIE. 2008; 7104. https://doi.org/10.1117/12.800190
43. Xu Ch., Li Y., Hu J., Yang X., Sheng S., Liu M. Evaluating the difference between the normalized difference vegetation index and net primary productivity as the indicators of vegetation vigor assessment at landscape scale. Environ. Monit. Assess. 2012; 184(3):1275–86. https://doi.org/10.1007/s10661-011-2039-1
44. Kursa M.B., Rudnicki W.R. Feature Selection with the Boruta Package. J. Statistical Software. 2010; 36(11):1–13. https://doi.org/10.18637/jss.v036.i11
45. Szul T., Tabor S., Pancerz K. Application of the BORUTA Algorithm to Input Data Selection for a Model Based on Rough Set Theory (RST) to Prediction Energy Consumption for Building Heating. Energies. 2021; 14(10):2779. https://doi.org/10.3390/en14102779
46. Pourghasemi H.R., Gayen A., Lasaponara R., Tiefenbacher J.P. Application of learning vector quantization and different machine learning techniques to assessing forest fire influence factors and spatial modelling. Environ. Res. 2020; 184:109321. https://doi.org/10.1016/j.envres.2020.109321
47. Breiman L. Random Forests. Mach Learn. 2001; 45(1):5–32. https://doi.org/10.1023/A:1010933404324
48. Jain P., Coogan S.C.P., Subramanian S.G., Crowley M., Taylor S., Flannigan M.D. A review of machine learning applications in wildfire science and management. Environ. Reviews. 2020; 28(4):478–505. https://doi.org/10.1139/er-2020-0019
49. Hawryło P., Bednarz B., Wężyk P., Szostak M. Estimating defoliation of Scots pine stands using machine learning methods and vegetation indices of Sentinel-2. Eur. J. Remote Sens. 2018 1; 51(1):194–204. https://doi.org/10.1080/22797254.2017.1417745
50. Mustafa A., Rienow A., Saadi I., Cools M., Teller J. Comparing support vector machines with logistic regression for calibrating cellular automata land use change models. Eur. J. Remote Sens. 2018; 51(1): 391–401. https://doi.org/10.1080/22797254.2018.1442179
51. Lu J., Lu D., Zhang X., Bi Y., Cheng K., Zheng M. Estimation of elimination half-lives of organic chemicals in humans using gradient boosting machine. BBA. Generat Subjects. 2016; 1860 (11, Part B): 2664–2671. https://doi.org/10.1016/j.bbagen.2016.05.019
52. Touzani S., Granderson J., Fernandes S. Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy and Build. 2018; 158: 1533–1543. https://doi.org/10.1016/j.enbuild.2017.11.039
53. Friedman J.H. Greedy function approximation: a gradient boosting machine. Ann. Statist. 2001; 1189–1232. https://doi.org/10.1214/aos/1013203451
54. Tian Z., Xiao J., Feng H., Wei Y. Credit Risk Assessment based on Gradient Boosting Decision Tree. 2019; Procedia Computer Science. 2020; 174: 150–160. https://doi.org/10.1016/j.procs.2020.06.070
55. Mosavi A., Golshan M., Janizadeh S., Choubin B., Melesse A., Dineva A. Ensemble models of GLM, FDA, MARS, and RF for flood and erosion susceptibility mapping: a priority assessment of sub-basins. Geocarto Int. 2020; 37(9):2541-2560. https://doi.org/10.1080/10106049.2020.1829101
56. Tien Bui D., Hoang N.D., Pham T.D., Ngo P.T.T., Hoa P.V., Minh N.Q. A new intelligence approach based on GIS-based Multivariate Adaptive Regression Splines and metaheuristic optimization for predicting flash flood susceptible areas at high-frequency tropical typhoon area. J. Hydrol. 2019; 575:314–326. https://doi.org/10.1016/j.jhydrol.2019.05.046
57. Chang Y., Zhu Z., Bu R., Chen H., Feng Y., Li Y. Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China. Landscape Ecol. 2013; 28(10):1989–2004. https://doi.org/10.1007/s10980-013-9935-4
58. Guo F., Zhang L., Jin S., Tigabu M., Su Z., Wang W. Modeling Anthropogenic Fire Occurrence in the Boreal Forest of China Using Logistic Regression and Random Forests. Forests. 2016; 7(11):250. https://doi.org/10.3390/f7110250
59. McLauchlan K.K., Higuera P.E., Miesel J., Rogers B.M., Schweitzer J., Shuman J.K. Fire as a fundamental ecological process: Research advances and frontiers. J. Ecol. 2020; 108(5):2047–69. https://doi.org/10.1111/1365-2745.13403
60. Van Etten E., Burrows N. On the Ecology of Australia’s Arid Zone: ‘Fire Regimes and Ecology of Arid Australia.’ In: On the Ecology of Australia’s Arid Zone. Springer, Cham. 2018; 243–282. https://doi.org/10.1007/978-3-319-93943-8_10
61. Li W., Xu Q., Yi J., Liu J. Predictive model of spatial scale of forest fire driving factors: a case study of Yunnan Province, China. Sci. Rep. 2022; 12(1):19029. https://doi.org/10.1038/s41598-022-23697-6
62. Eskandari S., Oladi J., Jalilvand H., Saradjian M.R. Prediction of Future Forest Fires using the MCDM Method. Pol. J. Environ. Stud. 2015; 30 (24):2309–14. https://www.pjoes.com/Prediction-of-Future-Forest-Fires-Using-r-nthe-MCDM-Method,89485,0,2.html
63. Pourghasemi H.R. GIS-based forest fire susceptibility mapping in Iran: a comparison between evidential belief function and binary logistic regression models. Scandinavian J. For. Res. 2016; 31(1):80–98. https://doi.org/10.1080/02827581.2015.1052750
64. Pourtaghi Z.S., Pourghasemi H.R., Aretano R., Semeraro T. Investigation of general indicators influencing on forest fire and its susceptibility modeling using different data mining techniques. Ecol. Indic. 2016; 64:72–84. https://doi.org/10.1016/j.ecolind.2015.12.030
65. Romero-Calcerrada R., Novillo C.J., Millington J.D.A., Gomez-Jimenez I. GIS analysis of spatial patterns of human-caused wildfire ignition risk in the SW of Madrid (Central Spain). Landscape Ecol. 2008; 23(3):341–54. https://doi.org/10.1007/s10980-008-9190-2
66. Faraji F., Alijanpour A., Sheidai Karkaj E., Motamedi J. The Consequences of Banqueting and Fire on Plant Functional Groups (Case Study: Atbatan Rangelands, Bostanabad County). ECOPERSIA. 2020; 8(4):191–8. http://ecopersia.modares.ac.ir/article-24-38912-en.html
67. Akhzari D., Mohammadi E., Saedi K. Studying the effect of fire on some vegetation and soil properties in a semi-arid shrubland (Case study: Kachaleh Rangelands, Kamyaran Region). ECOPERSIA. 2022; 10(1):27–35. http://ecopersia.modares.ac.ir/article-24-53263-en.html
68. Barreto J.S., Armenteras D. Open Data and Machine Learning to Model the Occurrence of Fire in the Ecoregion of “Llanos Colombo–Venezolanos.” Remote Sens. 2020; 12(23): 3921. https://doi.org/10.3390/rs12233921
69. Iban M.C., Sekertekin A. Machine learning based wildfire susceptibility mapping using remotely sensed fire data and GIS: A case study of Adana and Mersin provinces, Turkey. Ecol Inform. 2022; 69:101647. http://dx.doi.org/10.1016/j.ecoinf.2022.101647