Skip to main content
Springer Nature Link
Log in

Effect of climate change on fire regimes in natural resources of northern Iran: investigation of spatiotemporal relationships using regression and data mining models

  • Original Paper
  • Published:
Natural Hazards Aims and scope Submit manuscript

Abstract

Mazandaran province in northern Iran is one of the fire-prone areas in the country in which a wide area of its natural resources have been destroyed by fire in recent years. This research aimed to detect the spatiotemporal relationships between climatic variables and fire regimes in Mazandaran province in recent decades. The fire variables (dependent variables) were the number and area of fires. The climatic variables (independent variables) were seasonal temperature mean, seasonal maximum temperature mean, seasonal absolute maximum temperature, seasonal precipitation mean, seasonal relative humidity mean, seasonal wind speed mean, and seasonal maximum wind speed mean for 26 years (1996–2021). Pearson's correlation coefficient and regression models were used to investigate the temporal relationship between fire and climatic variables during study period. Data mining models were used to detect the spatial relationship between fire ignition and climatic parameters and to produce the fire danger maps. The fire occurrence map was obtained from Mazandaran Natural Resources and Watershed Administration and Moderate-Resolution Imaging Spectroradiometer (MODIS) sensor. The climatic maps were obtained by interpolation methods in GIS. The weight of climatic parameters in fire ignition was determined using MDG and MDA statistics from random forest (RF) algorithm. Then different data mining models (logistic regression, random forest, support vector machine, and SVM-RF ensemble model) and 70% of actual fires were used for modeling fire danger in R software. The area under the curve and 30% of actual fires were applied for accuracy assessment of the models. Results of temporal relationships indicated that there are significant relationships among the number of fires and seasonal absolute maximum temperature, seasonal precipitation mean, and seasonal relative humidity mean. On the other hand, a significant relationship was observed between the area of fires and seasonal temperature mean. The results of spatial relationship demonstrated that seasonal temperature mean, seasonal precipitation mean, and seasonal relative humidity mean had the greatest spatial importance in fire ignition. The results of accuracy assessment of fire danger models indicated that SVM-RF and RF models were the best models for fire danger mapping. Therefore, using the maps obtained from these models, it is possible to predict the climate-caused fires in natural ecosystems of Mazandaran province.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
€32.70 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (France)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data availability

The datasets generated and/or analyzed during the current study are not publicly available due [because this data is the results of author's efforts and studies] but are available from the corresponding author on reasonable request.

Abbreviations

AUC:

Area under the curve

DEM:

Digital elevation model

IDW:

Inverse distance weighting

LR:

Logistic regression

MNRWA:

Mazandaran Natural Resources and Watershed Administration

MODIS:

Moderate-Resolution Imaging Spectroradiometer

MDG:

Mean decrease gini

MDA:

Mean decrease accuracy

RF:

Random forest

ROC:

Receiver operating characteristic

SVM:

Support vector machine

UNESCO:

United Nations Educational, Scientific and Cultural Organization

References

  • Aghaii S, Jalilvand H, Kooch Y, Poormajidian MR (2011) Plant diversity with respect to ecological factor of altitude in Sardabrood forests of Chaloos, N Iran. Iran J Biol 24(3):400–411

    Google Scholar 

  • Arpaci A, Malowerschnig B, Sass O, Vacik H (2014) Using multivariate data mining techniques for estimating fire susceptibility of Tyrolean forests. Appl Geogr 53:258–270

    Article  Google Scholar 

  • Barbero R, Abatzoglou JT, Larkin NK, Kolden CA, Stocks B (2015) Climate change presents increased potential for very large fires in the contiguous United States. Int J Wildland Fire 24(7):892–899

    Article  Google Scholar 

  • Bedia J, Herrera S, Gutiérrez JM, Benali A, Brands S, Mota B, Moreno JM (2015) Global patterns in the sensitivity of burned area to fire-weather: Implications for climate change. Agric for Meteorol 214–215:369–379

    Article  Google Scholar 

  • Bihamta M, Zare Chahooki M (2015) Principles of statistics in natural resource sciences statistics. Tehran University Press, Tehran, p 300p

    Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  • Breiman L, Cutler A (2022) Random forest for classification and regression. UTC, 29p

  • Bui DT, Le KTh, Nguyen VC, Le HD, Revhaug I (2016) Tropical forest fire susceptibility mapping at the Cat Ba National Park area, Hai Phong City, Vietnam, using GIS-based Kernel logistic regression. Remote Sens 8(4):1–15

    Google Scholar 

  • Chen F, Niu Sh, Tong X, Zhao J, Sun Y, He T (2014) The Impact of precipitation regimes on forest fires in Yunnan Province. Southwest China Sci World J 2014:1–9

    Google Scholar 

  • Chong C, Huang E, Chen L (2017) Effects of climate change on Canadian forest fires. STEM Fellowship J 3(2):1–6

    Article  Google Scholar 

  • Chou YH (1992) Management of wildfires with a geographical information system. Int J Geogr Inf Syst 6:123–140

    Article  Google Scholar 

  • Donges N (2018) The random forest algorithm. Accessed https://towardsdatascience.com/the-random-forest-algorithm-d457d499ffcd

  • Eskandari S, Chuvieco E (2015) Fire danger assessment in Iran based on geospatial information. Int J Appl Earth Obs Geoinf 42:57–64

    Google Scholar 

  • Eskandari S, Jalilvand H (2017) Effect of weather changes on fire regime of Neka and Behshahr forests. Iran J for Range Protect Res 15(1):30–39

    Google Scholar 

  • Eskandari S, Moradi A (2020) Mapping the land uses and analyzing the landscape elements in south-western Iran: application of Landsat-7, field data, and landscape metrics. Int J Conserv Sci 11(2):557–564

    Google Scholar 

  • Eskandari S, Oladi J, Jalilvand H, Saradjian MR (2013) Role of human factors on fire occurrence in District Three of Neka Zalemroud forestsIran. World Appl Sci J 27(9):1146–1150

    Google Scholar 

  • Eskandari S, Oladi J, Jalilvand H, Saradjian MR (2015a) Prediction of future forest fires using the MCDM method. Pol J Environ Stud 24(5):2309–2314

    Google Scholar 

  • Eskandari S, Oladi J, Jalilvand H, Saradjian MR (2015b) Evaluation of the MODIS fire-detection product in Neka-Zalemroud fire-prone forests in Northern Iran. Pol J Environ Stud 24(5):2305–2308

    Google Scholar 

  • Field RD, Spessa AC, Aziz NA, Camia A, Cantin A, Carr R, de Groot WJ, Dowdy AJ, Flannigan MD, Manomaiphiboon K, Pappenberger F, Tanpipat V, Wang X (2015) Development of a global fire weather database. Nat Hazard 15:1407–1423

    Article  Google Scholar 

  • Gholamnia Kh, Nachappa ThG, Ghorbanzadeh O, Blaschke Th (2020) Comparisons of diverse machine learning approaches for wildfire susceptibility mapping. Symmetry 12(4):604

    Article  Google Scholar 

  • Ghorbanzadeh O, Valizadeh K, Blaschke T, Aryal J, Naboureh A, Einali J, Bian J (2019) Spatial prediction of wildfire susceptibility using field survey GPS data and machine learning approaches. Fire 2(3):43

    Article  Google Scholar 

  • Golkarian A, Naghibi SA, Kalantar B, Pradhan B (2018) Groundwater potential mapping using C5.0, random forest, and multivariate adaptive regression spline models in GIS. Environ Monitor Assess 190(3):149

    Article  Google Scholar 

  • Higuera PE, Abatzoglou JT, Littell JS, Morgan P (2015) The changing strength and nature of fire-climate relationships in the Northern Rocky Mountains, U.S.A., 1902–2008. PLoS ONE 10(6):1–21

    Article  Google Scholar 

  • IBM SPSS Statistics 22 (2015) Brief Guide of IBM SPSS Statistics 22. Accessed https://www.ibm.com/support/knowledgecenter/en/SSLVMB_22.0.0/com.ibm.spss.statistics_22.kc.doc (http://www.sussex.ac.uk/its/pdfs/SPSS_Brief_Guide_22.pdf), 87 p.

  • Jolly WM, Cochrane MA, Freeborn PH, Holden ZA, Brown TJ, Williamson GJ, Bowman DMJS (2015) Climate-induced variations in global wildfire danger from 1979 to 2013. Nat Commun 6(7537):1–11

    Google Scholar 

  • Karatzoglou A, Smola A, Hornik K, Zeileis A (2004) Kernlab: An S4 Package for Kernel Methods in R. J Stat Softw 11:1–20

    Article  Google Scholar 

  • Kordestani MD, Naghibi SA, Hashemi H, Ahmadi K, Kalantar B, Pradhan B (2019) Groundwater potential mapping using a novel data-mining ensemble model. Hydrogeol J 27(1):211–224

    Article  Google Scholar 

  • Koutsias N, Karteris M (1998) Logistic regression modelling of multitemporal Thematic Mapper data for burned area mapping. Int J Remote Sens 19:3499–3514

    Article  Google Scholar 

  • Lee C (2017) Feature importance measures for tree models-Part I. Accessed https://medium.com/the-artificial-impostor/feature-importance-measures-for-tree-models-part-i-47f187c1a2c3

  • Loboda TV (2004) Estimating potential fire danger within the Siberian Tiger Habitat. Master thesis, University of Maryland, Maryland, USA

  • Martell DL, Otukol S, Stocks BJ (1987) A logistic model for predicting daily people-caused forest fire occurrence in Ontario. Can J for Res 17:394–401

    Article  Google Scholar 

  • Martinez J, Vega-Garcia C, Chuvieco E (2009) Human-caused wildfire risk rating for prevention planning in Spain. J Environ Manage 90:1241–1252

    Article  Google Scholar 

  • Mas JF, Filho BSS, Pontius RG, Farfan M (2013) A suite of tools for ROC analysis of spatial models. Int J Geo-Inf 2(3):869–888

    Article  Google Scholar 

  • Mazandaran Natural Resources and Watershed Administration (MNRWA) (2019) Statistics and data of fire in Mazandaran province. Protection Unit of MNRA, Sari, 128p

  • Moreno MV, Chuvieco E (2016) Fire regime characteristics along environmental gradients in Spain. Forests 7:262–275

    Article  Google Scholar 

  • Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens 66:247–259

    Article  Google Scholar 

  • Naimi B, Araujo M (2016) Package ‘sdm’. Accessed https://cran.r-project.org/web/packages/sdm/sdm.pdf

  • Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira J (2012) Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest. For Ecol Manage 275:117–129

    Article  Google Scholar 

  • Pitman AJ, Narisma GT, McAneney J (2007) The impact of climate change on the risk of forest and grassland fires in Australia. Clim Change 84:383–401

    Article  Google Scholar 

  • R Core Team (2014) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. Accessed http://www.R-project.org/

  • Razavi-Termeh SV, Sadeghi-Niaraki A, Choi SM (2019) Groundwater potential mapping using an integrated ensemble of three bivariate statistical models with random forest and logistic model tree models. Water 11(8):1596

    Article  Google Scholar 

  • Smith MJ, Goodchild MF, Longley PA (2007) Geospatial analysisa comprehensive guide to principles, techniques and software tools. Troubador Publishing Ltd, Leicester, p 516

    Google Scholar 

  • Song Ch, Kwan M, Song W, Zhu J (2017) A Comparison between spatial econometric models and random forest for modeling fire occurrence. Susceptibility 9(819):1–21

    Google Scholar 

  • Tavakkoli Piralilou S, Einali G, Ghorbanzadeh O, Nachappa TG, Gholamnia K, Blaschke T, Ghamisi P (2022) A Google Earth Engine approach for wildfire susceptibility prediction fusion with remote sensing data of different spatial resolutions. Remote Sensing 14(3):672

    Article  Google Scholar 

  • Tošić I, Mladjan D, Gavrilov MB, Živanović S, Radaković MG, Putniković S, Petrović P, Krstić Mistridželović I, Marković SB (2019) Potential influence of meteorological variables on forest fire risk in Serbia during the period 2000–2017. Open Geosci 11:414–425

    Article  Google Scholar 

  • Turco M, Llasat MC, Hardenberg JV, Provenzale A (2013) Impact of climate variability on summer fires in a Mediterranean environment (northeastern Iberian Peninsula). Clim Change 116:665–678

    Article  Google Scholar 

  • UNESCO (2019) Hyrcanian forests. Accessed: https://whc.unesco.org/en/list/1584/

  • Urrutia-Jalabert R, Gonzalez ME, Gonzalez-Reyes A, Lara A, Garreaud R (2018) Climate variability and forest fires in central and south-central Chile. Ecosphere 9(4):1–18

    Article  Google Scholar 

  • Yesilnacar EK (2005) The application of computational intelligence to landslide susceptibility mapping in Turkey. Ph.D. thesis, Department of Geomatics, University of Melbourne, Melbourne, Australia

  • Zumbrunnen T, Pezzattic GB, Menéndezd P, Bugmann H, Bürgia M, Conederac M (2011) Weather and human impacts on forest fires: 100 years of fire history in two climatic regions of Switzerland. For Ecol Manag 261:2188–2199

    Article  Google Scholar 

Download references

Acknowledgements

This work is based upon research funded by “Iran National Science Foundation (INSF)” under Project No. 99030457. Authors appreciate INSF for its support to perform this research.

Funding

This research has been funded by "Iran National Science Foundation (INSF)" under project No. 99030457.

Author information

Authors and Affiliations

  1. Forest Research Division, Research Institute of Forests and Rangelands, Agricultural Research Education and Extension Organization (AREEO), Tehran, Iran

    Saeedeh Eskandari & Hooman Ravanbakhsh

  2. Head of Plant Patologhy Group, Protection and Conservation Department, Natural Resources and Watershed Organization of Iran, Tehran, Iran

    Yazdanfar Ahangaran

  3. Head of Meteorological Research Department, Kohgiluyeh and Boyer Ahmad Meteorological Administration, Yasouj, Iran

    Zolfaghar Rezapour

  4. Department of Soil Science, College of Agriculture, Shiraz University, Shiraz, Iran

    Hamid Reza Pourghasemi

Authors
  1. Saeedeh Eskandari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hooman Ravanbakhsh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yazdanfar Ahangaran
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zolfaghar Rezapour
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hamid Reza Pourghasemi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

SE collected the required data, prepared the input maps, conducted the research, and analyzed the data. She wrote the paper, as well. HR helped to conduct the research. YA helped in collection of fire data for the research. ZR helped in collection of climatic data for the research. HRP helped in fire danger modeling and mapping in this research.

Corresponding author

Correspondence to Saeedeh Eskandari.

Ethics declarations

Conflict of interest

There is no declaration of interest by authors.

Ethics approval and consent to participate

All authors approve the ethics and consent to participate in this research.

Consent for publication

All authors have consent to publish this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Eskandari, S., Ravanbakhsh, H., Ahangaran, Y. et al. Effect of climate change on fire regimes in natural resources of northern Iran: investigation of spatiotemporal relationships using regression and data mining models. Nat Hazards 119, 497–521 (2023). https://doi.org/10.1007/s11069-023-06133-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11069-023-06133-4

Keywords

Search

Navigation