Forest Fire Risk Zone Mapping with Prediction of Forest Fire through Support Vector Machines (SVM) for Kothagudem, Telangana, India
DOI:
https://doi.org/10.36808/if/2025/v151i4/170679Keywords:
Forest fire, Machine learning model (MLM), Support vector machine (SVM), Forest fire risk index, Forest litter.Abstract
Forest fire is major man-made and/or natural disaster in which the destruction is multifaceted. This risk required timely detection and need to be curbed before fire occurred as prevention. It is therefore essential to make fire risk zonation map so that the fire can be watched and controlled timely. For risk map in study area, factors that are assumed to be affecting forest fire are land use and land cover (LULC), distance from road, litter weight, aspect, elevation and slope using suitable, weight, rank and assigning an index which was further represented under low, moderate and high risk. The thematic layers of all these factors were constructed in Geographical Information System (GIS) and overlaid to delineate the fire risk zone map. The low-risk zones are in scrub-shrub, orchards, moist deciduous and agriculture while high and moderate risk of forest fire exist in dry-deciduous and degraded-dry deciduous forest area. The area under low risk is 35.94%, moderate risk is 47.18% and 16.88% under high risk. The forest fire vulnerable areas were also integrated with SVM classification model to predict the fire and non-fire points, with an accuracy of more than 80% for each zone and precision, recall and f1-score during testing phase for each zone gave good results. The predicted instances were mapped onto vulnerable areas and the analysis showed that SVM are able to classify fire points. The integration of remote sensing and machine learning models can help in delineating more accurate status of region and more precise information useful for monitoring and mitigation of forest fire.
References
Ajin R.S., Ciobotaru A., Vinod P.G. and Jacoba M.K. (2015). Forest and Wildland Fire Risk Assessment Using Geospatial Techniques: A Case Study of Nemmara Forest Division, Kerala, India. J. Wetlands Biodiversity, 5: 29-37.
Ajin R.S., Loghin A.M., Vinod P.G. and Jacob M.K. (2016). Forest Fire Risk Zone Mapping Using RS and GIS Techniques: A Study in Achankovil Forest Division, Kerala, India. J Earth Environ Health Sci., 2: 109-15. DOI: https://doi.org/10.4103/2423-7752.199288
Amalina P., Prasetyo L.B. and Rushayati S.B. (2016). Forest Fire Vulnerability Mapping in Way Kambas National Park. Procedia Environmental Sciences, 33: 239 – 252. DOI: https://doi.org/10.1016/j.proenv.2016.03.075
Arulrajan P., Kaur A. and Garbyal S.S. (2024). High-resolution prediction of forest fire incidence using Artificial Neural Networks. Indian Forester, 150(3): 195-208. DOI: 10.36808/if/2024/v150i3/170243 DOI: https://doi.org/10.36808/if/2024/v150i3/170243
Babu K.V.S., Roy A. and Prasad P.R. (2016). Forest fire risk modeling in Uttarakhand Himalaya using TERRA satellite datasets. European Journal of Remote Sensing, 49(1): pp.381395. DOI: https://doi.org/10.5721/EuJRS20164921
Brereton R.G. and Lloyd G.R. (2010). Support Vector Machines for classification and regression. Analyst, 135: 230–267 DOI: https://doi.org/10.1039/B918972F
Carvalho N.S., Ferreira I.J.M., Körting T.S., Aragão L.E.O.C. and Anderson L.O. (2019, 14-17 April). Random Forest And Support Vector Machine Applied For Mapping Burned Areas In Amazon.
Santos, SP-Brasil Chandra K.K. and Bhardwaj A.K. (2015). Incidence of Forest Fire in India and Its Effect on Terrestrial Ecosystem Dynamics, Nutrient and Microbial Status of Soil. International Journal of Agriculture and Forestry, 5(2): 69-78.DOI: 10.5923/j.ijaf.20150502.01
Chanthiya P. and Kalaivani V. (2021). Forest fire detection on LANDSAT images using support vector machine. Concurrency Computat Pract Exper, e6280. https://doi.org/10.1002/ cpe.6280 DOI: https://doi.org/10.1002/cpe.6280
Flannigan M.D, Stocks B.J. and Wotton B.M. (2000). Climate change and forest fires. Science of the Total Environment, 262(3): 221-229. https://doi.org/10.1016/S0048-9697(00) 00524-6 DOI: https://doi.org/10.1016/S0048-9697(00)00524-6
García M., Riaño D., Chuvieco E., Salas J. and Danson F.M. (2011). Multispectral and LiDAR data fusion for fuel type mapping using Support Vector Machine and decision rules. Remote Sensing of Environment, 115: 1369–1379. DOI: https://doi.org/10.1016/j.rse.2011.01.017
Gigovi´c L., Pourghasemi H.R., Drobnjak S. and Bai S. (2019). Testing a New Ensemble Model Based on SVM and Random Forest in Forest Fire Susceptibility Assessment and Its Mapping in Serbia's Tara National Park. Forests, 10: 408; doi:10.3390/f10050408 DOI: https://doi.org/10.3390/f10050408
Ice G.G., Neary D.G. and Adams P.W. (2004). Effects of wildfire on soils and watershed processes. DOI: https://doi.org/10.1093/jof/102.6.16
Jaafari A. and Pourghasemi H.R. (2019). Factors Influencing Regional-Scale Wildfire Probability in Iran: An Application of Random Forest and Support Vector Machine. Spatial Modeling in GIS and R for Earth and Environmental Sciences. DOI: https://doi.org/10.1016/B978-0-12-815226-3.00028-4 DOI: https://doi.org/10.1016/B978-0-12-815226-3.00028-4
Jaiswal R.K., Mukherjee S., Raju K.D. and Saxena R. (2002). Forest fire risk zone mapping from satellite imagery and GIS. International Journal of Applied Earth Observation and Geoinformation, 4(1): 1-10. DOI: https://doi.org/10.1016/S0303-2434(02)00006-5
Jhariya M.K. (2017). Influences of Forest Fire on Forest Floor and Litterfall in Bhoramdeo Wildlife Sanctuary (C.G.), India. Journal of Forest and Environmental Science, 33(4): 330-341. https://doi.org/10.7747/JFES.2017.33.4.330
Karra and Kontgis (2021). Global land use/land cover with Sentinel-2 and deep learning. IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE. DOI: https://doi.org/10.1109/IGARSS47720.2021.9553499
Kavzoglu T., Sahin E.K. and Colkesen I. (2014). Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression. Landslides, 11(3): 425-439. DOI: https://doi.org/10.1007/s10346-013-0391-7
Kerdprasop N., Poomka P., Chuaybamroong P. and Kerdprasop K. (2018). Forest Fire Area Estimation using Support Vector Machine as an Approximator. In Proceedings of the 10th International Joint Conference on Computational Intelligence (IJCCI 2018), pages 269-273. DOI: 10.5220/0007224802690273 DOI: https://doi.org/10.5220/0007224802690273
Pandey K. and Ghosh S.K. (2018). Modeling of parameters for forest fire risk zone mapping. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, ISPRS TC V Mid-term Symposium “Geospatial Technology – Pixel to People. Dehradun, India DOI: https://doi.org/10.5194/isprs-archives-XLII-5-299-2018
Rawat G.S. (2003). Fire risk assessment for forest fire control management in Chilla Forest range of Rajaji National Park Uttaranchal (India). Master's thesis, International Institute for Geo-Information Science and Earth Observation Enschede, The Netherlands.
Rossa C.G. (2017). The effect of fuel moisture content on the spread rate of forest fires in the absence of wind or slope. International Journal of Wildland Fire, 26(1): 24 31. DOI: https://doi.org/10.1071/WF16049
Schunk C., Ruth B., Leuchner M., Wastl C. and Menzel A. (2016). Comparison of different methods for the in situ measurement of forest litter moisture content. Natural Hazards & Earth System Sciences Discussions, 16(2): 403–415. DOI: https://doi.org/10.5194/nhess-16-403-2016
Shao Y., Feng Z., Sun L., Yang X., Li Y., Xu B. and Chen Y. (2022). Mapping China's Forest Fire Risks with Machine Learning. Forests, 13: 856. https://doi.org/10.3390/f13060856 DOI: https://doi.org/10.3390/f13060856
Shao Y., Feng Z., Cao M., Wang W., Sun L., Yang X., Ma T., Guo Z., Fahad S., Liu X. and Wang. Z. (2023). Ensemble Model for Forest Fire Occurrence Mapping in China. Forests, 14: 704. https://doi.org/10.3390/f14040704 DOI: https://doi.org/10.3390/f14040704
Somashekar R.K., Ravikumar P., Mohan Kumar C.N., Prakash K.L. and Nagaraja B.C. (2009). Burnt Area Mapping of Bandipur National Park, India using IRS 1C/1D LISS III data. Journal of the Indian Society of Remote Sensing, 37(1): 37-50. DOI: https://doi.org/10.1007/s12524-009-0010-1
Tatli H. and Türkeş M. (2014). Climatological Evaluation of Haines Forest Fire Weather Index over the Mediterranean Basin. Meteorological Applications, 21(3): 545-552. DOI: https://doi.org/10.1002/met.1367
Tehrany M.S., Pradhan B., Mansor S. and Ahmad N. (2015). Flood susceptibility assessment using GIS based support vector machine model with different kernel types. Catena, 125: 91-101. DOI: https://doi.org/10.1016/j.catena.2014.10.017
Wijaya A. and Gloaguen R. (2007). Comparison of Multisource Data Support Vector Machine Classification for Mapping of Forest Cover. IEEE, 1-4244-1212-9/07. DOI: https://doi.org/10.1109/IGARSS.2007.4423038
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Unless otherwise stated, copyright or similar rights in all materials presented on the site, including graphical images, are owned by Indian Forester.
