Uncovering the hidden patterns of fire risks: A cluster analysis approach (K-Medoids and FCM) for Hyrcanian Forest in Iran

Document Type : Research Paper

Authors

1 Department of Forestry, Faculty of Natural Resources, University of Guilan, Iran

2 Assistant Professor, Faculty of Chemistry, University of Science and Technology, Mazandaran

10.22124/cjes.2024.7977

Abstract

Forest fires have become a significant environmental concern in the Hyrcanian Forest, causing extensive loss of vegetation and posing a threat to biodiversity. Accurate prediction of high-risk fire locations is crucial for effective forest management. In this study, we developed and evaluated a clustering-based model using a multilayer perceptron artificial neural network with an error backpropagation training procedure to model fire risk potential in Saravan Forest, Guilan Province, North Iran. To optimize generalization, the model utilized two unsupervised clustering-specific procedures, namely Fuzzy C-Means and k-Medoids. The primary focus of our study was on the model's ability to predict potential fire risk locations, which is essential for forest fire prevention and control. The input criteria included recorded fire incidents, distances to farmland, roads, rivers, air pressure, solar radiation, slope, aspect, wind speed, and percentage of canopy cover density. The results showed that the procedure of the two algorithms used in this study in allocating potential fire hazard points is highly similar, differing mainly in the methodology employed for data center allocation. According to the results, the RMSE, R2, and MSE for the model used in this study are respectively equal to 0.2861, 99.38, and 0.01919, which indicates the reliability of the model. Moreover, according to the Confusion matrix analysis table's results, FCM was slightly better than K-medoids in terms of its predictive accuracy. This model demonstrated high accuracy in predicting fire hazards, showing promising potential for forest fire prediction using clustering-based models. Additionally, our model exhibited superior performance compared to other clustering techniques for identifying potential fire hazard sites. Our developed clustering-based model provides valuable insights for forest managers to identify locations at fire risk, enabling more efficient resource allocation and preventative measures. This approach can significantly improve forest fire management and reduce ecological damage caused by wildfires.

Keywords

References

 
Adab, H Kasturi Kanniah, KD & Solaimani, K 2013, Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques. Natural Hazards (Dordr) 65: 1723-1743, DOI:10.1007/s11069-012-0450-8.
Argañaraz, JP Pizarro, GG Zak, M Landi, MA & Bellis, LM 2015, Human and Biophysical Drivers of Fires in Semiarid Chaco Mountains of Central Argentina. Sci. Total Environment, 520: 1-12, https://doi.org/10.1016/ j.scitotenv.2015.02.081.
Bharany, S Sharma, S Frnda, J Shuaib, M Khslid, MI Hussain, S Iqbal, J & Uliah, SS 2022, Wildfire monitoring based on energy efficient clustering approach for FANETS, Drones, 6: 193.
Bezdek, J 1981, Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York, DOI: 10.1007/978-1-4757-0450-1.
Chai, T & Draxler, RR 2014, Root Mean Square Error (RMSE) Or Mean Absolute Error (MAE)? Geoscientific Model Development (GMD) & Discussions, 7: 1525-1534, DOI: 10.5194/gmdd-7-1525-2014.
Dunn, JC 1973, A Fuzzy Relative of the ISODATA Process and its use in detecting compact well-separated clusters. Journal of Cybernetics, 3: 32-57, DOI: 10.1080/01969727308546046.
Esakar, S & Chaudhari, M 2013, A review of clustering algorithms, www.ijcst.com 4.
Eskandari, S 2015, Investigation of relation between climate change and fire in the forests of Golestan Province, IJFRPR. 13.
Eskandari, S & Chuvieco, E 2015, Fire danger assessment in Iran based on geospatial information. International Journal of Applied Earth Observation and Geoinformation, 42: 57-64, DOI: 10.1016/j.jag.2015.05.006.
Eskandari, S Oladi, J Jalilvand, H & Saradjian, MR 2013, Role of human factors on fire occurrence in district three of Neka Zalemroud Forests, Iran, World Applied Sciences Journal, 27, DOI: 10.5829/idosi.wasj. 2013.27.09.708.
Frahi, E Ghodskhahdaryaei, M Mohamadi Samani, K & Amlashi, M 2012, Review of fire sensitive areas with emphasis on drought impact with the joint use of DSI, AHP and GIS (Case study: Forest Saravan, Guilan Province), Forest and Range Protection Research. 10: 83-101, https://www.sid.ir/en/Journal/ViewPaper.aspx? ID=529534.
Fawcett, T 2006, An introduction to ROC analysis, Pattern Recognition Letters, 27 (8): 861-74, DOI: 10.1016/ j.patrec.2005.10.010.
Giwa, O & Abdsamad, B 2018, Fire detection in a still image using color information. https://doi.org/10.48550/ arXiv.1803.03828.
Global Forest Watch 2018 Tree cover loss in Rasht, Guilan, Iran, https://www.globalforestwatch.org.
Hunt, RJ 1986, Percent agreement, Pearson's correlation, and Kappa as Measures of Inter-Examiner reliability, Journal of Dental Research, 65: 128-30, DOI: 10.1177/00220345860650020701.
Jafarzadeh, A Mahdavi, A & Jafarzadeh, H 2017, Evaluation of forest fire risk using the Apriori Algorithm and Fuzzy C-Means Clustering, DOI: 10.17221/7/2017-JFS.
Jain, P Cogan, SCP Subramanian, SG Crowley Taylor, S & Flannigan, MD 2020, A review of machine learning applications in wildfire science and management. Environmental Reviews, 28: 478-505. https://doi.org/ 10.1139/er-2020-0019.
Jiawei, H Kamber, M & Tung, A 2001, Spatial clustering methods in data mining: A survey. Data Mining and Knowledge Discovery, DATAMINE.
Karimov, J Ozbayoglu, M & Dogdu, N 2015, K-means performance improvements with centroid calculation heuristics both for serial and parallel environments. In: 2015 IEEE International Congress on Big Data, 444–451, DOI: 10.1109/BigDataCongress.2015.72.
Kaufman, L & Rousseeuw, PJ 2005, Finding groups in data: An Introduction to cluster analysis. Wiley series in probability and mathematical statistics, Hoboken, NJ: Wiley-Intercedence. http://catdir.loc.gov/catdir/ description/wiley033/89031460.html.
Khatami, A Mirghasemi, S Khosravi, A Lim, CP & Nahavandi, S 2017, A new PSO-Based approach to fire flame detection using K-Medoids Clustering, Expert Systems with Applications, 68: 69-80, DOI: 10.1016/j.eswa. 2016.09.021.
Khatami, A Mirghasemi, S Khosravi, A & Nahavandi, S 2015, An efficient hybrid algorithm for fire flame detection. In 2015 International Joint Conference on Neural Networks (IJCNN), edited by IEEE Staff, 1-6, Piscataway: IEEE.
Krishnapuram, R Joshi, A & Liyu, Y 1999, A Fuzzy Relative of the K-Medoids algorithm with application to web document and Snippet Clustering. In FUZZ-IEEE'99, 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315), 1281-1286 Vol. 33.
Lewis-Beck, MS & Skalaban, A 1990, The R-squared: Some straight talk. Political Analysis, 2: 153-171, DOI:10.1093/pan/2.1.153.
Littell, JDL Peterson, Riley, KL Yongquiang, L & Luce, CH 2016, A review of the relationships between drought and forest fire in the United States. Global Change Biology, 22 (7): 2353-2369.
Mood, Al Franklin, M Graybill, A & Duane, CB 2013, Introduction to the theory of statistics. 3. ed., McGraw Hill Education (India) ed., 13. reprint. New Delhi: McGraw-Hill Education (India).
Nayak, J Naik, B & Behera, HS 2015, Fuzzy C-Means (FCM) clustering algorithm: A decade review from 2000 to 2014, In: Computational Intelligence in Data Mining, 2: 133-149: Springer, New Delhi. https://link.springer.com/chapter/10.1007/978-81-322-2208-8_14.
Mohamed, SH Jaksa, M & Maier, H 2008, State of the art of artificial neural networks in geotechnical engineering, Electronic Journal of Geotechnical Engineering.
Piruz, B Razdar, B Bagherzadeh, A & Kavianpour, M 2010, Assessment of the damage caused by the dumping of waste from Rasht city in Saravan Forest area located in Gilan Province, National Conference on Man, Environment and Sustainable Development.
Rakshit, P Sarkar, S Khan, S Saha, P Bhattacharyya, S Dey, ... & Pal, S 2021, Prediction of forest fire using machine learning algorithms: The search for the better algorithm. In 2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA), pp. 1-6. IEEE.‏
Sathishkumar, VE, Cho, J Subramanian, M & Naren, O 2023, A forest fire and smoke detection using deep learning-based learning without forgetting. Fire Ecology, 19: 1-17.‏
Shahin, MA Jaksa, MB Holger, MR 2008, State of the art of artificial neural networks in geotechnical engineering, Electronic Journal of Geotechnical Engineering, 8: 1-26.
Shreya, M Rai, R & Shukla, S 2022, Forest fire prediction using machine learning and deep learning techniques. In: Computer networks and inventive communication technologies: Proceedings of Fifth ICCNCT 2022, pp. 683-694, Singapore: Springer Nature Singapore.‏
Tien Bui, D van Le, H & Hoang, ND 2018, GIS-based spatial prediction of tropical forest fire danger using a new hybrid machine learning method ecological informatics, 48: 104-116, DOI: 10.1016/j.ecoinf.2018.08.008.
Wei, Ch P Lee, YH Hsu Che, M 2000, Empirical comparison of fast clustering algorithms for large data sets. In Proceedings of the 33rd Annual Hawaii International Conference on System Sciences, edited by Ralph H. Sprague, 10: IEEE Computer Society, DOI:10.1109/HICSS.2000.926655.
Xu, R & Wunsch, D 2005, Survey of clustering algorithms. IEEE Transactions on Neural Networks, 16: 645-678. DOI: 10.1109/TNN.2005.845141.
Yaghameiyan mahabadi, N Khosroabadi, M & Asadi, H 2017, The effect of afforestation and topography on some physicochemical characteristics affecting soil quality in Saravan region of Gilan. Soil Research (Soil and Water Sciences), 31: 277-290.
Zareka, A Zamani, B Ghorbani, S Moalla, M & Jafari, H 2013, Mapping spatial distribution of forest fire using MCDM and GIS (Case study: Three forest zones in Guilan Province). Irianin Journal of forest and polar research, 21:218–30. DOI:10.22092/ijfpr.2013.3854.
Zhong, Zh Huang WLi, S & Zeng, Y 2017, Forest fire spread simulating model using cellular automaton with extreme learning machine. Ecological Modelling. 348: 33-43, DOI: 10.1016/j.ecolmodel.2016.12.022.
Caspian Journal of Environmental Sciences

Articles in Press, Corrected Proof
Available Online from 31 August 2024

Files

Share

How to cite

Statistics