Sınırlı Eğitim Verileri Durumunda Orman Yangını Duyarlılık Haritalamasında Makine Öğrenimi Performansının Değerlendirilmesi

Yıl 2022, Cilt: 4 Sayı: 2, 317 - 327, 26.10.2022

Mahyat Shafapourtehrany

https://doi.org/10.46387/bjesr.1174006

Öz

Orman yangını duyarlılık haritalaması çeşitli faktörlerden etkilenebilir. En etkili faktörlerden biri envanter verileri, kapsamı, biçimi ve güvenilirliğidir. Bu çalışma, Support Vector Machine’in (SVM) sınırlı eğitim verisi koşulları altında orman yangınına duyarlı alanları tespit etme ve haritalama kabiliyetine sahip olup olmadığını değerlendirmeyi amaçlamaktadır. Bu hipotezi test etmek için Türkiye'nin Doğu Akdeniz Bölgesi'nde yer alan Muğla ilindeki orman yangınları pilot çalışma alanı olarak seçilmiştir. Bahsedilen orman yangını Muğla'da 29 Temmuz 2021'de başlamış ve yerleşim alanlarını, hayvanları ve geniş ormanlık alanları önemli ölçüde etkilemiştir. Bağımsız değişkenler olarak on dört orman yangını etkili değişken analizinde kullanılmıştır. Doğruluk değerlendirmesi için Area Under thr Curve (AUC) tekniği kullanılarak uygulama yapılmıştır. Başarı oranı ve tahmin oranları sırasıyla (%91.42) ve (%87.69)’dir. Tahmin oranına göre, SVM diğer yanık alanları en hassas bölgeler olarak başarıyla tanımladı.

Anahtar Kelimeler

Orman Yangını, Envanter, Duyarlılık, Türkiye, Jeo-uzamsal

Evaluation of Machine Learning Performance in Wildfire Susceptibility Mapping Under Limited Training Data Condition

Öz

Wildfire susceptibility mapping can be affected by several factors. One of the most influential factors is inventory data, its extent, format, and reliability. This study aims to evaluate if the Support Vector Machine (SVM) has the capability to detect and map the forest fire susceptible areas under limited training data conditions. To test this hypothesis wildfires in Mugla province located in the Eastern Mediterranean Region of Turkey have been selected as a pilot study area. The wildfire started in Mugla, on 29 July 2021, that considerably affected the residential areas, animals, and vast areas of forests. Fourteen wildfire influential variables have been used in the analysis as independent variables. Accuracy assessment has been implemented using the Area Under the Curve (AUC) technique. Success rate and prediction rates were (91.42%) and (87.69%) respectively. According to the prediction rate, SVM successfully recognized other burnt areas as the most susceptible regions.

Anahtar Kelimeler

Wildfire, Inventory, Susceptibility, Turkey, Geospatial

Kaynakça

• Ajin, R., Loghin, A.-M., Jacob, M. K., Vinod, P., & Krishnamurthy, R. (2016). The risk assessment study of potential forest fire in Idukki Wildlife Sanctuary using RS and GIS techniques. International Journal of Advanced Earth Science and Engineering, 5(1), 308-318.
• Aldersley, A., Murray, S. J., & Cornell, S. E. (2011). Global and regional analysis of climate and human drivers of wildfire. Science of the Total Environment, 409(18), 3472-3481.
• Barmpoutis, P., Papaioannou, P., Dimitropoulos, K., & Grammalidis, N. (2020). A review on early forest fire detection systems using optical remote sensing. Sensors, 20(22), 6442.
• Bennett, K. P., & Bredensteiner, E. J. (2000). Duality and geometry in SVM classifiers. ICML.
• Boers, N., Bookhagen, B., Barbosa, H. M., Marwan, N., Kurths, J., & Marengo, J. (2014). Prediction of extreme floods in the eastern Central Andes based on a complex networks approach. Nature communications, 5(1), 1-7.
• Brenning, A. (2005). Spatial prediction models for landslide hazards: review, comparison and evaluation. Natural Hazards and Earth System Sciences, 5(6), 853-862.
• Choubin, B., Moradi, E., Golshan, M., Adamowski, J., Sajedi-Hosseini, F., & Mosavi, A. (2019). An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Science of the Total Environment, 651, 2087-2096.
• Crawford‐Flett, K., Blake, D. M., Pascoal, E., Wilson, M., & Wotherspoon, L. (2022). A standardised inventory for New Zealand's stopbank (levee) network and its application for natural hazard exposure assessments. Journal of Flood Risk Management, 15(2), e12777.
• Deb, P., Moradkhani, H., Abbaszadeh, P., Kiem, A. S., Engström, J., Keellings, D., & Sharma, A. (2020). Causes of the widespread 2019–2020 Australian bushfire season. Earth's Future, 8(11), e2020EF001671.
• Dou, J., Yunus, A. P., Tien Bui, D., Sahana, M., Chen, C.-W., Zhu, Z., Wang, W., & Pham, B. T. (2019). Evaluating GIS-based multiple statistical models and data mining for earthquake and rainfall-induced landslide susceptibility using the LiDAR DEM. Remote Sensing, 11(6), 638.
• Eke, M., Cingiroglu, F., & Kaynak, B. (2022). Impacts of summer 2021 wildfire events in Southwestern Turkey on air quality with multi-pollutant satellite retrievals.
• Eslami, R., Azarnoush, M., Kialashki, A., & Kazemzadeh, F. (2021). Gis-based forest fire susceptibility assessment by random forest, artificial neural network and logistic regression methods. Journal of Tropical Forest Science, 33(2), 173-184.
• Gholamnia, K., Gudiyangada Nachappa, T., Ghorbanzadeh, O., & Blaschke, T. (2020). Comparisons of diverse machine learning approaches for wildfire susceptibility mapping. Symmetry, 12(4), 604.
• Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., & Aryal, J. (2019). Forest fire susceptibility and risk mapping using social/infrastructural vulnerability and environmental variables. Fire, 2(3), 50.
• Ghorbanzadeh, O., Valizadeh Kamran, 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.
• Gigović, L., Pourghasemi, H. R., Drobnjak, S., & 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(5), 408.
• Güngöroğlu, C. (2017). Determination of forest fire risk with fuzzy analytic hierarchy process and its mapping with the application of GIS: The case of Turkey/Çakırlar. Human and Ecological Risk Assessment: An International Journal, 23(2), 388-406.
• Hosseini, M., & Lim, S. (2021). Gene expression programming and ensemble methods for bushfire susceptibility mapping: a case study of Victoria, Australia. Geomatics, Natural Hazards and Risk, 12(1), 2367-2386.
• Hosseini, M., & Lim, S. (2022). Gene expression programming and data mining methods for bushfire susceptibility mapping in New South Wales, Australia. Natural Hazards, 1-17.
• Huyen, D., & Tuan, V. A. (2008). Applying GIS and multi criteria evaluation in forest fire risk zoning in son la province, Vietnam. International Conference on Geoinformation Spatial-Infrastructure Development, Hanooi, Vietnam.
• Iban, M. C., & Sekertekin, A. (2022). Machine learning based wildfire susceptibility mapping using remotely sensed fire data and GIS: A case study of Adana and Mersin provinces, Turkey. Ecological Informatics, 69, 101647.
• Jenkins, M. E., Bedward, M., Price, O., & Bradstock, R. A. (2020). Modelling bushfire fuel hazard using biophysical parameters. Forests, 11(9), 925.
• Khan, S., Crozier, M., & Kennedy, D. (2012). Influences of place characteristics on hazards, perception and response: a case study of the hazardscape of the Wellington Region, New Zealand. Natural Hazards, 62(2), 501-529.
• Liu, Y., Liu, Y., Fu, J., Yang, C.-E., Dong, X., Tian, H., Tao, B., Yang, J., Wang, Y., & Zou, Y. (2021). Projection of future wildfire emissions in western USA under climate change: contributions from changes in wildfire, fuel loading and fuel moisture. International Journal of Wildland Fire, 31(1), 1-13.
• Ljubomir, G., Pamučar, D., Drobnjak, S., & Pourghasemi, H. R. (2019). Modeling the spatial variability of forest fire susceptibility using geographical information systems and the analytical hierarchy process. In Spatial modeling in GIS and R for earth and environmental sciences (pp. 337-369). Elsevier.
• Marjanovic, M., Bajat, B., & Kovacevic, M. (2009). Landslide susceptibility assessment with machine learning algorithms. 2009 International Conference on Intelligent Networking and Collaborative Systems. Meyer, D., Leisch, F., & Hornik, K. (2003). The support vector machine under test. Neurocomputing, 55(1-2), 169-186.
• Moskwa, E., Bardsley, D. K., Robinson, G. M., & Weber, D. (2018). Generating narratives on bushfire risk and biodiversity values to inform environmental policy. Environmental science & policy, 89, 30-40.
• Nami, M., Jaafari, A., Fallah, M., & Nabiuni, S. (2018). Spatial prediction of wildfire probability in the Hyrcanian ecoregion using evidential belief function model and GIS. International journal of environmental science and technology, 15(2), 373-384.
• Noble, W. S. (2006). What is a support vector machine? Nature biotechnology, 24(12), 1565-1567.
• Patle, A., & Chouhan, D. S. (2013). SVM kernel functions for classification. 2013 International Conference on Advances in Technology and Engineering (ICATE).
• Perera, K., Tateishi, R., Akihiko, K., & Herath, S. (2021). A Combined Approach of Remote Sensing, GIS, and Social Media to Create and Disseminate Bushfire Warning Contents to Rural Australia. Earth, 2(4), 715-730.
• Pham, B. T., Pradhan, B., Bui, D. T., Prakash, I., & Dholakia, M. (2016). A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental Modelling & Software, 84, 240-250.
• Pourghasemi, H. R. (2016). GIS-based forest fire susceptibility mapping in Iran: a comparison between evidential belief function and binary logistic regression models. Scandinavian Journal of Forest Research, 31(1), 80-98.
• Pouyan, S., Pourghasemi, H. R., Bordbar, M., Rahmanian, S., & Clague, J. J. (2021). A multi-hazard map-based flooding, gully erosion, forest fires, and earthquakes in Iran. Scientific Reports, 11(1), 1-19.
• Sachdeva, S., Bhatia, T., & Verma, A. (2018). GIS-based evolutionary optimized Gradient Boosted Decision Trees for forest fire susceptibility mapping. Natural Hazards, 92(3), 1399-1418.
• Sari, F. (2021). Forest fire susceptibility mapping via multi-criteria decision analysis techniques for Mugla, Turkey: A comparative analysis of VIKOR and TOPSIS. Forest Ecology and Management, 480, 118644.
• Shafapour Tehrany, M., Kumar, L., Neamah Jebur, M., & Shabani, F. (2019). Evaluating the application of the statistical index method in flood susceptibility mapping and its comparison with frequency ratio and logistic regression methods. Geomatics, Natural Hazards and Risk, 10(1), 79-101.
• Shmuel, A., & Heifetz, E. (2022). Global Wildfire Susceptibility Mapping Based on Machine Learning Models. Forests, 13(7), 1050.
• Stambaugh, M. C., & Guyette, R. P. (2008). Predicting spatio-temporal variability in fire return intervals using a topographic roughness index. Forest Ecology and Management, 254(3), 463-473.
• Suthaharan, S. (2016). Support vector machine. In Machine learning models and algorithms for big data classification (pp. 207-235). Springer.
• Taseen, S., Abbas, M., Munir, F., Ullah, I., & Tahir, M. (2022). Impact of Overlapping Disaster in Turkey: COVID-19 Pandemic and Wildfires. Journal of Contemporary Studies in Epidemiology and Public Health, 3(1).
• Tavakkoli Piralilou, S., Einali, G., Ghorbanzadeh, O., Nachappa, T. G., 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.
• Tehrany, M. S., Özener, H., Kalantar, B., Ueda, N., Habibi, M. R., Shabani, F., Saeidi, V., & Shabani, F. (2021). Application of an ensemble statistical approach in spatial predictions of bushfire probability and risk mapping. Journal of Sensors, 2021.
• Van Dao, D., Jaafari, A., Bayat, M., Mafi-Gholami, D., Qi, C., Moayedi, H., Van Phong, T., Ly, H.-B., Le, T.-T., & Trinh, P. T. (2020). A spatially explicit deep learning neural network model for the prediction of landslide susceptibility. Catena, 188, 104451.
• Vapnik, V. N. (1999). An overview of statistical learning theory. IEEE transactions on neural networks, 10(5), 988-999.
• Verde, J., & Zêzere, J. (2010). Assessment and validation of wildfire susceptibility and hazard in Portugal. Natural Hazards and Earth System Sciences, 10(3), 485-497.
• Wang, X.-z., He, Q., Chen, D.-G., & Yeung, D. (2005). A genetic algorithm for solving the inverse problem of support vector machines. Neurocomputing, 68, 225-238.