Modeling fires based on the results of correlation analysis


  • Olga Butenko Department of Geoinformation technologies and space monitoring of the Earth, Zhukovsky National aerospace university “KHAI”, Kharkiv, Ukraine
  • Anna Topchiy Department of Geoinformation technologies and space monitoring of the Earth, Zhukovsky National aerospace university “KHAI”, Kharkiv, Ukraine



modeling, ecology, methods, data, parameters


In order to monitor and study in more detail the causes and probability of the occurrence and spread of fires in the east of Ukraine in the combat zone, mathematical modeling of the factors influencing the occurrence of fires based on linear regression was performed in this study. The initial assessment of a priori information presented in a discrete form is a time—consuming process. A large dataset with a time interval requires application of ready—made methods and solutions. By applying statistical analysis techniques and historical analogies, it becomes possible to visually and graphically evaluate the initial data. This evaluation serves as the foundation for classifying factors, which enables their division into samples for subsequent analysis and modeling.
The expediency of application of correlation analysis is demonstrated by its ability to establish and illustrate the connections between fires and hostilities across different time intervals. To examine the connection between fires and the factors contributing to their occurrence, the widely used method of linear regression was applied, which is common in solving problems of ecological monitoring of the Earth.
Consequently, a program code was developed to provide the implementation of the linear regression algorithm. Since a large data set requires ready—made mathematical tools with a visualization function, therefore, the Python programming language was chosen as a tool for mathematical modeling of fires in eastern Ukraine caused by ongoing active hostilities. To facilitate simulation, random variables are partitioned with a distribution ratio of 40% for testing models and 60% for training models. The visual materials in this study encompass the initial data for subsequent analysis, the outcomes of data set partitioning, and their corresponding models. The tabular data comprises quantitative assessments of test and training models, serving as a basis for decision—making regarding the degree to which prediction results align with the study's objectives. These quantitative evaluations of prediction outcomes highlight the necessity of a comprehensive initial set of factors influencing fire initiation, along with their qualitative and quantitative classification. The implementation of the mathematical algorithm confirms the ease of application of regression methods.
However, when employing regression analysis to model fires without prior knowledge, it highlights the importance of conducting supplementary analysis through other established methods and synthesizing additional data. This can be achieved by utilizing interval estimates with the aid of fuzzy logic.


Artés, T., Cencerrado, A., Cortés, A., Margalef, T. (2016). Time aware genetic algorithm for forest fire propagation prediction: Exploiting multi—core platforms. Concurrency and Computation Practice and Experience, 29(9), 3837. DOI:

Avilaflores, D.Y., Pompagarcia, M., Antonionemiga, X., Rodrigueztrejo, D.A., Vargasperez, E., Santillan—Perez, J. (2010). Driving factors for forest fire occurrence in Durango State of Mexico: A geospatial perspective. Chinese Geographical Science , 20(6), pp. 491–497. DOI:

Balbi, J.-H., Chatelon, F.J., Rossi, J.L., Simeoni, A., Viegas, D.X., Rossa, C. (2014). Modelling of eruptive fire occurrence and behaviour. Journal of Environmental Science and Engineering, 3, pp. 115-132. DOI:

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. doi:

Bhusal, S., Mandal, R. (2020). Forest fire occurrence, distribution and future risks in Arghakhanchi district, Nepal. Journal of Geography , 2(1), pp.10–20.

Cunningham, A.A., Martell, D.L. (1973). A Stochastic Model for the Occurrence of Man—caused Forest Fires. Canadian Journal of Forest Research, 3(2), pp.282–287. doi:

Gülçin, D., Deniz, B. (2020). Remote sensing and GIS—based forest fire risk zone mapping: The case of Manisa, Turkey. Turkish Journal of Forestry / Türkiye Ormancılık Dergisi, 21(1), pp. 15–24. doi:

Kalantar, B., Ueda, N., Idrees, M.O., Janizadeh, S., Ahmadi, K., Shabani, F. (2020). Forest Fire Susceptibility Prediction Based on Machine Learning Models with Resampling Algorithms on Remote Sensing Data. Remote Sensing, 12, 3682. DOI:

Ko, B.C., Cheong, K.H., Nam, J.Y. (2009). Fire detection based on vision sensor and support vector machines. Fire Safety Journal, 44(3), pp. 322–329. DOI:

Liao, B.Q., Wei, J., Song, W.G., Tan, C.C. (2008). Logistic and ZIP Regression Model for Forest Fire Data. Fire Safety Science, 3, pp. 143–149.

Naranjo, S., Brito, N., Núñez, V. (2022). Analysis of the use of the Python programming language for statistical calculations. Espirales Revista multidisciplinaria de investigación, 6(41). DOI: 10.31876/er.v6i41.813.

Maffei, C., Lindenbergh, R.C., Menenti, M. (2021). Combining multi—spectral and thermal remote sensing to predict forest fire characteristics. ISPRS Journal of Photogrammetry and Remote Sensing, 181, pp. 400–412. doi:

Pradeep, G.S., Prasad, M.K., Kuriakose, S.L., Ajin, R.S., Oniga, V.E., Rajaneesh A., Mammen, P.C., Patel, N., Nikhil, S., Danumah, J.H. (2021). Forest Fire Risk Zone Mapping of Eravikulam National Park in India. Croatian Journal of Forest Engineering, 43(1), pp. 199–217. DOI:

Prasad, A.M., Iverson, L.R., Liaw, A. (2006). Newer classification and regression tree techniques: Bagging and random forests for ecological prediction. Ecosystems, 9(2), pp. 181–199. DOI:

Qiu, J., Wang, H., Shen, W., Zhang, Y., Su, H., Li, M. (2021). Quantifying Forest Fire and Post—Fire Vegetation Recovery in the Daxin’anling Area of Northeastern China Using Landsat Time—Series Data and Machine Learning. Remote Sensing , 13(4), 792. doi:

Sachdeva, S., Bhatia, T., Verma, A.K. (2018). GIS—based evolutionary optimized Gradient Boosted Decision Trees for forest fire susceptibility mapping. Natural Hazards, 92(3), pp. 1399–1418. DOI:

Sakr, G.E., Elhajj, I.H., Mitri, G.H. (2011). Efficient forest fire occurrence prediction for developing countries using two weather parameters. Engineering Applications of Artificial Intelligence, 24(5), pp. 888–894. DOI:

Shi, S., Yao, C., Wang, S., Han, W. (2018). A Model Design for Risk Assessment of Line Tripping Caused by Wildfires. Sensors, 18(6):1941. DOI:

Venkatesh, K., Preethi, K., Ramesh, H. (2020). Evaluating the effects of forest fire on water balance using fire susceptibility maps. Ecological Indicators, 110, 105856. doi:

Xufeng, L., Zhongyuan, L., Wenjing, C., Xueying, S. (2023). Forest Fire Prediction Based on Long- and Short-Term Time-Series Network. Forests, 14(4), 778. doi:

Yongqi, P., Yudong, L., Zhongke, F., Zemin, F., Ziyu, Z., Shilin, C. , Hanyue, Z. (2022). Forest Fire Occurrence Prediction in China Based on Machine Learning Methods. Remote Sensing, 14(21), 5546. doi:






Earth observation data applications: Challenges and tasks