Implementation of a neural network model in the Statistica 12 for mudflow frequency forecasting

The article describes some principles of operation of an artificial neural network. It provides an example of implementing a neural network model by selecting its best architecture using the Statistica 12 software package. The article considers a method for neural network forecasting of a series of mudflow events based on nonlinear relationships with precipitation and temperature series. To solve the problem, the Data Mining (intelligent data analysis) block – Neural Networks was used in the Statistica 12 package. A multilayer perceptron (MLP) was chosen as a neural network method, and a hyperbolic tangent (tanh) was used as an activation function. Based on deep learning algorithms, a mathematical model MPL 2-50-1 was developed, which is capable of learning on the used data (precipitation, temperature, number of mudflows for the period 1953-2015) and forecasting the number of mudflows based on the meteorological parameters (precipitation, temperature) entered into the model. It was found that with average precipitation values of more than 110 mm in the period from May to September from 2016 to 2034, the number of mudflows is predicted to be from 10 to 13, which is higher than their average value of n = 8 for the period with actual initial data from 1953 to 2015. Trends in the number of mudflows in the Terskol Gorge in the warm season from 1953 to 2015 (the period with actual data) and from 2016 to 2034 (the period with predicted data) were determined using polynomial and linear trends. It follows from the linear trend equation that, on average, over the entire period, including the predicted one, the number of mudflows tends to grow slightly by 0.3/10 years. The polynomial trend demonstrates an increase and decrease in the number of mudflows at different time intervals. In the forecast interval of 2016-2034, the decrease in the number of mudflows demonstrates both a polynomial trend and a linear trend.

1. Soldatenko SA. Artificial intelligence and its application in numerical weather forecasting problems. Meteorologiya i Gi-drologiya. 2024;(4):5-27. (In Russ.).

2. Sumachev AE, Banshchikova LS, Griga SA. Application of artificial neural network training methods in forecasting higher water levels using the example of the rivers of the Dvina-Pechora basin district. Meteorologiya i Gidrologiya. 2024;(4):104-115. (In Russ.).

3. Ashabokov BA, Tashilova AA, Kesheva LA, Teunova NV. Sinusoidal regression model for assessing the dynamics of mudflows. Science. Innovations. Technologies. 2024;(3):71-94. (In Russ.). https://doi.org/10.37493/2308-4758.2024.3.4

4. Zolina OG, Bulygina ON. Modern climatic variability of characteristics of extreme precipitation in Russia. Fundamental and Applied Climatology. 2016;(1):84-103. (In Russ.).

5. Ashabokov BA, Tashilova AA, Kesheva LA, Teunova NV. Analysis of climate change in the Caucasus region: the end of the 20th - the beginning of the 21st century. CLIMATE. Special issue: Climate Variability and Change in the 21st Century. CLIMATE. 2019;7(11):1-15. https://doi.org/10.3390/cli7010011

6. Yun W-T, Krishnamurti TN. Linear and non-linear multi-model superensemble prediction model. Atmosphere, 2002;12(3):26-31.

7. Kondratieva NV. Distribution and features of manifestation of mudflow processes on the northern and southwestern slopes of the Greater Caucasus. dissertation of dr. of geogr. sciences. Nalchik. 2018. 402 p. (In Russ.).

8. Tashilova AA, Fedchenko LM, Zalikhanov MCh, Kondratieva NV. Analysis of mudflow dynamics against the background of climate change in the high-mountain zone of Kabardino-Balkaria. Science. Innovations. Technologies. 2024;(1):69-90. (In Russ.). https://doi.org/10.37493/2308-4758.2024.14

9. Neural networks. STATISTICA Neural Networks. Methodology and technologies of modern data analysis. Ed. V.P. Borovikov. 2nd ed. Telecom; 2008. 392 p. (In Russ.).

10. Electronic textbook on statistics. Available from: http://statsoft.ru/home/textbook/default.htm [Accessed 27 June 2024]. (In Russ.).

11. Filatova TV. Application of neural networks for data approximation. Tomsk State University Journal. 2004;(284):121-125. (In Russ.).

12. Khaikin S. Neural networks: full course. 2nd ed.: trans. from English. Moscow: Williams Publishing House; 2006. 1104 p. (In Russ.).

13. Golyandina NE. The Caterpillar-SSA Method. Time Series Analysis. SPb: SPbSU Publishing House; 2004. 76 p. (In Russ.).

14. Golyandina NE. The Caterpillar-SSA Method. Time Series Forecast. SPb: SPbSU Publishing House; 2004. 52 p. (In Russ.).

15. Golyandina N, Nekrutkin V, Zhigljansky A. Analysis of Time Series Structure/ SSA and Related Techniques. London Chapman & Hall/CRC; 2001.305 p.