Development of Avalanche Prediction Algorithms Based on a Set of Parameters

Natalya Denissova, Olga Petrova, Е.М. Федькин, Gulzhan Daumova, Evgeny Sergazinov

Journal of Advances in Information Technology, 2025

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.12720/jait.16.6.904-915
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This article presents the results of a study conducted to develop an avalanche predictive model based on a set of climatic data.The research area includes the territory of East Kazakhstan, where a sharply continental climate prevails with hot summers and cold and snowy winters.With climate change, despite the low altitudes in this mountainous area, the problem of avalanche safety is acute in the region.To compile a avalanche predictive model, meteorological data from regional weather stations for 23 years (2001-2024) and meteorological observations in avalanche-prone areas for 19 years (2005-2024) were analyzed.This information was compared with the recorded data on spontaneous avalanches over the past 11 years (2013-2024).A database was created to carry out the research.The meteorological data is analyzed using mathematical statistics methods with the construction of probable trends of regional climatic changes.MATLAB data analysis has shown a significant relationship between sudden warming, increased wind speed, and precipitation that precedes avalanches.The analysis showed the need to take these parameters into account when developing a forecast model, as the likelihood of dangerous weather events will increase every year.The avalanche prediction was performed using regression analysis (logistic regression).The Loginom Community statistical software package is used for this purpose.The quality of the constructed predictive model was assessed.In the future, it will be used to predict spontaneous avalanche based on observations of meteorological data in avalanche-prone areas of the East Kazakhstan region.