Risk Warning Model for Railway Meteorological Disasters Based on Random Forest and XGBoost

View at publisher Summarise with VIRAT
Authors: Yan Dong, Jingjing Min, Feng Xiao, Peng He
Cited by: 0
References: 2

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper focuses on railway meteorological disasters, thoroughly analyzing the impact mechanisms of common meteorological events (such as heavy rain and strong winds) on railway infrastructure and operational safety. By employing machine learning and statistical methods, we construct precise risk assessment and early warning models. Through in-depth analysis of historical meteorological and railway operation data, we quantify the complex relationship between meteorological factors and railway delays, determining risk thresholds for different meteorological disasters. The results indicate that the model can effectively identify high-risk sections and time periods, providing data support for railway authorities to develop scientific disaster prevention and reduction strategies. This has significant practical implications for enhancing the railway's ability to respond to meteorological disasters and ensuring the safety of railway transportation.

Fields of Study & Subjects

Transportation Systems and Safety Infrastructure Resilience and Vulnerability Analysis Evaluation and Optimization Models

Publication details

Journal / source
IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
Pages
1684–1691
Publication date
28 January 2026
Language
EN