Early Detection of Flight Accident Risks Through Machine Learning

DOI

https://www.doi.org/10.59256/indjcst.20260501066

Published In

Volume 5, Issue 1 (2026)

Published Online

January-April 2026

Pages

572-575

Article Type

Original Article

Check for updates

Flight safety is increasingly challenged by dynamic operational and environmental conditions, which traditional static risk assessment methods fail to address effectively. This paper presents an AI-powered Flight Accident Prediction and Dynamic Risk Assessment System that leverages a Long Short-Term Memory (LSTM) model to analyze sequential flight parameters in conjunction with real-time weather data. The proposed system captures temporal dependencies in flight data to predict accident risk levels continuously and classifies flights into low, medium, or high-risk categories. By enabling real-time monitoring and early warning capabilities, the system facilitates proactive decision-making for pilots and air traffic controllers. Experimental results demonstrate improved prediction accuracy and timely risk detection compared to conventional methods, thereby contributing to enhanced aviation safety and operational efficiency