Hybrid ML predicts rare aircraft landing safety events

Researchers have developed a hybrid machine learning framework to predict rare safety events during aircraft landing phases using imbalanced flight data. The system combines a long short-term memory (LSTM) autoencoder to identify deviations from normal flight behavior with statistical flight-history features. This fused data is then fed into a class-weighted XGBoost classifier, achieving a mean macro recall above 0.90 across multiple airports. The study highlights the importance of class weighting and demonstrates the framework's interpretability by associating predictions with relevant operational variables. AI

IMPACT Enhances safety in aviation by improving the detection of rare critical events during aircraft landings.

RANK_REASON Academic paper detailing a novel machine learning methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• CatalyzeX
• DagsHub
• DASHlink
• Gotit.pub
• Hugging Face
• long short-term memory
• Nasa
• ScienceCast
• XGBoost

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →