This study investigates teleconnection drivers for heatwave prediction in South Korea using machine learning and explainable AI. The research reveals that snow depth variability in the Gobi Desert and Tianshan Mountains are crucial and predictable drivers, exhibiting high correlation with summer climate teleconnection triggers and regional variabilities. A Light Gradient Boosting Machine (LGBM) model outperforms other methods in predicting heatwave frequency, highlighting the advantages of advanced ML techniques in capturing complex relationships.
Publisher
Nature Communications
Published On
Aug 03, 2024
Authors
Yeonsu Lee, Dongjin Cho, Jungho Im, Cheolhee Yoo, Joonele Lee, Yoo-Geun Ham, Myong-In Lee
Tags
heatwave prediction
machine learning
explainable AI
teleconnection
snow depth variability
climate triggers
Gobi Desert
Related Publications
Explore these studies to deepen your understanding of the subject.
