Geographic Transferability of Machine Learning Models for Short-Term Airport Fog Forecasting
This addresses the challenge of location-specific failures in machine learning models for airport fog forecasting, offering a transferable tool for aviation safety, though it is incremental in its feature engineering approach.
This study tackled the problem of geographic generalization in short-term airport fog forecasting by developing a coordinate-free feature set based on thermodynamic and radiative processes, achieving AUC values of 0.923-0.947 across distances up to 11,650 km in zero-shot tests at multiple airports.
Short-term forecasting of airport fog (visibility < 1.0 km) presents challenges in geographic generalization because many machine learning models rely on location-specific features and fail to transfer across sites. This study investigates whether fundamental thermodynamic and radiative processes can be encoded in a coordinate-free (location-independent) feature set to enable geographic transferability. A gradient boosting classifier (XGBoost) trained on Santiago, Chile (SCEL, 33S) data from 2002-2009 was evaluated on a 2010-2012 holdout set and under strict zero-shot tests at Puerto Montt (SCTE), San Francisco (KSFO), and London (EGLL). The model achieved AUC values of 0.923-0.947 across distances up to 11,650 km and different fog regimes (radiative, advective, marine). Consistent SHAP feature rankings show that visibility persistence, solar angle, and thermal gradients dominate predictions, suggesting the model learned transferable physical relationships rather than site-specific patterns. Results suggest that physics-informed, coordinate-free feature engineering can yield geographically transferable atmospheric forecasting tools.