Fusing Deep Learning and Gradient Boosting for Robust Minute-Level Atmospheric Visibility Nowcasting

Atmospheric visibility nowcasting is vital for safety-critical operations but remains challenging due to complex atmospheric dynamics. We propose a compact stacking ensemble merging a multilayer perceptron (MLP) and gradient-boosted regression trees (GBRT). The model, trained on seven months of minute-scale resolution data with a variability-adaptive filter to suppress sensor noise, employs cross-validation. Results demonstrate that the ensemble achieves its peak performance in the operationally critical low-visibility regime (V < 5 km). This range is particularly significant as it encompasses the Category I and II (CAT I/II) operational thresholds defined by the World Meteorological Organization (WMO) for aviation and surface transportation safety. In this regime, the ensemble yields an R2 of 0.82 and an MAE≈385 m, significantly outperforming single learners during rapid weather transitions. Conversely, in the high-visibility regime (V > 20 km), the explanatory power decreases (R2 of 0.46) due to inherent forward-scattering sensor uncertainties and low aerosol concentrations. Despite these range-specific physical limitations, the model maintains high robustness with narrowly centered residuals. This efficient approach, utilizing cost-effective in situ sensors, is highly suitable for airport and road-weather applications and offers strong potential for multi-site scalability.