Abstract:Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data.
| Comments: | Published in Theoretical and Applied Climatology |
| Subjects: | Atmospheric and Oceanic Physics (physics.ao-ph); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG) |
| MSC classes: | 68T05, 62M45, 62P12, 86A10 |
| ACM classes: | I.2.6; I.5.2; J.2 |
| Cite as: | arXiv:2605.21507 [physics.ao-ph] |
| (or arXiv:2605.21507v1 [physics.ao-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21507 arXiv-issued DOI via DataCite |
|
| Journal reference: | Theoretical and Applied Climatology, vol. 157, art. no. 283, 2026 |
| Related DOI: | https://doi.org/10.1007/s00704-026-06219-6
DOI(s) linking to related resources |
From: Bong Gyun Shin [view email]
[v1]
Sat, 9 May 2026 16:58:22 UTC (11,179 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。