Saved in:
Bibliographic Details
Main Authors: Shin, Bong Gyun, Lee, Chan Sik, Suh, Hyesun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.21507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917517965918208
author Shin, Bong Gyun
Lee, Chan Sik
Suh, Hyesun
author_facet Shin, Bong Gyun
Lee, Chan Sik
Suh, Hyesun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21507
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
Shin, Bong Gyun
Lee, Chan Sik
Suh, Hyesun
Atmospheric and Oceanic Physics
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
68T05, 62M45, 62P12, 86A10
I.2.6; I.5.2; J.2
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.
title Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
topic Atmospheric and Oceanic Physics
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
68T05, 62M45, 62P12, 86A10
I.2.6; I.5.2; J.2
url https://arxiv.org/abs/2605.21507