Deep learning models for visibility forecasting using climatological data

Low visibility conditions affect safety and traffic operations, leading to adverse scenarios that often result in serious accidents. Due to the complexity and variability associated with modeling weather variables, visibility forecasting remains a highly challenging task and a matter of significant interest for transportation agencies nationwide. Given that the literature on single-step visibility forecasting is very scarce, this study explores the use of deep learning models for single-step visibility forecasting using time series climatological data. Five different deep learning models were developed, trained, and tested using data from two weather stations located in the US state of Florida, which is one of the top states nationwide dealing with low visibility problems. The authors provide discussions of the models' results and areas for future research. (c) 2022 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.

Automated summary

Low visibility conditions have negative impacts on safety and traffic operations, leading to serious accidents. Due to the complexity and variability of weather variables, visibility forecasting is a challenging task for transportation agencies. This study explores the application of deep learning models using time series climatological data for single-step visibility forecasting. Five different deep learning models were developed, trained, and tested using data from weather stations in Florida, which is one of the states heavily affected by low visibility problems. The authors discuss the results of the models and suggest future research directions.