AIR-VIEW: The Aviation Image Repository for Visibility Estimation of Weather, A Dataset and Benchmark

TL;DR

This paper introduces AIR-VIEW, a comprehensive aviation image dataset for visibility estimation, along with benchmark results using common machine learning approaches, addressing the lack of publicly available aviation visibility datasets.

Contribution

It provides a new, large-scale dataset from FAA weather cameras and establishes benchmark results for visibility estimation using multiple approaches.

Findings

The dataset enables supervised learning for aviation visibility estimation.

Benchmark results demonstrate the effectiveness of common approaches on the new dataset.

Comparison against ASTM standard shows competitive performance.

Abstract

Machine Learning for aviation weather is a growing area of research for providing low-cost alternatives for traditional, expensive weather sensors; however, in the area of atmospheric visibility estimation, publicly available datasets, tagged with visibility estimates, of distances relevant for aviation, of diverse locations, of sufficient size for use in supervised learning, are absent. This paper introduces a new dataset which represents the culmination of a year-long data collection campaign of images from the FAA weather camera network suitable for this purpose. We also present a benchmark when applying three commonly used approaches and a general-purpose baseline when trained and tested on three publicly available datasets, in addition to our own, when compared against a recently ratified ASTM standard.