ASCNet: Research on all-sky camera images classification at the Muztagh-ata site

TL;DR

This paper introduces ASCNet, a novel deep learning model combining ResNet34 and specialized modules to accurately classify all-sky camera images for cloud coverage analysis at the Muztagh-ata site, achieving over 92% accuracy.

Contribution

The paper presents ASCNet, an innovative model with a unique architecture for nighttime all-sky camera image classification, demonstrating superior performance over existing models.

Findings

Achieved 92.66% accuracy in image classification

Model outperforms other models in ablation and comparison tests

Demonstrated strong generalization ability for astronomical image analysis

Abstract

Cloud coverage is one of the crucial elements of site testing in astronomy. All-sky camera (ASC) images are beneficial for our research on cloud coverage. In this paper, we propose ASCNet, an innovative model specifically designed for classifying nighttime ASC images collected at the Muztagh-ata site from 2022 March to 2024 June. ASCNet integrates ResNet34 with an ASCModule, which employs Depthwise Dilated Convolution and embeds lightweight Squeeze-and-Excitation attention within its branches to extract fine-grained texture information from the luminance channel. The data set is partitioned by category, with 70% of images assigned to the training set and 30% to the test set. The model's performance is assessed by comparing its predictions on the test set with manually annotated labels, yielding a consistency rate of 92.7%. All evaluation metrics of ASCNet are as follows: Accuracy 92.66%, Precision 83.26%, Recall 84.25%, and F1-Score 83.67%, and both ablation and comparative experiments demonstrate significant superiority over other models. A confusion matrix is utilized to analyze the differences between manual classification and model classification. The statistical results demonstrate the model's excellent classification performance and its robust generalization ability, illustrating that ASCNet has potential for application in future astronomical image classifications.