Voting in Transfer Learning System for Ground-Based Cloud Classification

Mario Manzo,Simone Pellino

doi:10.3390/make3030028

Mario Manzo, Simone Pellino

Open Access

https://doi.org/10.3390/make3030028

Copy DOI

Abstract

Cloud classification is a great challenge in meteorological research. The different types of clouds, currently known and present in our skies, can produce radioactive effects that impact the variation of atmospheric conditions, with consequent strong dominance over the earth’s climate and weather. Therefore, identifying their main visual features becomes a crucial aspect. In this paper, the goal is to adopt pretrained deep neural networks-based architecture for clouds image description, and subsequently, classification. The approach is pyramidal. Proceeding from the bottom up, it partially extracts previous knowledge of deep neural networks related to original task and transfers it to the new task. The updated knowledge is integrated in a voting context to provide a classification prediction. The framework trains the neural models on unbalanced sets, a condition that makes the task even more complex, and combines the provided predictions through statistical measures. An experimental phase on different cloud image datasets is performed, and the results achieved show the effectiveness of the proposed approach with respect to state-of-the-art competitors.

Highlights

Extr. 2021, 3, 542–553. https://Clouds are a constant presence in our skies; combined with the role assumed by ecosystems, they are important in determining the atmospheric conditions, hours of sunshine and temperature
With the purpose of addressing the above problems, we present a framework based on deep transfer and voting learning for cloud image classification
With the purpose of producing compliant performance, the settings reported in recent cloud classification methods are adopted

Summary

Introduction

Clouds are a constant presence in our skies; combined with the role assumed by ecosystems, they are important in determining the atmospheric conditions, hours of sunshine and temperature. Dynamic atmospheric conditions, attributed to climate change, have led to an increase in attention to the behavior of clouds [1]. Climate models allow to predict climate changes, but their precision degree is currently insufficient and attributable to alteration in the conditions determined by different phenomena. Cloud behavior prediction is important for estimating climate change. The visual information contained in the image is unable to accurately describe the clouds, due to the large variations in appearance. The non-visual features, known as multimodal information, obtainable from the cloud process formation, such as temperature, humidity, pressure and wind speed, can be of help

Methods

Results

Discussion

Conclusion