eprintid: 17766
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/77/66
datestamp: 2023-12-19 03:24:05
lastmod: 2023-12-19 03:24:05
status_changed: 2023-12-19 03:08:39
type: article
metadata_visibility: show
creators_name: Umair, M.
creators_name: Hashmani, M.A.
title: A Visual-Range Cloud Cover Image Dataset for Deep Learning Models
ispublished: pub
keywords: Cost effectiveness; Costs; Deep learning; Offshore oil well production; Offshore structures; Statistical tests, Cloud cover; Cover-image; Dataset; Efficientnet-b0; Environmental conditions; Googlenet; Image datasets; Learning models; Resnet-50; Visual range, Classification (of information)
note: cited By 0
abstract: Coastal and offshore oil and gas structures and operations are subject to continuous exposure to environmental conditions (ECs) such as varying air and water temperatures, rough sea conditions, strong winds, high humidity, rain, and varying cloud cover. To monitor ECs, weather and wave sensors are installed on these facilities. However, the capital expenditure (CAPEX) and operational expenses (OPEX) of these sensors are high, especially for offshore structures. For observable ECs, such as cloud cover, a cost-effective deep learning (DL) classification model can be employed as an alternative solution. However, to train and test a DL model, a cloud cover image dataset is required. In this paper, we present a novel visual-range cloud cover image dataset for cloud cover classification using a deep learning model. Various visual-range sky images are captured on nine different occasions, covering six cloud cover conditions. For each cloud cover condition, 100 images are manually classified. To increase the size and quality of images, multiple label-preserving data augmentation techniques are applied. As a result, the dataset is expanded to 9,600 images. Moreover, to evaluate the usefulness of the proposed dataset, three DL classification models, i.e., GoogLeNet, ResNet-50, and EfficientNet-B0, are trained, tested, and their results are presented. Even though EfficientNet-B0 had better generalization ability and marginally higher classification accuracy, it was discovered that ResNet-50 is the best choice for cloud cover classification due to its lower computational cost and competitive classification accuracy. Based on these results, it is concluded that the proposed dataset can be used in further research in DL-based cloud cover classification model development © 2022,International Journal of Advanced Computer Science and Applications.All Rights Reserved
date: 2022
publisher: Science and Information Organization
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124000490&doi=10.14569%2fIJACSA.2022.0130166&partnerID=40&md5=9f8f50eb37bb18c9a45310e03e5c3d84
id_number: 10.14569/IJACSA.2022.0130166
full_text_status: none
publication: International Journal of Advanced Computer Science and Applications
volume: 13
number: 1
pagerange: 534-541
refereed: TRUE
issn: 2158107X
citation:   Umair, M. and Hashmani, M.A.  (2022) A Visual-Range Cloud Cover Image Dataset for Deep Learning Models.  International Journal of Advanced Computer Science and Applications, 13 (1).  pp. 534-541.  ISSN 2158107X