Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification
More than 60 percent of the global surface is covered by clouds, and they play a vital role in the hydrological circle, climate change, and radiation budgets by modifying shortwaves and longwave. Weather forecast reports are critical to areas such as air and sea transport, energy, agriculture, and t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/14/2/280 |
| _version_ | 1797622413551206400 |
|---|---|
| author | Emmanuel Kwabena Gyasi Purushotham Swarnalatha |
| author_facet | Emmanuel Kwabena Gyasi Purushotham Swarnalatha |
| author_sort | Emmanuel Kwabena Gyasi |
| collection | DOAJ |
| description | More than 60 percent of the global surface is covered by clouds, and they play a vital role in the hydrological circle, climate change, and radiation budgets by modifying shortwaves and longwave. Weather forecast reports are critical to areas such as air and sea transport, energy, agriculture, and the environment. The time has come for artificial intelligence-powered devices to take the place of the current method by which decision-making experts determine cloud types. Convolutional neural network models (CNNs) are starting to be utilized for identifying the types of clouds that are caused by meteorological occurrences. This study uses the publicly available Cirrus Cumulus Stratus Nimbus (CCSN) dataset, which consists of 2543 ground-based cloud images altogether. We propose a model called Cloud-MobiNet for the classification of ground-based clouds. The model is an abridged convolutional neural network based on MobileNet. The architecture of Cloud-MobiNet is divided into two blocks, namely the MobileNet building block and the support MobileNet block (SM block). The MobileNet building block consists of the weights of the depthwise separable convolutions and pointwise separable convolutions of the MobileNet model. The SM block is made up of three dense network layers for feature extraction. This makes the Cloud-MobiNet model very lightweight to be implemented on a smartphone. An overall accuracy success of 97.45% was obtained for the CCSN dataset used for cloud-type classification. Cloud-MobiNet promises to be a significant model in the short term, since automated ground-based cloud classification is anticipated to be a preferred means of cloud observation, not only in meteorological analysis and forecasting but also in the aeronautical and aviation industries. |
| first_indexed | 2024-03-11T09:10:58Z |
| format | Article |
| id | doaj.art-5e015b674b9f4da6bfdc2687e9b63163 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-11T09:10:58Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-5e015b674b9f4da6bfdc2687e9b631632023-11-16T19:02:38ZengMDPI AGAtmosphere2073-44332023-01-0114228010.3390/atmos14020280Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud ClassificationEmmanuel Kwabena Gyasi0Purushotham Swarnalatha1School of Computer Science and Engineering, VIT University, Vellore 632014, IndiaSchool of Computer Science and Engineering, VIT University, Vellore 632014, IndiaMore than 60 percent of the global surface is covered by clouds, and they play a vital role in the hydrological circle, climate change, and radiation budgets by modifying shortwaves and longwave. Weather forecast reports are critical to areas such as air and sea transport, energy, agriculture, and the environment. The time has come for artificial intelligence-powered devices to take the place of the current method by which decision-making experts determine cloud types. Convolutional neural network models (CNNs) are starting to be utilized for identifying the types of clouds that are caused by meteorological occurrences. This study uses the publicly available Cirrus Cumulus Stratus Nimbus (CCSN) dataset, which consists of 2543 ground-based cloud images altogether. We propose a model called Cloud-MobiNet for the classification of ground-based clouds. The model is an abridged convolutional neural network based on MobileNet. The architecture of Cloud-MobiNet is divided into two blocks, namely the MobileNet building block and the support MobileNet block (SM block). The MobileNet building block consists of the weights of the depthwise separable convolutions and pointwise separable convolutions of the MobileNet model. The SM block is made up of three dense network layers for feature extraction. This makes the Cloud-MobiNet model very lightweight to be implemented on a smartphone. An overall accuracy success of 97.45% was obtained for the CCSN dataset used for cloud-type classification. Cloud-MobiNet promises to be a significant model in the short term, since automated ground-based cloud classification is anticipated to be a preferred means of cloud observation, not only in meteorological analysis and forecasting but also in the aeronautical and aviation industries.https://www.mdpi.com/2073-4433/14/2/280Cloud-MobiNetremote sensingartificial intelligenceconvolutional neural networkclimate changemachine learning |
| spellingShingle | Emmanuel Kwabena Gyasi Purushotham Swarnalatha Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification Atmosphere Cloud-MobiNet remote sensing artificial intelligence convolutional neural network climate change machine learning |
| title | Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification |
| title_full | Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification |
| title_fullStr | Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification |
| title_full_unstemmed | Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification |
| title_short | Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification |
| title_sort | cloud mobinet an abridged mobile net convolutional neural network model for ground based cloud classification |
| topic | Cloud-MobiNet remote sensing artificial intelligence convolutional neural network climate change machine learning |
| url | https://www.mdpi.com/2073-4433/14/2/280 |
| work_keys_str_mv | AT emmanuelkwabenagyasi cloudmobinetanabridgedmobilenetconvolutionalneuralnetworkmodelforgroundbasedcloudclassification AT purushothamswarnalatha cloudmobinetanabridgedmobilenetconvolutionalneuralnetworkmodelforgroundbasedcloudclassification |