Deep Convolutional Activations-Based Features for Ground-Based Cloud Classification

Liu

Geophysical Research Letters

et al. 2018

161

Clouds have an enormous influence on the Earth's energy balance, climate, and weather. Cloud types have different cloud radiative effects, which is an essential indicator of the cloud effect on radiation. Therefore, identifying the cloud type is important in meteorology. In this letter, we propose a new convolutional neural network model, called CloudNet, for accurate ground‐based meteorological cloud classification. We build a ground‐based cloud data set, called Cirrus Cumulus Stratus Nimbus, which consists of 11 categories under meteorological standards. The total number of cloud images is three times that of the previous database. In particular, it is the first time that contrails, a type of cloud generated by human activity, have been taken into account in the ground‐based cloud classification, making the Cirrus Cumulus Stratus Nimbus data set more discriminative and comprehensive than existing ground‐based cloud databases. The evaluation of a large number of experiments demonstrates that the proposed CloudNet model could achieve good performance in meteorological cloud classification.

Section: Datamentioning

confidence: 99%

Section: Ground-based Cloud Databasesmentioning

confidence: 99%

CloudNet: Ground‐Based Cloud Classification With Deep Convolutional Neural Network

Liu

Geophysical Research Letters

et al. 2018

161

“…In this study, we compare our experimental result with all other previous studies that experimented with the same dataset (SWIMCAT). The performance metrics are calculated using confusion matrix data that were published in previous research (in the case of Shi et al [24], the detail confusion matrix data was not provided; only accuracy is compared). The first three papers [20], [16], and [19] applied traditional machine learning approaches and they obtained accuracies of 91.1%, 95.1%, and 98.3%, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Ye et al [22,23] improved feature extraction using a CNN by resorting to the deep convolutional visual features and the Fisher vector and then used an SVM classifier. Shi et al [24] proposed a CNN model to extract features using different pooling strategies and used a multi-label linear SVM classifier. Zhang et al [25] used a trained CNN to extract local features from part summing maps based on feature maps called deep visual information for multi-view ground-based cloud recognition.…”

mentioning

confidence: 99%

A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets

2019

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model.

“…Afterward, they employed Fisher vector encoding to further improve the cloud classification results. Shi et al [25] extracted visual features from both the shallow and deep convolutional layers of the network. They also evaluated the performance of fully connected (FC) layer for cloud classification.…”

Section: Introductionmentioning

confidence: 99%

Deep multimodal fusion for ground-based cloud classification in weather station networks

Liu

Mei

2018

J Wireless Com Network

Most existing methods only utilize the visual sensors for ground-based cloud classification, which neglects other important characteristics of cloud. In this paper, we utilize the multimodal information collected from weather station networks for ground-based cloud classification and propose a novel method named deep multimodal fusion (DMF). In order to learn the visual features, we train a convolutional neural network (CNN) model to obtain the sum convolutional map (SCM) by using a pooling operation across all the feature maps in deep layers. Afterwards, we employ a weighted strategy to integrate the visual features with multimodal features. We validate the effectiveness of the proposed DMF on the multimodal ground-based cloud (MGC) dataset, and the experimental results demonstrate the proposed DMF achieves better results than the state-of-the-art methods.