A Convolutional Neural Network Approach for Estimating Tropical Cyclone Intensity Using Satellite-based Infrared Images

Combinido, Jay Samuel; Mendoza, J.; Aborot, Jeffrey

doi:10.1109/icpr.2018.8545593

Cited by 45 publications

(27 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Boyo Chen et al [14], [24] presented a rotation-blended CNNs for the TC intensity regression model based on water vapor, passive micro-wave rain rate and infrared data. Combinido et al [25] migrated the pretrained VGG19 on ImageNets to the TC intensity estimation and obtained the RMSE of 13.23 kts only from the infrared cloud image of the TC obtained from the stationary satellite. Wimmers et al [26], [27] mixed and analyzed passive microwave images from different frequency bands for different levels of TCs.…”

Section: Related Workmentioning

confidence: 99%

A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry

et al. 2020

View full text Add to dashboard Cite

Accurate estimation of tropical cyclone (TC) intensity is the key to understanding and forecasting the behavior of TC and is crucial for initialization in forecast models and disaster management in the meteorological industry. TC intensity estimation is a challenge because it requires domain knowledge to manually extract TC cloud structure features and form various sets of parameters obtained from satellites. In this paper, a novel hybrid model is proposed based on convolutional neural networks (CNNs) for TC intensity estimation with satellite remote sensing. According to the intensity of TCs, we divide them into three types and use three different models for intensity regression, respectively. The results show that the use of piecewise thinking can improve the model's fitting speed on small samples. A classification network is provided to classify unlabeled TC samples before TC regression, whose results would determine which regression network to estimate these samples. Finally, the estimation values are sent to the backpropagation (BP) neural network to fit the suitable intensity values. Experimental results demonstrate that our model achieves high accuracy and low root-mean-square error (RMSE up to 8.91 kts) by just using inferred images. INDEX TERMS Convolutional neural networks, hybrid model, tropical cyclone intensity estimation, infrared imagery.

show abstract

Section: Related Workmentioning

confidence: 99%

A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Previous studies on estimating TC intensity using satellite data have used long-wavelength infrared images at about 11 µm, which can be used to observe the cloud top pattern. The studies have typically used 2D-CNN models to analyze single-spectral TC images [17,18]. In this study, we used multi-spectral infrared images from short-wavelength at 3.7 µm to long-wavelength at 12.0 µm that were derived from a meteorological satellite sensor in a multi-dimensional CNN framework.…”

Section: Convolutional Neural Network (Cnns)mentioning

confidence: 99%

“…Pradhan et al [17] estimated the intensity of TCs using single IR images based on CNNs, resulting in an RMSE of 10.18 kts. Combinido et al [18] adopted the Visual Geometry Group 19-layer (VGG19) model for estimating TC intensity, which is a well-performing 2D-CNN architecture for image analysis proposed by Simonyan et al [19]. They used single IR TC images from multiple geostationary satellite sensors from 1996 to 2016 over the Western North Pacific to develop the model, resulting in an RMSE of 13.23 kts.…”

Section: Introductionmentioning

confidence: 99%

Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks from Geostationary Satellite Data

Lee

Cha

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

For a long time, researchers have tried to find a way to analyze tropical cyclone (TC) intensity in real-time. Since there is no standardized method for estimating TC intensity and the most widely used method is a manual algorithm using satellite-based cloud images, there is a bias that varies depending on the TC center and shape. In this study, we adopted convolutional neural networks (CNNs) which are part of a state-of-art approach that analyzes image patterns to estimate TC intensity by mimicking human cloud pattern recognition. Both two dimensional-CNN (2D-CNN) and three-dimensional-CNN (3D-CNN) were used to analyze the relationship between multi-spectral geostationary satellite images and TC intensity. Our best-optimized model produced a root mean squared error (RMSE) of 8.32 kts, resulting in better performance (~35%) than the existing model using the CNN-based approach with a single channel image. Moreover, we analyzed the characteristics of multi-spectral satellite-based TC images according to intensity using a heat map, which is one of the visualization means of CNNs. It shows that the stronger the intensity of the TC, the greater the influence of the TC center in the lower atmosphere. This is consistent with the results from the existing TC initialization method with numerical simulations based on dynamical TC models. Our study suggests the possibility that a deep learning approach can be used to interpret the behavior characteristics of TCs.

show abstract

“…Convolutional neural networks (CNN) are the class of neural networks designed to process images and have been used for TC intensity estimates (Pradhan et al, 2017;Lee et al, 2020;B. Chen et al, 2019;Wimmers et al, 2019;Combinido et al, 2018;R. Chen et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Using Video Recognition to Identify Tropical Cyclone Positions

Smith

Toumi

2021

Geophysical Research Letters

View full text Add to dashboard Cite

Tropical cyclone (TC) center fixing is a challenge for improving forecasting and establishing TC climatologies. We propose a novel objective solution through the use of video recognition algorithms. The videos of tropical cyclones in the Western North Pacific are of sequential, hourly, geostationary satellite infra-red (IR) images. A variety of convolutional neural network architectures are tested. The best performing network implements convolutional layers; a convolutional long short-term memory layer; and fully connected layers. Cloud features rotating around a center are effectively captured in this video-based technique. Networks trained with long-wave IR channels outperform a water vapour channel based network. The average position across the two IR networks has a 19.3 km median error across all intensities. This equates to a 42% lower error over a baseline technique. This video based method combined with the high geostationary satellite sampling rate can provide rapid and accurate automated updates of TC centers.

show abstract

A Convolutional Neural Network Approach for Estimating Tropical Cyclone Intensity Using Satellite-based Infrared Images

Cited by 45 publications

References 21 publications

A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry

A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry

Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks from Geostationary Satellite Data

Using Video Recognition to Identify Tropical Cyclone Positions

Contact Info

Product

Resources

About