Deep Learning Algorithm for Satellite Imaging Based Cyclone Detection
(2020) In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13. p.827-839- Abstract
Satellite images are primary data in weather prediction modeling. Deep learning-based approach, a viable candidate for automatic image processing, requires large sets of annotated data with diverse characteristics for training purposes. Accuracy of weather prediction improves with data having a relatively dense temporal resolution. We have employed interpolation and data augmentation techniques for enhancement of the temporal resolution and diversifications of characters in a given dataset. Algorithm requires classical approaches during preprocessing steps. Three optical flow methods using 14 different constraint optimization techniques and five error estimates are tested here. The artificially enriched data (optimal combination from... (More)
Satellite images are primary data in weather prediction modeling. Deep learning-based approach, a viable candidate for automatic image processing, requires large sets of annotated data with diverse characteristics for training purposes. Accuracy of weather prediction improves with data having a relatively dense temporal resolution. We have employed interpolation and data augmentation techniques for enhancement of the temporal resolution and diversifications of characters in a given dataset. Algorithm requires classical approaches during preprocessing steps. Three optical flow methods using 14 different constraint optimization techniques and five error estimates are tested here. The artificially enriched data (optimal combination from the previous exercise) are used as a training set for a convolutional neural network to classify images in terms of storm or nonstorm. Several cyclone data (eight cyclone datasets of a different class) were used for training. A deep learning model is trained and tested with artificially densified and classified storm data for cyclone classification and locating the cyclone vortex giving minimum 90% and 84% accuracy, respectively. In the final step, we show that the linear regression method can be used for predicting the path.
(Less)
- author
- Shakya, Snehlata LU ; Kumar, Sanjeev and Goswami, Mayank
- organization
- publishing date
- 2020
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Miscellaneous applications, optical data
- in
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- volume
- 13
- article number
- 8977395
- pages
- 13 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85081653152
- ISSN
- 1939-1404
- DOI
- 10.1109/JSTARS.2020.2970253
- language
- English
- LU publication?
- yes
- id
- 8b2a116a-eb5b-40fa-b77a-a8043b06daf6
- date added to LUP
- 2021-01-11 13:11:40
- date last changed
- 2022-04-26 23:13:55
@article{8b2a116a-eb5b-40fa-b77a-a8043b06daf6,
abstract = {{<p>Satellite images are primary data in weather prediction modeling. Deep learning-based approach, a viable candidate for automatic image processing, requires large sets of annotated data with diverse characteristics for training purposes. Accuracy of weather prediction improves with data having a relatively dense temporal resolution. We have employed interpolation and data augmentation techniques for enhancement of the temporal resolution and diversifications of characters in a given dataset. Algorithm requires classical approaches during preprocessing steps. Three optical flow methods using 14 different constraint optimization techniques and five error estimates are tested here. The artificially enriched data (optimal combination from the previous exercise) are used as a training set for a convolutional neural network to classify images in terms of storm or nonstorm. Several cyclone data (eight cyclone datasets of a different class) were used for training. A deep learning model is trained and tested with artificially densified and classified storm data for cyclone classification and locating the cyclone vortex giving minimum 90% and 84% accuracy, respectively. In the final step, we show that the linear regression method can be used for predicting the path.</p>}},
author = {{Shakya, Snehlata and Kumar, Sanjeev and Goswami, Mayank}},
issn = {{1939-1404}},
keywords = {{Miscellaneous applications; optical data}},
language = {{eng}},
pages = {{827--839}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}},
title = {{Deep Learning Algorithm for Satellite Imaging Based Cyclone Detection}},
url = {{http://dx.doi.org/10.1109/JSTARS.2020.2970253}},
doi = {{10.1109/JSTARS.2020.2970253}},
volume = {{13}},
year = {{2020}},
}