2018
DOI: 10.1186/s40645-018-0245-y
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model

Abstract: We propose a deep learning approach for identifying tropical cyclones (TCs) and their precursors. Twenty year simulated outgoing longwave radiation (OLR) calculated using a cloud-resolving global atmospheric simulation is used for training two-dimensional deep convolutional neural networks (CNNs). The CNNs are trained with 50,000 TCs and their precursors and 500,000 non-TC data for binary classification. Ensemble CNN classifiers are applied to 10 year independent global OLR data for detecting precursors and TC… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
54
0
2

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 84 publications
(59 citation statements)
references
References 28 publications
0
54
0
2
Order By: Relevance
“…CNN could successfully cope with the task with high accuracy. CNN also has been employed by Matsuoka et al[72] who developed a CNN technique for the estimation of tropical cyclones. The training process was performed in the presence of longwave radiation outgoing during twenty-year simulation which has been calculated by employing a cloud-resolving global atmospheric simulation.…”
mentioning
confidence: 99%
“…CNN could successfully cope with the task with high accuracy. CNN also has been employed by Matsuoka et al[72] who developed a CNN technique for the estimation of tropical cyclones. The training process was performed in the presence of longwave radiation outgoing during twenty-year simulation which has been calculated by employing a cloud-resolving global atmospheric simulation.…”
mentioning
confidence: 99%
“…Several promising studies using AI for TC detection and prediction have already been published (e.g. Jin et al, 2008;Loridan et al, 2017;Mercer and Grimes, 2017;Matsuoka et al, 2018;Wimmers et al, 2019). One can hope that a continuing improvement of AI technology can be harnessed to enhance high-impact weather forecasting in regions with a vulnerable population, including south-eastern Africa.…”
Section: Discussionmentioning
confidence: 99%
“…B. die El-Niño-oder La-Niña-Phänomene. Matsuoka et al nutzen beispielsweise Deep Learning, um tropische Wirbelstürme und deren Vorläufer zu detektieren, wodurch die Frühwarnung vor diesen Ereignissen verbessert werden kann [20]. Das System ist dabei sogar in der Lage, mit einer 75 %igen Genauigkeit die Vorläufer solcher tropischen Wirbelstürme bis zu 7 Tage vorher korrekt zu detektieren.…”
Section: Ausblickunclassified