Convolutional variational autoencoder for Northeast US coastal wind and flood hazard data augmentation

The coasts of the Northeastern United States experience wind and flood damage as a result of extratropical cyclones (such as Nor’easters). However, recorded data is limited for hazard analysis and resilience evaluation. This paper describes a method that can efficiently augment the time series of ex...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Neural computing & applications Ročník 37; číslo 16; s. 9537 - 9564
Hlavní autoři:	Jia, Yiming, Sasani, Mehrdad
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London Springer London 01.06.2025 Springer Nature B.V
Témata:	Artificial Intelligence Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Cyclones Data augmentation Data Mining and Knowledge Discovery Flood damage Generative adversarial networks Goodness of fit Hazard assessment Image Processing and Computer Vision Machine learning Multivariate analysis Normal distribution Original Article Probability and Statistics in Computer Science Statistical analysis Time measurement Time series Wind damage Wind speed United States > US Data augmentation Extratropical cyclone Wind speed Flood elevation Convolutional variational autoencoder Time series
ISSN:	0941-0643, 1433-3058
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	The coasts of the Northeastern United States experience wind and flood damage as a result of extratropical cyclones (such as Nor’easters). However, recorded data is limited for hazard analysis and resilience evaluation. This paper describes a method that can efficiently augment the time series of extratropical cyclone severity measures (wind speed and flood elevation) by leveraging convolutional variational autoencoders, a deep learning technique. As a generative model, the proposed convolutional variational autoencoder learns the probability distribution of latent features (here, low-dimensional underlying characteristics of the time series) as a multivariate normal distribution. The augmented severity measure time series are then obtained in two steps: (1) randomly sampling data from the learned multivariate normal distribution and (2) using the randomly sampled data as the input to the decoder of the trained convolutional variational autoencoder to generate severity measures. A case study is conducted to evaluate the quality of the augmented wind speed and flood elevation time series of the extratropical cyclones recorded in Boston Harbor (adjacent to the city of Boston, Massachusetts). This study also demonstrates that the proposed method outperforms other established time series data augmentation methods (i.e., Dynamic Time Warping and Conditional Generative Adversarial Network). An application for hazard frequency analysis—modeling the joint probability of wind speed and flood elevation using a Gumbel copula—is also presented. The results demonstrate that the augmented data can significantly reduce the uncertainty of the estimated copula parameter while obtaining a goodness-of-fit metric value (negative log-likelihood) similar to that of the original, non-augmented data. The proposed convolutional variational autoencoder can be used to augment any time series data. The user-friendly codes are published.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0941-0643 1433-3058
DOI:	10.1007/s00521-025-11085-w