EUVIMEDEUVIMED entdecken
Crossref

A Novel CNN Approach to Identify Cyclones using the MN-Net Framework

Dhanalakshmi, Ravikanth Garladinne, Ummadi Janardhan Reddy, Lakshmikantha Reddy, E. R. Aruna, Venkata Sai Manoj Edula

Pertanika Journal of Science and Technology · 24.07.2026 · 34 (S1)

DOI: 10.47836/pjst.34.s1.08 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pertanika Journal of Science and Technology, online erschienen am 24.07.2026. Verfasst von Dhanalakshmi und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cyclone detection is a critical task in meteorology for minimising the impact of extreme weather events. Traditional approaches rely on satellite observations and numerical weather prediction models, which often lack efficiency in real-time detection. In this study, we propose MN-Net, a stacked ensemble deep learning framework that integrates MobileNet and NASNet architectures for cyclone image classification. The model leverages transfer learning and feature-level fusion to enhance classification performance. We provide the community with a large dataset of labelled images of cyclones and non-cyclones and additionally augment our training set with data augmentation techniques to enhance the network’s ability to generalise. Our experimental results highlight the supremacy of MN-Net in terms of accuracy, precision, recall and F1-score over strong baseline models. The overall architecture is suitable for integration into early warning systems for timely cyclone detection and warning dissemination.

Zitieren

APA

Dhanalakshmi, Garladinne, R., Reddy, U. J., Reddy, L., Aruna, E. R., & Edula, V. S. M. (2026). A Novel CNN Approach to Identify Cyclones using the MN-Net Framework. Pertanika Journal of Science and Technology, 34(S1). https://doi.org/10.47836/pjst.34.s1.08

Vancouver

Dhanalakshmi, Garladinne R, Reddy UJ, Reddy L, Aruna ER, Edula VSM. A Novel CNN Approach to Identify Cyclones using the MN-Net Framework. Pertanika Journal of Science and Technology. 2026;34(S1). doi:10.47836/pjst.34.s1.08

BibTeX
@article{Dhanalakshmi2026,
  author = {Dhanalakshmi and Garladinne, Ravikanth and Reddy, Ummadi Janardhan and Reddy, Lakshmikantha and Aruna, E. R. and Edula, Venkata Sai Manoj},
  title = {A Novel CNN Approach to Identify Cyclones using the MN-Net Framework},
  journal = {Pertanika Journal of Science and Technology},
  year = {2026},
  volume = {34},
  number = {S1},
  doi = {10.47836/pjst.34.s1.08}
}
Kostenlos starten →