EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data

Kim VanExel, Samendra Sherchan, Siyan Liu

Journal of Imaging · 24.01.2025 · 11 (2) · 32

DOI: 10.3390/jimaging11020032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 24.01.2025. Verfasst von Kim VanExel und 2 weiteren Autor:innen. Beteiligte Einrichtung: Bioenvironmental Sciences Department, Morgan State University, Baltimore, MD 21251, USA. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Oak Ridge Institute for Science and Education, U.S. Department of Energy’s Omni Technology Alliance Internship Program, US Department of Energy (DOE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research study utilized artificial intelligence (AI) to detect natural disasters from aerial images. Flooding and desertification were two natural disasters taken into consideration. The Climate Change Dataset was created by compiling various open-access data sources. This dataset contains 6334 aerial images from UAV (unmanned aerial vehicles) images and satellite images. The Climate Change Dataset was then used to train Deep Learning (DL) models to identify natural disasters. Four different Machine Learning (ML) models were used: convolutional neural network (CNN), DenseNet201, VGG16, and ResNet50. These ML models were trained on our Climate Change Dataset so that their performance could be compared. DenseNet201 was chosen for optimization. All four ML models performed well. DenseNet201 and ResNet50 achieved the highest testing accuracies of 99.37% and 99.21%, respectively. This research project demonstrates the potential of AI to address environmental challenges, such as climate change-related natural disasters. This study’s approach is novel by creating a new dataset, optimizing an ML model, cross-validating, and presenting desertification as one of our natural disasters for DL detection. Three categories were used (Flooded, Desert, Neither). Our study relates to AI for Climate Change and Environmental Sustainability. Drone emergency response would be a practical application for our research project.

Schlagwörter

Stichwörter der Autor:innen

AICNNUAVsclimate changedesertificationfloodingneural networksremote sensingsatellitetransfer learning

Autor:innen und Institutionen

  • Bioenvironmental Sciences Department, Morgan State University, Baltimore, MD 21251, USA.
  • Center for Climate Change & Health, Morgan State University, Baltimore, MD 21251, USA.
  • Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA.

Förderung

  • Oak Ridge Institute for Science and Education
  • U.S. Department of Energy’s Omni Technology Alliance Internship Program
  • US Department of Energy (DOE)
  • NSF

Zitieren

APA

VanExel, K., Sherchan, S., & Liu, S. (2025). Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data. Journal of Imaging, 11(2), 32. https://doi.org/10.3390/jimaging11020032

Vancouver

VanExel K, Sherchan S, Liu S. Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data. Journal of Imaging. 2025;11(2):32. doi:10.3390/jimaging11020032

BibTeX
@article{VanExel2025,
  author = {VanExel, Kim and Sherchan, Samendra and Liu, Siyan},
  title = {Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {2},
  pages = {32},
  doi = {10.3390/jimaging11020032}
}
Kostenlos starten →