Comparative Analysis of Drought Detection Using Satellite Imagery with Deep Learning Models

Rama Devi Gunnam*
Periodicity:January - March'2025

Abstract

Drought detection is essential for effective environmental and agricultural planning. In this study, we leveraged satellite imagery from the USGS Landsat8 dataset, focusing on RGB bands, to develop a deep learning-based model for identifying drought conditions. To classify the data, we used the number of cows present in the images—images with 0 or 1 cow were labeled as Class 0, while those with 2 or more cows were categorized as Class 1. Drought conditions are detected if an image falls under Class 0, whereas Class 1 indicates no drought. We trained and evaluated four deep learning models: EfficientNetB0, MobileNetV2, VGG16, and a custom CNN. By analyzing performance metrics such as accuracy, precision, recall, and F1-score, we found that EfficientNetB0 outperformed the other models, with an accuracy of 90.31% and a precision of 90.58%. These results demonstrate its reliability in detecting drought-prone areas. Our findings emphasize the potential of deep learning for satellite-based drought detection, offering valuable insights for environmental monitoring and resource management.

Keywords

Drought Detection, Landsat8 dataset, Deep learning, CNN (Convolutional Neural Network), Classification

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 15 15 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.