Abstract
An oil spill is a leakage of pipelines, vessels, oil rigs, or tankers that leads to the release of petroleum products into the marine environment or on land that happened naturally or due to human action, which resulted in severe damages and financial loss. Satellite imagery is one of the powerful tools currently utilized for capturing and getting vital information from the Earth's surface. But the complexity and the vast amount of data make it challenging and time-consuming for humans to process. However, with the advancement of deep learning techniques, the processes are now computerized for finding vital information using real-time satellite images. This paper applied three deep-learning algorithms for satellite image classification, including ResNet50, VGG19, and InceptionV4; They were trained and tested on an open-source satellite image dataset to analyze the algorithms' efficiency and performance and correlated the classification accuracy, precisions, recall, and f1-score. The result shows that InceptionV4 gives the best classification accuracy of 97% for cloudy, desert, green areas, and water, followed by VGG19 with approximately 96% and ResNet50 with 93%. The findings proved that the InceptionV4 algorithm is suitable for classifying oil spills and no spill with satellite images on a validated dataset.
Keywords
Classification, Marine, Oil spill, satellite images, deep learning
Article Type
Special Issue Article
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite this Article
Abba, Abubakar Salihu; Mustaffa, Noorfa Haszlinna; Hashim, Siti Zaiton Mohd; and Alwee, Razana
(2024)
"Oil spill classification based on satellite image using deep learning techniques,"
Baghdad Science Journal: Vol. 21:
Iss.
2, Article 42.
DOI: https://doi.org/10.21123/bsj.2024.9767
