Characterization analysis and identification of common marine oil spill types using hyperspectral remote sensing

ABSTRACT

Marine oil spills cause great pollution to the marine environment and require development of efficient cleaning plans. Accurate identification of the oil type involved in the spill is of great significance for rapid and effective treatment. Hyperspectral remote sensing plays an important role in oil spill detection and oil type identification. We designed an outdoor oil spill experiment to simulate an oil spill in a marine environment. Five common oil types were selected as the experimental starting materials: crude oil, fuel oil, diesel oil, gasoline, and palm oil. Hyperspectral data of the five oils were collected from different solar times by Analytical Spectral Devices (ASD) FieldSpec4. The relationship between the spectral absorption baseline height of the different oil types and solar time is investigated. The characteristic analysis method of spectral standard deviation was used to obtain characteristic bands of the different oil types. Using both full spectrum and selected characteristic bands, oil type identification experiments were performed using the Support Vector Machine (SVM) model, respectively. The results show that oil type identification using selected characteristic bands is 3.70% more accurate compared with that using the full spectrum, reaching 83.33%.

KEYWORDS:

• Marine oil spill
• Spectral analysis
• Oil type recognition
• Hyperspectral remote sensing

Acknowledgements

This work was supported by the National Natural Science Foundation of China [grant number 61890964], [grant number 41706208], [grant number 41776182]. We thank Esther Posner, PhD, from Edanz Group (www.edanzediting.com/ac) for editing a draft of this manuscript. We would like to express our sincere appreciation to anonymous reviewers who provided valuable comments to help improve this paper.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [61890964, 41706208, 41776182].