Detection of Complex Formations in an Inland Lake from Sentinel-2 Images Using Atmospheric Corrections and a Fully Connected Deep Neural Network

The detection of complex formations, initially suspected to be oil spills, is investigated using atmospherically corrected multispectral satellite images and deep learning techniques. Several formations have been detected in an inland lake in Northern Greece. Four atmospheric corrections (ACOLITE, i...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 16; no. 20; p. 3913
Main Authors Mantsis, Damianos F., Moumtzidou, Anastasia, Lioumbas, Ioannis, Gialampoukidis, Ilias, Christodoulou, Aikaterini, Mentes, Alexandros, Vrochidis, Stefanos, Kompatsiaris, Ioannis
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.10.2024
Subjects
Accuracy
Algorithms
Artificial neural networks
Atmospheric correction
Chlorophyll
Deep learning
Drinking water
Environmental monitoring
Formations
Hydrocarbons
Lakes
Machine learning
Neural networks
oil spill
Oil spills
Pollution detection
Polymers
Remote monitoring
Remote sensing
Satellite imagery
Satellites
Sensors
water body pollution
Water quality
Iran
Online AccessGet full text

Cover

More Information
Summary:The detection of complex formations, initially suspected to be oil spills, is investigated using atmospherically corrected multispectral satellite images and deep learning techniques. Several formations have been detected in an inland lake in Northern Greece. Four atmospheric corrections (ACOLITE, iCOR, Polymer, and C2RCC) that are specifically designed for water applications are examined and implemented on Sentinel-2 multispectral satellite images to eliminate the influence of the atmosphere. Out of the four algorithms, iCOR and ACOLITE are able to depict the formations sufficiently; however, the latter is chosen for further processing due to fewer uncertainties in the depiction of these formations as anomalies across the multispectral range. Furthermore, a number of formations are annotated at the pixel level for the 10 m bands (red, green, blue, and NIR), and a deep neural network (DNN) is trained and validated. Our results show that the four-band configuration provides the best model for the detection of these complex formations. Despite not being necessarily related to oil spills, studying these formations is crucial for environmental monitoring, pollution detection, and the advancement of remote sensing techniques.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16203913