Development of band ratioing algorithms and neural networks to detection of oil spills using Landsat ETM+ data

Taravat, Alireza; Frate, Fabio Del

doi:10.1186/1687-6180-2012-107

Cited by 35 publications

(27 citation statements)

References 13 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lee et al [8] developed an algorithm for discriminating film-like oil from thick oil using DubaiSat-2 and Landsat Operational Land Imager (OLI) data. Taravat et al [9] performed ratio operations on Landsat 7 ETM images to enhance oil spill features. They concluded that the bands' difference between 660 and 560 nm, division at 660 and 560, and division at 825 and 560 nm, normalized by 480 nm, provide the best result.…”

Section: Introductionmentioning

confidence: 99%

Oil Spill Detection and Mapping Using Sentinel 2 Imagery

Kolokoussis

Karathanassi

2018

JMSE

View full text Add to dashboard Cite

Two object-based image analysis methods are developed for detecting oil spills from known natural outflows as well as light oil spill events using Sentinel 2 imagery. The methods are applied to Sentinel 2 images of a known area of natural oil outflow as well as on a Sentinel 2 image of a recent oil spill event along the south coast of Athens, Greece. The preliminary results are considered very successful and consistent, with a high degree of applicability to other Sentinel 2 satellite images. Further testing and fine tuning of the proposed object-based methodology should be carried out using atmospheric correction and ground truth.

show abstract

Section: Introductionmentioning

confidence: 99%

Oil Spill Detection and Mapping Using Sentinel 2 Imagery

Kolokoussis

Karathanassi

2018

JMSE

View full text Add to dashboard Cite

show abstract

“…To effectively and accurately predict and forecast an oil spill, it is strongly suggested that multiple satellite observations and hydrodynamic models integrated. With sophisticated algorithms, such as artificial neural networks (Taravat and Del Frate 2012), to classify oil spill and measure oil thickness, the efficiency of rapid responses for emergency oil spills can be significantly improved, and more active strategies to combat oil spills can be made.…”

Section: Resultsmentioning

confidence: 99%

Satellite-Based Tracking of Oil Pollution in the Arabian Gulf and the Sea of Oman

Zhao¹,

Temimi²,

Azhar³

et al. 2015

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

Two oil spill events were investigated using multisensor satellite images in the Al Khafji and Al Fujairah regions. Oil slicks were characterized with Red-Green-Blue (RGB) and floating algae index (FAI) images. Oil slicks near Al Khafji were detected on April 19, 2014 by Landsat 8 and covered around 29.04 km 2 . Sequential VIIRS and MODIS/Aqua images collected on the same day observed the same slicks, which indicated different appearances in the RGB images. Another event was recorded near Al Fujairah on May 11, 2014 by both Landsat 8 and Aqua. The total area coverage of oil slicks was 114.6 km 2 . The estimated slick trajectories from GNOME driven by ocean circulation data from the Regional Ocean Model System (ROMS) and meteorological data were assessed with the movement patterns of satellite-detected oil slicks. The average absolute percentage error of velocity of slick movement between satellite observation and GNOME simulation was 33% for both events. The directions of slick movement showed an agreement between satellite observation and model simulation in 5 out of 7 trajectories' cases. This implies that the integration of multisensor satellite measurements and spill trajectory modeling is very helpful to forecast and predict the fate and transport of oil spills. Résumé. Deux déversements d'hydrocarbures ontétéétudiés en utilisant des images satellitaires multicapteurs dans les régions d'Al Khafji et d'Al Fujairah. Les nappes de pétrole ontété caractérisées avec des images rouge-vert-bleu (RVB) « red-green-blue (RGB) » et avec l'indice d'algues flottantes « floating algae index » (FAI). Les nappes de pétrole près d'Al Khafji ontété détectées le 19 avril 2014 par Landsat 8 et elles couvraient environ 29,04 km 2 . Les images séquentielles VIIRS et MODIS/Aqua acquises le même jour ont observé les mêmes nappes, indiquées par différents aspects dans les images RVB. Un autreévènement aété détecté près d'AlFujairah le 11 mai 2014à la fois par Landsat 8 et Aqua. La superficie totale de ces nappesétait de 114,6 km 2 . Les trajectoires des déversements d'hydrocarbure estiméesà partir de GNOME, en utilisant les données de la circulation océanique du Regional Ocean Model System (ROMS) et les données météorologiques, ontétéévaluées en utilisant les déplacements des nappes de pétrole détectées par satellite. Le pourcentage d'erreur absolue moyenne de la vitesse de mouvement de la nappe entre l'observation par satellite et la simulation de GNOMEétait de 33% pour les 2évènements. Les directions de mouvements des nappes ont montré un accord entre l'observation par satellite et la simulation du modèle dans 5 des 7 cas de trajectoires. Ceci implique que l'intégration de mesures satellitaires multicapteurs et la modélisation des trajectoires des déversements sont très utiles pour prévoir et prédire le devenir et le transport des déversements de pétrole.

show abstract

“…The stripes in Landsat ETM+ data (caused by the SLC in the ETM+ instrument failed on 31 May 2003) have been removed according to Taravat et al [93]. Pixels not affected by striping are used to construct spline functions describing spatial grey level distributions of an image [93].…”

Section: Image Pre-processingmentioning

confidence: 99%

“…Pixels not affected by striping are used to construct spline functions describing spatial grey level distributions of an image [93].…”

Section: Image Pre-processingmentioning

confidence: 99%

A Spaceborne Multisensory, Multitemporal Approach to Monitor Water Level and Storage Variations of Lakes

Taravat

Rajaei²,

Emadodin

et al. 2016

Water

Self Cite

View full text Add to dashboard Cite

Lake Urmia, the second largest saline Lake on earth and a highly endangered ecosystem, is on the brink of a serious environmental disaster similar to the catastrophic death of the Aral Sea. Progressive drying has been observed during the last decade, causing dramatic changes to Lake Urmia's surface and its regional water supplies. The present study aims to improve monitoring of spatiotemporal changes of Lake Urmia in the period 1975-2015 using the multi-temporal satellite altimetry and Landsat (5-TM, 7-ETM+ and 8-OLI) images. In order to demonstrate the impacts of climate change and human pressure on the variations in surface extent and water level, Lake Sevan and Van Lake with different characteristics were studied along with the Urmia Lake. Normalized Difference Water Index-Principal Components Index (NDWI-PCs), Normalized Difference Water Index (NDWI), Modified NDWI (MNDWI), Normalized Difference Moisture Index (NDMI), Water Ratio Index (WRI), Normalized Difference Vegetation Index (NDVI), Automated Water Extraction Index (AWEI), and MultiLayer Perceptron Neural Networks (MLP NNs) classifier were investigated for the extraction of surface water from Landsat data. The presented results revealed that MLP NNs has a better performance in the cases where the other models generate poor accuracy. The results show that the area of Lake Sevan and Van Lake have increased while the area of Lake Urmia has decreased by~65.23% in the past decades, far more than previously reported (~25% to 50%). Urmia Lake's shoreline has been receding severely between 2010 and 2015 with no sign of recovery, which has been partly blamed on prolonged droughts, aggressive regional water resources development plans, intensive agricultural activities, and anthropogenic changes to the system. The results also indicated that (among the proposed factors) changes in inflows due to overuse of surface water resources and constructing dams (mostly during 1995-2005) are the main reasons for Urmia Lake's shoreline receding. The model presented in this manuscript can be used by managers as a decision support system to find the effects of building new dams or other infrastructures.

show abstract

Development of band ratioing algorithms and neural networks to detection of oil spills using Landsat ETM+ data

Cited by 35 publications

References 13 publications

Oil Spill Detection and Mapping Using Sentinel 2 Imagery

Oil Spill Detection and Mapping Using Sentinel 2 Imagery

Satellite-Based Tracking of Oil Pollution in the Arabian Gulf and the Sea of Oman

A Spaceborne Multisensory, Multitemporal Approach to Monitor Water Level and Storage Variations of Lakes

Contact Info

Product

Resources

About