Detection and Quantification of Daily Marine Oil Pollution Using Remote Sensing

Dhavalikar, Anagha S.; Choudhari, Pranali

doi:10.1007/s11270-022-05752-0

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the inclusion of speeded-up robust features (SURF) enhances classification precision. Focusing on the Eastern Arabian Sea, the study successfully validates reported oil spills in 2017 and uncovers previously unreported incidents in 2020, shedding light on oil spill occurrences in the region [Dhavalikar & Choudhari, 2022]…”

supporting

confidence: 54%

A Comprehensive Analysis of Marine Life Pollution Using Machine Learning Techniques on historical shipping Pollutants data

Singh

2024

IJSREM

View full text Add to dashboard Cite

Oil spills significantly threaten marine and coastal ecosystems, resulting in devastating ecological and economic consequences. The current research highlights the key aspects surrounding oil spills, including their causes, environmental impacts, and mitigation strategies. Oil spills, resulting from accidents during offshore drilling, transportation, or natural seepage, pose severe ecological and societal challenges. These incidents release vast quantities of oil into marine ecosystems, leading to widespread environmental degradation. The impact of oil spills is influenced by factors such as spill volume, oil type, environmental conditions, and response effectiveness. Ecologically, oil spills harm marine life through toxic effects, habitat destruction, and interference with reproductive cycles. Birds, marine mammals, fish, and shoreline organisms suffer from oil exposure, leading to long-term population declines. The economic consequences are significant, affecting fishers, tourism, and coastal industries. The clean-up process involves mechanical removal, chemical dispersants, and controlled burns, each with its environmental trade-offs. Oil spill assessment methods encompass satellite monitoring, modeling, and ecological surveys to estimate damages and aid restoration efforts. Prevention measures include stricter regulations, technological advancements, and industry best practices. Public awareness and international cooperation are vital for enhancing spill preparedness and response. In the paper, oil spills continue to challenge environmental sustainability and economic stability. Addressing their multifaceted impacts demands an integrated approach involving mitigation, rigorous assessment, and global collaboration to prevent future disasters and safeguard our oceans and coastlines. An expansive dataset gathered from Queensland, Australia, incorporating intricate information about ships, regions, longitudes, latitudes, and pollutants, the study markedly advances the capability to identify oceanic oil spills and enhances our understanding of the resulting impact on marine life. In that, algorithms are used of machine learning techniques such as SVC and LogisticRegression. In the course of the study, machine learning techniques are applied, featuring algorithms like Support Vector Classification (SVC) and Logistic Regression. These algorithms play a crucial role in the analysis, contributing to the extraction of valuable insights from the dataset. Keywords: Bilge, Diesel, Hydraulic Oil, Types of Ship, Machine learning algorithms

show abstract

supporting

confidence: 54%

A Comprehensive Analysis of Marine Life Pollution Using Machine Learning Techniques on historical shipping Pollutants data

Singh

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…For studies using pixel-wise classification or semantic segmentation, one advantage is that the exact locations covered with oil are predicted; however, applying them to an operational service might be computationally intensive as they classify each pixel of the given images, which are the entire SAR scenes. Therefore, previous studies have utilized the oil spill detection tool provided in the Sentinel Application Platform (SNAP) toolbox, which identifies suspicious dark formations with thresholding and generates image patches containing areas of interest (Dhavalikar and Choudhari 2022;El-Magd et al 2021). After obtaining the image patches, the authors applied dark spot detection, feature extraction and classification methods to acquire the final detections of oil slicks (Dhavalikar and Choudhari 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, previous studies have utilized the oil spill detection tool provided in the Sentinel Application Platform (SNAP) toolbox, which identifies suspicious dark formations with thresholding and generates image patches containing areas of interest (Dhavalikar and Choudhari 2022;El-Magd et al 2021). After obtaining the image patches, the authors applied dark spot detection, feature extraction and classification methods to acquire the final detections of oil slicks (Dhavalikar and Choudhari 2022).…”

Section: Introductionmentioning

confidence: 99%