Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification. Sherif, K., Rizk, F. H., Zaki, A. M., Eid, M. M., Khodadadi, N., Ibrahim, A., Abdelhamid, A. A., Abualigah, L., & El-Kenawy, E. M. In 2024 International Telecommunications Conference (ITC-Egypt), pages 245–250, July, 2024. ![Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88% and a sensitivity of 92.86% at the same time, while the specificity is 99.88%. The sensitivity of this diagnostic test is 96.30%, and the specificity is 94.74%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards.
@inproceedings{sherif_revolutionizing_2024,
title = {Revolutionizing {Oil} {Spill} {Detection}: {A} {Machine} {Learning} {Approach} for {Satellite} {Image} {Classification}},
shorttitle = {Revolutionizing {Oil} {Spill} {Detection}},
url = {https://ieeexplore.ieee.org/document/10620599},
doi = {10.1109/ITC-Egypt61547.2024.10620599},
abstract = {Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88\% and a sensitivity of 92.86\% at the same time, while the specificity is 99.88\%. The sensitivity of this diagnostic test is 96.30\%, and the specificity is 94.74\%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards.},
urldate = {2024-08-17},
booktitle = {2024 {International} {Telecommunications} {Conference} ({ITC}-{Egypt})},
author = {Sherif, Khaled and Rizk, Faris H. and Zaki, Ahmed Mohamed and Eid, Marwa M. and Khodadadi, Nima and Ibrahim, Abdelhameed and Abdelhamid, Abdelaziz A. and Abualigah, Laith and El-Kenawy, El-Sayed M.},
month = jul,
year = {2024},
keywords = {Machine learning, Machine Learning, Computational modeling, Artificial neural networks, Predictive models, Oils, Analysis, Class Balancing, Data, Disasters, Environmental Monitoring, Feature Standardization, Model Evaluation, Oil Spill Classification, Sensitivity},
pages = {245--250},
file = {IEEE Xplore Abstract Record:C\:\\Users\\Ahmed\\Zotero\\storage\\QAYHZFIG\\10620599.html:text/html},
}
Downloads: 0
{"_id":"oisudzwtmCaAdEsPt","bibbaseid":"sherif-rizk-zaki-eid-khodadadi-ibrahim-abdelhamid-abualigah-etal-revolutionizingoilspilldetectionamachinelearningapproachforsatelliteimageclassification-2024","author_short":["Sherif, K.","Rizk, F. H.","Zaki, A. M.","Eid, M. M.","Khodadadi, N.","Ibrahim, A.","Abdelhamid, A. A.","Abualigah, L.","El-Kenawy, E. M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification","shorttitle":"Revolutionizing Oil Spill Detection","url":"https://ieeexplore.ieee.org/document/10620599","doi":"10.1109/ITC-Egypt61547.2024.10620599","abstract":"Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88% and a sensitivity of 92.86% at the same time, while the specificity is 99.88%. The sensitivity of this diagnostic test is 96.30%, and the specificity is 94.74%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards.","urldate":"2024-08-17","booktitle":"2024 International Telecommunications Conference (ITC-Egypt)","author":[{"propositions":[],"lastnames":["Sherif"],"firstnames":["Khaled"],"suffixes":[]},{"propositions":[],"lastnames":["Rizk"],"firstnames":["Faris","H."],"suffixes":[]},{"propositions":[],"lastnames":["Zaki"],"firstnames":["Ahmed","Mohamed"],"suffixes":[]},{"propositions":[],"lastnames":["Eid"],"firstnames":["Marwa","M."],"suffixes":[]},{"propositions":[],"lastnames":["Khodadadi"],"firstnames":["Nima"],"suffixes":[]},{"propositions":[],"lastnames":["Ibrahim"],"firstnames":["Abdelhameed"],"suffixes":[]},{"propositions":[],"lastnames":["Abdelhamid"],"firstnames":["Abdelaziz","A."],"suffixes":[]},{"propositions":[],"lastnames":["Abualigah"],"firstnames":["Laith"],"suffixes":[]},{"propositions":[],"lastnames":["El-Kenawy"],"firstnames":["El-Sayed","M."],"suffixes":[]}],"month":"July","year":"2024","keywords":"Machine learning, Machine Learning, Computational modeling, Artificial neural networks, Predictive models, Oils, Analysis, Class Balancing, Data, Disasters, Environmental Monitoring, Feature Standardization, Model Evaluation, Oil Spill Classification, Sensitivity","pages":"245–250","file":"IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Ahmed\\\\Zotero\\\\storage\\\\QAYHZFIG\\\\10620599.html:text/html","bibtex":"@inproceedings{sherif_revolutionizing_2024,\n\ttitle = {Revolutionizing {Oil} {Spill} {Detection}: {A} {Machine} {Learning} {Approach} for {Satellite} {Image} {Classification}},\n\tshorttitle = {Revolutionizing {Oil} {Spill} {Detection}},\n\turl = {https://ieeexplore.ieee.org/document/10620599},\n\tdoi = {10.1109/ITC-Egypt61547.2024.10620599},\n\tabstract = {Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88\\% and a sensitivity of 92.86\\% at the same time, while the specificity is 99.88\\%. The sensitivity of this diagnostic test is 96.30\\%, and the specificity is 94.74\\%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards.},\n\turldate = {2024-08-17},\n\tbooktitle = {2024 {International} {Telecommunications} {Conference} ({ITC}-{Egypt})},\n\tauthor = {Sherif, Khaled and Rizk, Faris H. and Zaki, Ahmed Mohamed and Eid, Marwa M. and Khodadadi, Nima and Ibrahim, Abdelhameed and Abdelhamid, Abdelaziz A. and Abualigah, Laith and El-Kenawy, El-Sayed M.},\n\tmonth = jul,\n\tyear = {2024},\n\tkeywords = {Machine learning, Machine Learning, Computational modeling, Artificial neural networks, Predictive models, Oils, Analysis, Class Balancing, Data, Disasters, Environmental Monitoring, Feature Standardization, Model Evaluation, Oil Spill Classification, Sensitivity},\n\tpages = {245--250},\n\tfile = {IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Ahmed\\\\Zotero\\\\storage\\\\QAYHZFIG\\\\10620599.html:text/html},\n}\n\n","author_short":["Sherif, K.","Rizk, F. H.","Zaki, A. M.","Eid, M. M.","Khodadadi, N.","Ibrahim, A.","Abdelhamid, A. A.","Abualigah, L.","El-Kenawy, E. M."],"key":"sherif_revolutionizing_2024","id":"sherif_revolutionizing_2024","bibbaseid":"sherif-rizk-zaki-eid-khodadadi-ibrahim-abdelhamid-abualigah-etal-revolutionizingoilspilldetectionamachinelearningapproachforsatelliteimageclassification-2024","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/10620599"},"keyword":["Machine learning","Machine Learning","Computational modeling","Artificial neural networks","Predictive models","Oils","Analysis","Class Balancing","Data","Disasters","Environmental Monitoring","Feature Standardization","Model Evaluation","Oil Spill Classification","Sensitivity"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/hJygNjxaDmfvtehHX","dataSources":["Gr4oTE3gHGLJxgDAy"],"keywords":["machine learning","machine learning","computational modeling","artificial neural networks","predictive models","oils","analysis","class balancing","data","disasters","environmental monitoring","feature standardization","model evaluation","oil spill classification","sensitivity"],"search_terms":["revolutionizing","oil","spill","detection","machine","learning","approach","satellite","image","classification","sherif","rizk","zaki","eid","khodadadi","ibrahim","abdelhamid","abualigah","el-kenawy"],"title":"Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification","year":2024}