Optimized Transfer Learning Pipeline Using ResNet-50 and Bayesian Optimization for Oil Spillage Detection

Mitong Dorcas, Muhammad Bashir Abdullahi, Emmanuel Ogbonnia
Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, PMLR 319:421-434, 2026.

Abstract

This paper presents an efficient transfer learning framework combining a pretrained ResNet-50 backbone with Bayesian hyperparameter optimisation for oil spill detection in Sentinel-1 SAR imagery. The architecture uses a frozen convolutional feature extractor followed by a compact classification head (Dense-256, Dropout, Sigmoid), with SGD optimiser hyperparameters automatically tuned: learning rate (0.001578), weight decay (0.012348), dropout (0.0129), and momentum (0.5872). On an imbalanced cohort with a large proportion of oceanic look-alike dark spots, the refined model achieves accuracy of 85.36%, weighted F1-score of 85.32, and balanced class-wise performance (Non-Oil F1 = 0.89; Oil F1 = 0.79). Training and validation curves demonstrate consistent convergence without overfitting, confirming the effectiveness of Bayesian optimisation in navigating the complex hyperparameter space of SAR-based oil spill classification. The framework provides a computationally efficient solution for operational monitoring with robust discrimination between genuine spills and natural look-alikes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v319-dorcas26a, title = {Optimized Transfer Learning Pipeline Using {ResNet-50} and {Bayesian} Optimization for Oil Spillage Detection}, author = {Dorcas, Mitong and Abdullahi, Muhammad Bashir and Ogbonnia, Emmanuel}, booktitle = {Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments}, pages = {421--434}, year = {2026}, editor = {Folorunso, Sakinat and Ogundokun, Roseline and Oladipo, Francisca}, volume = {319}, series = {Proceedings of Machine Learning Research}, month = {11--14 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v319/main/assets/dorcas26a/dorcas26a.pdf}, url = {https://proceedings.mlr.press/v319/dorcas26a.html}, abstract = {This paper presents an efficient transfer learning framework combining a pretrained ResNet-50 backbone with Bayesian hyperparameter optimisation for oil spill detection in Sentinel-1 SAR imagery. The architecture uses a frozen convolutional feature extractor followed by a compact classification head (Dense-256, Dropout, Sigmoid), with SGD optimiser hyperparameters automatically tuned: learning rate (0.001578), weight decay (0.012348), dropout (0.0129), and momentum (0.5872). On an imbalanced cohort with a large proportion of oceanic look-alike dark spots, the refined model achieves accuracy of 85.36%, weighted F1-score of 85.32, and balanced class-wise performance (Non-Oil F1 = 0.89; Oil F1 = 0.79). Training and validation curves demonstrate consistent convergence without overfitting, confirming the effectiveness of Bayesian optimisation in navigating the complex hyperparameter space of SAR-based oil spill classification. The framework provides a computationally efficient solution for operational monitoring with robust discrimination between genuine spills and natural look-alikes.} }
Endnote
%0 Conference Paper %T Optimized Transfer Learning Pipeline Using ResNet-50 and Bayesian Optimization for Oil Spillage Detection %A Mitong Dorcas %A Muhammad Bashir Abdullahi %A Emmanuel Ogbonnia %B Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments %C Proceedings of Machine Learning Research %D 2026 %E Sakinat Folorunso %E Roseline Ogundokun %E Francisca Oladipo %F pmlr-v319-dorcas26a %I PMLR %P 421--434 %U https://proceedings.mlr.press/v319/dorcas26a.html %V 319 %X This paper presents an efficient transfer learning framework combining a pretrained ResNet-50 backbone with Bayesian hyperparameter optimisation for oil spill detection in Sentinel-1 SAR imagery. The architecture uses a frozen convolutional feature extractor followed by a compact classification head (Dense-256, Dropout, Sigmoid), with SGD optimiser hyperparameters automatically tuned: learning rate (0.001578), weight decay (0.012348), dropout (0.0129), and momentum (0.5872). On an imbalanced cohort with a large proportion of oceanic look-alike dark spots, the refined model achieves accuracy of 85.36%, weighted F1-score of 85.32, and balanced class-wise performance (Non-Oil F1 = 0.89; Oil F1 = 0.79). Training and validation curves demonstrate consistent convergence without overfitting, confirming the effectiveness of Bayesian optimisation in navigating the complex hyperparameter space of SAR-based oil spill classification. The framework provides a computationally efficient solution for operational monitoring with robust discrimination between genuine spills and natural look-alikes.
APA
Dorcas, M., Abdullahi, M.B. & Ogbonnia, E.. (2026). Optimized Transfer Learning Pipeline Using ResNet-50 and Bayesian Optimization for Oil Spillage Detection. Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, in Proceedings of Machine Learning Research 319:421-434 Available from https://proceedings.mlr.press/v319/dorcas26a.html.

Related Material