Unsupervised Electrofacies Classification and Porosity Characterization in the Offshore Keta Basin Using Wireline Logs
📰 ArXiv cs.AI
Apply unsupervised machine learning to wireline logs for electrofacies classification and porosity characterization in offshore basins
Action Steps
- Collect wireline logs from offshore wells
- Apply K-means clustering in multivariate log space
- Evaluate clustering structure using inertia and silhouette diagnostics
- Identify and interpret clusters as electrofacies
- Characterize porosity using wireline log data and clustering results
Who Needs to Know This
Geologists and data scientists working in offshore basin analysis can benefit from this workflow to identify electrofacies and characterize porosity without relying on scarce core data
Key Insight
💡 Unsupervised machine learning can effectively identify electrofacies and characterize porosity in offshore basins using wireline logs
Share This
🌊 Unsupervised ML for electrofacies classification & porosity characterization in offshore basins! 📊
Key Takeaways
Apply unsupervised machine learning to wireline logs for electrofacies classification and porosity characterization in offshore basins
Full Article
Title: Unsupervised Electrofacies Classification and Porosity Characterization in the Offshore Keta Basin Using Wireline Logs
Abstract:
arXiv:2604.27126v1 Announce Type: new Abstract: This study presents an unsupervised machine learning workflow for electrofacies analysis in the offshore Keta Basin, Ghana, where core data are scarce. Six standard wireline logs from Well~C were analysed over a depth interval comprising approximately $11{,}195$ samples. K-means clustering was applied in multivariate log space, with the clustering structure evaluated using inertia and silhouette diagnostics. Four clusters were identified, supported
Abstract:
arXiv:2604.27126v1 Announce Type: new Abstract: This study presents an unsupervised machine learning workflow for electrofacies analysis in the offshore Keta Basin, Ghana, where core data are scarce. Six standard wireline logs from Well~C were analysed over a depth interval comprising approximately $11{,}195$ samples. K-means clustering was applied in multivariate log space, with the clustering structure evaluated using inertia and silhouette diagnostics. Four clusters were identified, supported
DeepCamp AI