May 7, 2024

Prediction of Total Skin Factor in Perforated Wells Using Models Powered by Deep Learning and Machine Learning

View Full Paper

Ask AI

Bookmark

Authors

STS. ThabetMethodist Hospital HZHadier Mohammed ZidanCentral Metallurgical Research and Development Institute AEAhmed Ayman Elhadidy

Discussion

Member takes

Implication

Machine learning evaluation demonstrates accurate total skin factor prediction in perforated oil wells, highlighting a cost-effective alternative to pressure transient testing.

Key Points

Random Forest algorithms accurately predict total skin factor in perforated wells, outperforming eight other machine learning models across diverse reservoir conditions.
Top-performing Random Forest models achieved a 2.9% mean absolute percent error, yielding an R2 of 0.975 when evaluated against conventional well test measurements.
Assessment of 19,040 data points across 1,088 perforated wells validated nine algorithms, which highlights potential to optimize hydraulic fracturing treatments.

Cite This Study

Thabet et al. (2024) studied this question.

synapsesocial.com/papers/68e6b299b6db64358763414e https://doi.org/10.2118/219187-ms

View Full Paper

Ask AI

Bookmark

Implication

Machine learning evaluation demonstrates accurate total skin factor prediction in perforated oil wells, highlighting a cost-effective alternative to pressure transient testing.

Prediction of Total Skin Factor in Perforated Wells Using Models Powered by Deep Learning and Machine Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Prediction of Total Skin Factor in Perforated Wells Using Models Powered by Deep Learning and Machine Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider