What type of study is this?

Leveraging Data-driven Approach for Sand Production Prediction and Management in Oil and Gas Wells

View Full Paper

Ask AI

Bookmark

Authors

Research demonstrates effective sand production prediction using support vector and random forest models, highlighting management strategies.

The ν-support vector classification model achieved 100% accuracy on training data, indicating high effectiveness.
The random forest model for predicting sand occurrence demonstrated 97.65% training accuracy and 88.89% on test data.
An AdaBoost regression model predicted the expected sand volume with 99.51% training accuracy and 79.07% on test data.
These machine learning models underline the importance of proactive strategies for sand control, minimizing operational risks.

Oladipupo et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Research demonstrates effective sand production prediction using support vector and random forest models, highlighting management strategies.