Dataset for A TDA-based Seismic Attribute Selection Model for Random Forest Oil Production Prediction

This dataset contains the seismic attribute data and oil production measurements used to develop and validate a topology-based seismic attribute selection framework combined with Random Forest regression. The dataset includes 1342 samples with one target variable (oil production) and seven seismic attributes. The data were used for persistent homology analysis, topological feature extraction, seismic attribute ranking, and oil production prediction.