CoGameReg improves seismic reservoir property prediction with sparse labels
CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction
Machine Learning
Summary
Predicting underground reservoir properties from seismic data is hard because detailed labeled measurements are very limited. The paper presents CoGameReg, a method that combines multiple prediction models and weighs their contributions to create better guesses on unlabeled data. Their approach uses game theory to assign importance scores to these models based on their past performance, which helps improve predictions when few labels are available. Tests show CoGameReg works well on both synthetic data and real field measurements, especially when labeled data is very scarce.
What this means in practice
- •For petroleum reservoir engineers: Enhance property predictions in reservoirs using sparse well data combined with dense seismic measurements to guide drilling and production.
- •For geophysical data analysts: Improve seismic attribute interpretation through collaborative regression models that better estimate reservoir characteristics where labeled data are limited.
Authors
Zhiyu Guo, Jiwei Jia, Lei Li
Abstract
Accurate estimation of reservoir properties from seismic data remains challenging when well-log labels are sparse but three-dimensional seismic observations are abundant. We present CoGameReg, a cooperative-game-based semi-supervised regression framework that uses contribution-weighted predictions of heterogeneous regressors to construct shared pseudo-labels. This design makes each regressor's influence explicit in the learning targets generated for unlabeled seismic samples under sparse well control. The Tri-Game Shapley mechanism combines a rank-MSE performance game with a pairwise consistency game to estimate nonnegative regressor weights from labeled training data. These weights remain fixed during collaborative training and are reused for final prediction fusion. Candidate pseudo-labels are screened using a common local k-nearest-neighbor error-reduction criterion before retraining. We evaluate CoGameReg on 10 public regression datasets, a synthetic three-dimensional P-wave velocity prediction task, and a field water-saturation application. The benchmark advantage is most pronounced at the 2.5% labeled-data ratio and decreases as supervision increases. CoGameReg obtains the best blind-well metrics in the synthetic experiment. In the field application, predictions clipped to 0-100% yield a pooled coefficient of determination of 0.5942, a root mean square error of 5.7441 percentage points, and a Pearson correlation of 0.8265 across three blind wells. CoGameReg has the highest Pearson correlation among the four field methods. The results support the use of CoGameReg to integrate sparse well labels with dense seismic attributes, with performance varying across metrics and well locations.