Open access
Jul 2026
ALSTMResNet: Active-Learning-Enhanced LSTMResNet as an Efficiency-Oriented Training Framework for Well Anomaly Monitoring Under Partial Labels
Results indicate that ALSTMResNet can support cost-aware oil-well anomaly monitoring when labels are partially available and retraining resources are constrained, although uncertainty, entropy, margin, least-confidence, and random querying have limited separation in the present binary setting.
Feng Ge, Zhi Yang, Fan Yu et al.
· Processes · 0 citations