ResNet18 Combined With CBAM Achieves 86.36 Percent Accuracy in Lithology Identification
A ResNet18 model integrating the CBAM attention module achieved an 86.36 percent lithology identification accuracy when trained with optimized learning ...
A ResNet18 model integrating the CBAM attention module achieved an 86.36 percent lithology identification accuracy when trained with optimized learning ...
Researchers integrated continuous well-log calcium regression with AdaBoost classification to map challenging calcareous sandstone interbeds across the East China Sea ...
A study of six Browse Basin wells shows gradient boosting can reconstruct sonic logs missing under a harsh simulated pattern, ...
Researchers in China have unveiled SpecMamba-Net, a dual-branch Mamba-based AI that fuses frequency-domain texture cues with linear-complexity global state-space modeling ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine