Evidence item

The indexed Matilda record reproduces the 12-well case study and reported SE-ResNet18 performance. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 17538

Source: An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks · locator {} · excerpt hash sha256:69550142159acf95462388dc2252ae9996194a772414051d6fe51c0c6f2bbf71

Exact excerpt

This study uses data from 12 cored wells in the Chang 8 Member, Jiyuan Oilfield (western Ordos Basin) to develop a permeability-driven integrated workflow for reservoir evaluation. We first build an SE-ResNet18 model with one-dimensional convolution and residual learning to capture vertical continuity in well logs, achieving R² = 0.86 and RMSE = 0.287 mD for permeability regression.

Linked claims

Claim	Direction	Relevance	Steps	Counted
5a094627	SUPPORT	DIRECT	0	yes

Audits

None.