Fig. 4: SHAP analysis of XGBoost feature importance with progressive feature exclusion. | npj Metamaterials

Fig. 4: SHAP analysis of XGBoost feature importance with progressive feature exclusion.

From: Machine learning-based mechanics of TPMS architected materials driven by unit-cell geometric features

Fig. 4: SHAP analysis of XGBoost feature importance with progressive feature exclusion.The alternative text for this image may have been generated using AI.

a–d SHAP feature importance with full feature set including volume fraction Vf. e–h SHAP feature importance excluding volume fraction Vf. i–l SHAP feature importance excluding both Vf and principal moment of inertia I11 to reveal intrinsic contributions of remaining geometric descriptors.

Back to article page