Skip to main content

Table 10 Evolution of the standard deviation of residuals for various GRNN models predicting F a and F v in the TP–RF case

From: Deriving amplification factors from simple site parameters using generalized regression neural networks: implications for relevant site proxies

Truncated profiles F a F v
Number of parameters Explanatory parameters Standard deviation of residuals Variance reduction Standard deviation of residuals Variance reduction
All 5 Depth + f 0 + V smn + C v  + V s30 0.0095 99.28% 0.0017 99.97%
3 (best triplet) f 0 + C v  + V s30 0.0185 97.2% 0.0061 99.57%
2 (best pair for Fa) f 0 + C v 0.0375 88.8% 0.0229 93.9%
2 (convenient pair) f 0 + V s30 0.0511 79.1% 0.0127 98.1%
1 (best, Fa) C v 0.0734 57.05% 0.0736 37.9%
1 (best, Fv) f 0 0.0764 53.47% 0.0428 79%
1 (usual) V s30 0.0925 31.4% 0.0777 30.8%
Initial σ 0.112 0.0934