Skip to main content

Table 5 List of considered GRNN models

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

Output values Period/normalized frequency Set of profiles Set of explanatory variables (site parameters) Combinations
AF(T), F a , F v Period RP 6: Depth, f 0, C v , V sm, V s30, V bedrock 63 = 6 1-parameter, 15 pairs, 20 triplets, 15 quadruplets, 6 quintuplets, 1 (all 6 parameters)
AF(f/f 0) Normalized f/f 0 RP 5: Depth, C v , V sm, V s30, V bedrock 31 = 5 1-parameter, 10 pairs, 10 triplets, 5 quadruplets 1 (all 5 parameters)
AF(T), F a , F v Period NP 5: Depth, f 0, C v , V sm, V s30 31 = 5 1-parameter, 10 pairs, 10 triplets, 5 quadruplets 1 (all 5 parameters)
AF(f/f 0) Normalized f/f 0 NP 4: Depth, C v , V sm, V s30 15 = 4 1-parameter, 6 pairs, 4 triplets, 1 (all 4 parameters)
AF(T), F a , F v Period TP 5: Depth, f 0, C v , V sm, V s30 31 = 5 1-parameter, 10 pairs, 10 triplets, 5 quadruplets 1 (all 5 parameters)
AF(f/f 0) Normalized f/f 0 TP 4: Depth, C v , V sm, V s30 15 = 4 1-parameter, 6 pairs, 4 triplets, 1 (all 4 parameters)