Skip to main content
Earth, Planets and Space
Fig. 10 | Earth, Planets and Space

Fig. 10

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

Fig. 10

Variation in root-mean-square error, standard deviation of residuals \(\varepsilon_{\text{GRNN}} \left( {\theta ,T_{i} } \right)\), for various GRNN models with various sets of input site parameters (indicated with different colors), compared to the initial variability \(\sigma_{0} \left( {\theta ,T_{i} } \right)\) (solid green line) for the RP–RF (a, top), NP–RF (b, middle), and TP–RF (c, bottom). Data are displayed as a function of real period

Back to article page