Artificial intelligence in general and optimization tasks applied to the design of
very efficient structures rely on response surfaces to forecast the output of functions, and are vital
part of these methodologies. Yet they have important limitations, since greater precisions require
greater data sets, thus, training or updating larger response surfaces become computationally
expensive or unfeasible. This has been an important bottle neck limitation to achieve more
promising results, rendering many optimization and AI tasks with a low performance.
To solve this challenge, a new methodology created to segment response surfaces is hereby
presented. Differently than other similar methodologies, this algorithm named outer input method
has a very simple and robust operation, generating a mesh of near isopopulated partitions of
inputs which share similitude. The great advantage it offers is that it can be applied to any data
set with any type of distribution, such as random, Cartesian, or clustered, for domains with any
number of coordinates, significantly simplifying any metamodel with a mesh ensemble.
This study demonstrates how one of the most known and precise metamodel denominated
Kriging, yet with expensive computation costs, can be significantly simplified with a response
surface mesh, increasing training speed up to 567 times, while using a quad-core parallel
processing. Since individual mesh elements can be parallelized or updated individually, its faster
operational speed has its speed increased.