Parameter estimation for complex physical problems often suffers from finding ‘solutions’ that are not physically realistic. The PEUQSE software provides tools for finding physically realistic parameter estimates, graphs of the parameter estimate positions within parameter space, and plots of the final simulation results.
13
stars
5
forks
source link
add 'sobol' and "latin hypercube' as distribution types (like 'uniform') and Variance-based sensitivities #171
This will also allow us to get the first order and second order Variance-based sensitivities to see which parameters are most important for a given response. We can then make spider plots or similar.
Currently, we have several distribution types, such as 'uniform'. We do not have 'sobol' as an initial distribution type.
It will not be hard to make. Salib returns the parameter vectors for sampling, like in param_values in the example page for Saltelli: https://salib.readthedocs.io/en/latest/basics.html#an-example
there is also latin hypercube: https://salib.readthedocs.io/en/latest/api/SALib.sample.html?highlight=Saltelli#module-SALib.sample.saltelli
This will also allow us to get the first order and second order Variance-based sensitivities to see which parameters are most important for a given response. We can then make spider plots or similar.
https://en.wikipedia.org/wiki/Variance-based_sensitivity_analysis#:~:text=Variance-based%20sensitivity%20analysis%20%28often%20referred%20to%20as%20the,be%20attributed%20to%20inputs%20or%20sets%20of%20inputs.