https://github.com/SciML/GlobalSensitivity.jl
Robust, Fast, and Parallel Global Sensitivity Analysis (GSA) in Julia
https://github.com/SciML/GlobalSensitivity.jl
differential-equations efast global-sensitivity-analysis gsa julia julia-language julialang morris-method ode ordinary-differential-equations scientific-machine-learning sciml sensitivity-analysis sobol-method
Last synced: 2 months ago
JSON representation
Robust, Fast, and Parallel Global Sensitivity Analysis (GSA) in Julia
- Host: GitHub
- URL: https://github.com/SciML/GlobalSensitivity.jl
- Owner: SciML
- License: mit
- Created: 2020-11-10T17:29:39.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2025-03-27T03:25:00.000Z (4 months ago)
- Last Synced: 2025-04-22T07:04:12.616Z (3 months ago)
- Topics: differential-equations, efast, global-sensitivity-analysis, gsa, julia, julia-language, julialang, morris-method, ode, ordinary-differential-equations, scientific-machine-learning, sciml, sensitivity-analysis, sobol-method
- Language: Julia
- Homepage: https://docs.sciml.ai/GlobalSensitivity/stable/
- Size: 24.1 MB
- Stars: 57
- Watchers: 6
- Forks: 22
- Open Issues: 28
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.bib
Awesome Lists containing this project
- awesome-sciml - SciML/GlobalSensitivity.jl
README
# GlobalSensitivity.jl
[](https://julialang.zulipchat.com/#narrow/stream/279055-sciml-bridged)
[](https://docs.sciml.ai/GlobalSensitivity/stable/)
[](https://codecov.io/gh/SciML/GlobalSensitivity.jl)
[](https://github.com/SciML/GlobalSensitivity.jl/actions?query=workflow%3ACI)
[](https://github.com/SciML/ColPrac)
[](https://github.com/SciML/SciMLStyle)
[](https://doi.org/10.21105/joss.04561)
GlobalSensitivity.jl package contains implementation of some the most popular GSA methods. Currently it supports Delta Moment-Independent, DGSM, EASI, eFAST, Morris, Mutual Information, Fractional Factorial, RBD-FAST, RSA, Sobol and Regression based sensitivity methods.
## Tutorials and Documentation
For information on using the package,
[see the stable documentation](https://docs.sciml.ai/GlobalSensitivity/stable/). Use the
[in-development documentation](https://docs.sciml.ai/GlobalSensitivity/dev/) for the version of
the documentation, which contains the unreleased features.
## Installation
The GlobalSensitivity.jl package can be installed with julia's package manager as shown below:
```julia
using Pkg
Pkg.add("GlobalSensitivity")
```
## General Interface
The general interface for performing global sensitivity analysis using this package is:
```julia
res = gsa(f, method, param_range; samples, batch = false)
```
## Example
### Sobol method on the [Ishigami function](https://www.sfu.ca/%7Essurjano/ishigami.html).
Serial execution
```julia
function ishi(X)
A = 7
B = 0.1
sin(X[1]) + A * sin(X[2])^2 + B * X[3]^4 * sin(X[1])
end
n = 600000
lb = -ones(4) * π
ub = ones(4) * π
sampler = SobolSample()
A, B = QuasiMonteCarlo.generate_design_matrices(n, lb, ub, sampler)
res1 = gsa(ishi, Sobol(order = [0, 1, 2]), A, B)
```
Using batching interface
```julia
function ishi_batch(X)
A = 7
B = 0.1
@. sin(X[1, :]) + A * sin(X[2, :])^2 + B * X[3, :]^4 * sin(X[1, :])
end
res2 = gsa(ishi_batch, Sobol(), A, B, batch = true)
```
### Regression based and Morris method sensitivity analysis of Lotka Volterra model.
```julia
using GlobalSensitivity, QuasiMonteCarlo, OrdinaryDiffEq, Statistics, CairoMakie
function f(du, u, p, t)
du[1] = p[1] * u[1] - p[2] * u[1] * u[2] #prey
du[2] = -p[3] * u[2] + p[4] * u[1] * u[2] #predator
end
u0 = [1.0; 1.0]
tspan = (0.0, 10.0)
p = [1.5, 1.0, 3.0, 1.0]
prob = ODEProblem(f, u0, tspan, p)
t = collect(range(0, stop = 10, length = 200))
f1 = function (p)
prob1 = remake(prob; p = p)
sol = solve(prob1, Tsit5(); saveat = t)
return [mean(sol[1, :]), maximum(sol[2, :])]
end
bounds = [[1, 5], [1, 5], [1, 5], [1, 5]]
reg_sens = gsa(f1, RegressionGSA(true), bounds)
fig = Figure(resolution = (600, 400))
ax, hm = CairoMakie.heatmap(fig[1, 1], reg_sens.partial_correlation,
figure = (resolution = (300, 200),),
axis = (xticksvisible = false,
yticksvisible = false,
yticklabelsvisible = false,
xticklabelsvisible = false,
title = "Partial correlation"))
Colorbar(fig[1, 2], hm)
ax, hm = CairoMakie.heatmap(fig[2, 1], reg_sens.standard_regression,
figure = (resolution = (300, 200),),
axis = (xticksvisible = false,
yticksvisible = false,
yticklabelsvisible = false,
xticklabelsvisible = false,
title = "Standard regression"))
Colorbar(fig[2, 2], hm)
fig
```
```julia
using StableRNGs
_rng = StableRNG(1234)
morris_sens = gsa(f1, Morris(), bounds, rng = _rng)
fig = Figure(resolution = (300, 200))
scatter(fig[1, 1], [1, 2, 3, 4], morris_sens.means_star[1, :],
color = :green, axis = (xticksvisible = false,
xticklabelsvisible = false, title = "Prey (Morris)"))
scatter(fig[1, 2], [1, 2, 3, 4], morris_sens.means_star[2, :],
color = :red, axis = (xticksvisible = false,
xticklabelsvisible = false, title = "Predator (Morris)"))
fig
```
## Citing
If you use this software in your work, please cite:
```bib
@article{dixit2022globalsensitivity,
title={GlobalSensitivity. jl: Performant and Parallel Global Sensitivity Analysis with Julia},
author={Dixit, Vaibhav Kumar and Rackauckas, Christopher},
journal={Journal of Open Source Software},
volume={7},
number={76},
pages={4561},
year={2022}
}
```