gPC ROM generated using SparseGridCollocation with Gamma distribution is not working correctly

[wangcj05]

---

Issue Description

What did you expect to see happen?

The gPC ROM generated using SparseGridCollocation with Gamma distribution should generate similar results with MonteCarlo

What did you see instead?

The predicted value from gPC does not agree with the Code executions, the inputs are youngsModulus, and force. The outputs are disp_x, and disp_y.
Results from Code:

youngsModulus,force,disp_x,disp_y
176574.579712,-132.140792122,0.0254384584278,-0.172387649733
425755.525175,-7.85914919469,0.000627476268902,-0.0042521900282
190033.125005,-83.1397770671,0.0148717340472,-0.100780606935
210154.666871,-14.6123587696,0.00236354215596,-0.0160169091405
231284.205188,-43.5948157121,0.00640723917344,-0.0434196476773
267340.506387,-266.852951695,0.0339304257776,-0.229934780476

Results from gPC:

youngsModulus,force,disp_x,disp_y
176574.579712,-132.140792122,5.47380623359e-09,-3.70940949265e-08
425755.525175,-7.85914919469,1.40689665974e-10,-9.53405290966e-10
190033.125005,-83.1397770671,3.17405035702e-09,-2.15094433782e-08
210154.666871,-14.6123587696,4.97911911674e-10,-3.37417711342e-09
231284.205188,-43.5948157121,1.33521875082e-09,-9.04831646883e-09
267340.506387,-266.852951695,7.05075070558e-09,-4.7780503148e-08

If I change the Gamma distribution to Normal or using NDspline ROM with Monte Carlo, both will generate similar results compared to the code outputs.

Do you have a suggested fix for the development team?

I guss the problem is scaling/normalization factors for the polynomial coefficients.

Please attach the input file(s) that generate this error. The simpler the input, the faster we can find the issue.

tests.zip

---

For Change Control Board: Issue Review

This review should occur before any development is performed as a response to this issue.

• 1. Is it tagged with a type: defect or improvement?
• 2. Is it tagged with a priority: critical, normal or minor?
• 3. If it will impact requirements or requirements tests, is it tagged with requirements?
• 4. If it is a defect, can it cause wrong results for users? If so an email needs to be sent to the users.
• 5. Is a rationale provided? (Such as explaining why the improvement is needed or why current code is wrong.)

---

For Change Control Board: Issue Closure

This review should occur when the issue is imminently going to be closed.

• 1. If the issue is a defect, is the defect fixed?
• 2. If the issue is a defect, is the defect tested for in the regression test system? (If not explain why not.)
• 3. If the issue can impact users, has an email to the users group been written (the email should specify if the defect impacts stable or master)?
• 4. If the issue is a defect, does it impact the latest stable branch? If yes, is there any issue tagged with stable (create if needed)?
• 5. If the issue is being closed without a merge request, has an explanation of why it is being closed been provided?

[alfoa]

@wangcj05 @PaulTalbot-INL who is taking this?

[PaulTalbot-INL]

An email for the users should be drafted noting the problem and the fix.

[wangcj05]

@PaulTalbot-INL Here it is.

Proposed Email:

Dear Users,

We recently realized that there was a defect in the SparseGridCollocation Sampler when Gamma distribution as described in issue #693. This issue has been resolved with the PR #713 and the modification is currently available in the devel branch.

[alfoa]

Email accepted... and checklist passed...