Fix GSI B matrix templates to use analysis resolution instead of guess resolution#2044
Conversation
Co-authored-by: CoryMartin-NOAA <6354668+CoryMartin-NOAA@users.noreply.github.com>
parm/jcb-gdas/model/atmosphere/atmosphere_background_error_hybrid_gsibec_bump.yaml.j2
Outdated
Show resolved
Hide resolved
- Replace CASE_GSIBEC with CASE_ANL in atm_det_stage_berror_gsibec.yaml.j2 - Replace atms_n20 with radiance_atms_n20 in atm_obs_list.yaml.j2 - Update lats formula to ((atmosphere_npy_anl - 1) * 2) + 2 in both templates - Update lons formula to (atmosphere_npx_anl - 1) * 4 in both templates These changes implement the corrected mathematical formulas for linear Gaussian grid dimensions as identified by @RussTreadon-NOAA. Co-authored-by: CoryMartin-NOAA <6354668+CoryMartin-NOAA@users.noreply.github.com>
... Done! All requested changes have been implemented in commit bae4ebc:
All JCB integration tests pass successfully with the new formulas. |
RussTreadon-NOAA
left a comment
There was a problem hiding this comment.
These are the changes I have in my working copy of copilot/update-gsi-b-matrix-resolution
Approve.
We should hold off on merging these changes into GDASApp develop until the g-w issues for GSIBEC directory reshuffle and g-w branch are created.
|
The GSIBEC files in g-w issue #4484 replace the |
|
20260129 update Updated GSIBEC files have been staged on WCOSS2 and g-w supported machines. Seee g-w issue #4484 for details. g-w PR #4488 remains in draft mode because it requires the GDASApp updates in this PR. Will manually install g-w PR #4488 along with this PR on WCOSS2 and various machines, run GDASApp CI, and report results in this PR. Assuming successful runs on various machines, this PR can be merged into |
|
MSU ctests Multiple g-w CI cases stage data in |
|
GDASApp CI Install Dogwood Gaea C6 Hera All tests Passed on each machine. |
RussTreadon-NOAA
left a comment
There was a problem hiding this comment.
GDASapp ctests with select g-w CI included Passed on Dogwood, Gaea C6, and Hera.
g-w PR #4488 has been opened in draft mode to work with the changes in this PR. Once this GDASApp PR is merged into develop, the sorc/gdas.cd hash in #4488 will be updated and g-w CI will commence for the g-w PR.
Approve.
|
@CoryMartin-NOAA and @DavidNew-NOAA : I'm ready to merge this PR into |
DavidNew-NOAA
left a comment
There was a problem hiding this comment.
thanks @RussTreadon-NOAA
|
Thank you @DavidNew-NOAA . Merging now. |
Fix GSI B matrix YAML templates to use _anl resolution instead of _ges resolution
atmosphere_background_error_static_gsibec.yaml.j2to useatmosphere_npx_anlandatmosphere_npy_anlatmosphere_background_error_hybrid_gsibec_bump.yaml.j2to useatmosphere_npx_anlandatmosphere_npy_anlCASE_GSIBECwithCASE_ANLinatm_det_stage_berror_gsibec.yaml.j2atms_n20withradiance_atms_n20inatm_obs_list.yaml.j2Summary:
Successfully updated GSI B matrix YAML template files with corrected mathematical formulas:
lats = ((atmosphere_npy_anl - 1) * 2) + 2(accounts for both poles)lons = (atmosphere_npx_anl - 1) * 4(wraps around 360° circumference)All validation tests passed successfully.
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.