Conversation
…uture.R (set in config); use all outputs in production to aid in development of multi-crop workflow
…add change since start as delta_<variable> to standard output; aggregate output to monthly means
no longer load renv in .Rprofile; hard code path to renv libraries in .Renviron
Revise mixed_system_prototype.qmd for clarity and to fix incorrect labels.
Co-authored-by: Chris Black <[email protected]>
…on density and stock and mask counties that cumulatively contribute <1% of total (consider this below detection limit given uncertainty)
…y and stock, save variable importance results; add logging and memory tracking
…qmd` from `downscaling_report.qmd` - Updated `040_downscale.R` to improve naming conventions and ensure training covariate matrices are saved correctly. - Refactor `041_aggregate_to_county.R` to streamline the aggregation process and improve readability. - Enhance `042_downscale_analysis.R` to load predictions and covariates, compute variable importance, and generate plots for partial dependence, ALE, and ICE effects using the `iml` package. - Improved logging.
62d0577 to
a2e81d8
Compare
… guidance for setting crs
…with different coordinates
Co-authored-by: Chris Black <[email protected]>
…dd PDP if vars are uncorrelated
There was a problem hiding this comment.
thanks @divine7022 and @infotroph ! I've addressed inline suggestions, should be wrapping up shortly.
|
@divine7022 finished addressing your suggestions. Coding style improvements
Clarified (scripts/031_aggregate_sipnet_output.R — AGB vs SOC baseline (annual_init))
"Why “100% woody + 50% annual” as canonical EFI export?"
"current approach assumes linear additivity, but mixed systems have non-linear interactions ?"
|
…ch with a warning so failures are visible in test logs
…torization works correctly, (2) edge case where annual_init == annual_value (delta = 0), and (3) the +/- 0.1% tolerance boundary for woody_cover in incremental mode; to improves confidence in edge case handling
divine7022
left a comment
There was a problem hiding this comment.
Thank you for your substantial effort on this PR, LGTM, this has been a long standing PR; we can merge this and address any remaining refinements in follow up iterations
|
for remaining open comment, I added a TODO to fix the OOB validation to evaluate spatial extrapolation. |
Update downscaling to support multiple PFTs including mixed systems, with demonstration of orchard + ground cover. Combine reports into webpage and publish to gh-pages.
combine_mixed_crops.Rfor mixed‐PFT aggregationggsave_optimized.Rto streamline plot saving; use svg and webp to reduce size and increase loading speedmatch_site_ids_by_location.Rto match site‐IDs based on lat/lonREADME.mdwith Quarto build/publish instructions_quarto.yml,index.qmd, and expanded docs (docs/,reports/) for a full Quarto‐powered websitedocs/workflow_documentation.mdfor clarity.Rprofilefor consistent repository messaging000-config.R, includin usingargparsefor development vs. production modesR/scripts