bcgov / bcgov/BGCprojections

Variable selection for final model

Open
#15 0 comments 0 reactions 0 assignees View on GitHub
Type: Workflow
Dominant language
R
Stars
1
Forks
0
PR merge metrics
No merged PRs in 30d

Description

- Define different variable sets, and test the effect of these decisions on final BGC projections.
- [ ] Baseline simple variable set (Tmax/Tmin/PPT)
- [ ] Expert set of variables included in Courtney's most recent models (selected by Will)
- [ ] Local variable selection
- [ ] Kitchen sink approach - ALL variables
- [ ] Sensitivity analysis to see how much it matters which variables are included

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are named. Start by locating the existing BGC projection workflow, then map where variable sets enter the final model. Done means the baseline, expert, local-selection, and kitchen-sink sets have been tested and their projection effects compared through a sensitivity analysis.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.