WUR-AI / WUR-AI/diffWOFOST

how to validate the results after introducing approximations

Open
#24 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

scientific
Dominant language
Python
Stars
25
Forks
6
Avg merge
2d 23h
Merged PRs (30d)
1

Description

When making wofost code differentiable, we need to check for look-up tables, hard thresholds, and mathematical operations on arrays. This might affect the results of wofost. We need to address the accuracy expectations for diffwofost compared to wofost. For example, should we consider tests passed if results are within, say, 10% relative difference? More? Less? See an example here. Also this comment and this comment.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the example in src/diffwofost/physical_models/crop/leaf_dynamics.py around lines 251–261, then review the linked discussion in pull request 12. Identify how lookup tables, hard thresholds, and array operations affect comparisons between diffWOFOST and WOFOST. Done means agreed accuracy expectations and validation tests or criteria that address the open relative-difference question.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, testing-qa
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.