Sunflower yield modeling with explainable artificial intelligence: Historical weather impacts across half a century of American production
Bibliographic record
Abstract
Abstract This study applies explainable artificial intelligence (XAI) to analyze the impact of inter‐year variation in weather conditions on yields of oilseed sunflower ( Helianthus annuus L.) across the United States. By integrating historical county‐level yield data from 1976 to 2022 with monthly meteorological data over the same period, we identified key weather predictors influencing sunflower yields at national and state levels along with critical yield‐sensitive threshold temperature and precipitation values that predict reduced yield. Across the sunflower production range, the most critical climate variables identified are July and August maximum temperatures and total precipitation, reflecting yield vulnerability to summer heat waves and drought during budding and flowering. Secondarily, overly cool temperatures during spring planting and establishment (May–June) reduce yields, as do overly cool end‐of‐season temperatures during seed maturation and harvest (September–October), indicating risk of frost or insufficient growing degree days to support plant development. Winter precipitation and temperatures were also detected as important to overall yield dynamics, in particular where wetter winters benefitted yields. Specific temperature and precipitation tipping points vary across the geographic extent of production, but align with existing agronomic knowledge. Our XAI approach enhances model transparency, offering valuable insights for farmers and policymakers to develop adaptive strategies for sunflower cultivation under climate change. Future research incorporating additional factors like soil characteristics and agricultural practices can further refine yield predictions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".