County-level corn yield prediction using supervised machine learning
Bibliographic record
Abstract
The main objectives of this study are (1) to compare several machine learning models to predict county-level corn yield in the study area and (2) to compare the feasibility of machine learning models for in-season yield prediction. We acquired remotely sensed vegetation indices data from moderate resolution imaging spectroradiometer using the Google Earth Engine (GEE). Vegetation indices for a span of 15 years (2006–2020) were processed and downloaded using GEE for the months corresponding to crop growth (April–October). We compared nine machine learning models to predict county-level corn yield. Furthermore, we analyzed the in-season yield prediction performance using the top three machine learning models. The results show that partial least square regression (PLSR) outperformed other machine learning models for corn yield prediction by achieving the highest training and testing performance. The study area’s top three models for county-level corn yield prediction were PLSR, support vector regression (SVR) and ridge regression. For in-season yield prediction, the SVR model performed comparatively well by achieving testing R2 = 0.875. For in-season corn yield prediction, SVR outperformed other models. The results show that machine learning models can predict both in-season yield (best model R2 = 0.875) and end-of-season yield (best model R2 = 0.861) with satisfactory performance. The results indicate that remote sensing data and machine learning models can be used to predict crop yield before the harvest with decent performance. This can provide useful insights in terms of food security and early decision making related to climate change impacts on food security.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".