Bibliographic record
Abstract
Abstract. Accurate monitoring of crop yield is important for ensuring food security. However, exiting yield datasets with a coarse spatial resolution are inadequate for capturing small scale spatial heterogeneity. Current yield estimation methods, such as machine learning models or the assimilation of remotely sensed biophysical variables into crop growth models, depend heavily on ground observations and involve significant computational costs. To solve these problems, a hybrid framework coupling the World Food Studies Simulation Model (WOFOST) and the Gated Recurrent Unit model (GRU) was proposed to generate a 20 m soybean yield dataset in Northeast China from 2019 to 2023 (NortheastChindaSoybeanYield20m). A soybean growth dataset was first generated based on the WOFOST that simulated various production scenarios (climates, crop varieties, soil types and agro-managements). The GRU model was then trained for characterizing relationships between model simulated LAI and soybean yield. The trained model was then applied for soybean yield estimation in Northeast China using time series LAI of different growth stages derived from Sentinel-2. The accuracy of the dataset was evaluated by in-situ measured and statistical data. The overall accuracy was 287.44 kg ha-1 and 272.36 kg ha-1 in the root mean squared error (RMSE) for field and regional scale, respectively. Stable results were achieved through the years with mean relative error (MRE) on average of 11.46 % in municipal scale and 7.94 % in provincial scale. Results demonstrated that the model was able to capture spatial-temporal variation of soybean yield. The NortheastChinaSoybeanYield20m was able to capture spatial-temporal variation of soybean yield, which can be applied for optimizing soybean production distribution and guiding agricultural decision-making. The NortheastChinaSoybeanYield20m dataset can be downloaded from https://doi.org/10.5281/zenodo.14263103 (Xu et al., 2024).
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 | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.019 | 0.010 |
| Insufficient payload (model declined to judge) | 0.307 | 0.257 |
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".