Developing a phenology- and pixel-based algorithm for mappingrapeseed at 10 m spatial resolution using multi-source data
Bibliographic record
Abstract
Abstract. As a major oilseed crop, large-scale and high-resolution maps of rapeseed (Brassica napus L.) are critical for predicting annual production and ensuring global energy security. However, such free maps are still unavailable in large areas. We designed a new pixel- and phenology-based algorithm and produced a new data product for rapeseed planting area (2017–2019) over 33 countries at 10-m spatial resolution based on the multiple data. The product showed a good consistence (R2 = 0.88) with the official statistics (Food and Agricultural Organization of the United Nations, FAO) at national level. Rapeseed maps achieved at least 0.81 F1-scores of spatial consistency when comparing with the Cropland Data Layer (CDL) of America, Annual Crop Inventory (ACI) in Canada and Crop Map of England (CROME) in England. Moreover, their F1-scores ranged 0.84–0.92 based on the independent validation samples, implying a good consistency with ground truth. Furthermore, we found that rapeseed crop rotation is ≥2 years in almost all countries. Our derived maps with high accuracy suggest the robustness of pixel- and phenology-based algorithm in identifying rapeseed over large regions with various climate and landscapes. The derived rapeseed planting areas freely downloaded can be applied to predict rapeseed production and optimize planting structure. The product is available publicly at http://dx.doi.org/10.17632/ydf3m7pd4j.3 (Han et al., 2021).
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".