AAFC annual crop inventory
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Understanding the state and trends in agriculture production is essential to combat both short-term and long-term threats to stable and reliable access to food for all, and to ensure a profitable agricultural sector. In 2007, Agriculture and Agri-Food Canada (AAFC) took its first steps towards the development of an operational software system for mapping the crop types of individual fields using satellite observations. Focusing on the Prairie Provinces in 2009 and 2010, a Decision Tree (DT) based methodology was applied using optical (Landsat-5, AWiFS, DMC, SPOT) and radar (Radarsat-2) imagery. For the 2011 growing season and further years, this activity is extended to other provinces in support of a national crop inventory. At present, this approach can consistently deliver a crop inventory that meets the overall target accuracy of at least 85% at a final spatial resolution of 30m. To achieve full operational status, however, further development is required to optimize the data processing chain. Crop maps covering Canada's entire agricultural region are typically delivered eight months following the end of the growing season. To better meet the needs of AAFC and its partners, as well as those of potential new users, map delivery needs to be more timely. Indeed, there is considerable demand for two map products: an estimated within-season inventory (released during the growing season) as well as a final end-of-season inventory (released shortly after the end of the growing season). To this end, Earth Observation Service (EOS) staff is implementing a new and fully automated crop classifier that should significantly reduce production time. In 2012, the lack of affordable optical data forced AAFC to rely mostly on RADARSAT-2 data. This brings new challenges, given a doubling of the number of images as compared to 2011. In the coming years, new EO data (Landsat 8, Radarsat Constellation Mission, Sentinel-2) will have a significant positive impact on the quality of the AAFC crop inventory.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.014 | 0.023 |
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 it