An adaptive mapping framework for the management of peat soils: a new Irish Peat Soils Map.
Bibliographic record
Abstract
Accurate mapping is necessary for effective management of peat soils to help reduce GHG emissions and improve environmental quality. However, mapping peat soils remains a major challenge: definitions of peat soils vary substantially, field data are sparse and difficult to produce, and remote sensing of limited use for converted peatlands. Using an Adaptive Mapping Framework developed for the Derived Irish Peat Map, this study describes our work to update the map with refined and new datasets. These include incorporation of areas considered to be underlain by shallow peat soils (≥ 10 cm and ≥ 8.6 % Organic Matter content), and augmentation of the overall test dataset with an additional ~ 20,000 points.The workflow for map generation employed 20 Decision Tree Output Maps (DTOMs), aggregated into 33 Map Combinations (MCs). The MC selected for the update had the highest accuracy metrics (≥ 80 %), consisting of DTOMs with a user accuracy ≥ 60 % and assessed over a minimum number of test points ≥ 50. The resulting map reveals peat to underlie 1.66 M ha of Ireland (~ 23.3 % of the country), with an overall accuracy of 84 % and a F1 score for peat areas of 85 %. This extent is 13.2 % larger than that delineated in previous versions and at least 18.8 % larger than areas presented in other previous maps. The methodology also allows transparency from which data sources the different peat layers of the new map are coming from and to distinguish different peat thickness ranges (≥ 10 cm, ≥ 30-40 cm).We demonstrate the utility of the mapping framework to facilitate the production of a more reliable peat map than previous mapping attempts. This approach has potential relevance for peat mapping elsewhere, in areas containing disparate datasets (e.g., land cover, soil map, etc.), covering different time periods, or employing different production methods. The accuracy metrics generated also suggest that the approach can be used as a basis for implementing or updating European and national regulations concerning carbon-rich soils in comparable settings to those encountered in Ireland.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".