Comparing and evaluating digital soil mapping methods in a Hungarian forest reserve
Bibliographic record
Abstract
Illés, G., Kovács, G. and Heil, B. 2011. Comparing and evaluating digital soil mapping methods in a Hungarian forest reserve. Can. J. Soil Sci. 91: 615–626. To investigate applications of widespread digital soil mapping methods in forestry management, soil maps for a Hungarian forest reserve were developed using general discriminant and classification tree analysis as predictive tools. Soil samples were collected applying an unaligned semi-systematic grid. Second level units of the World Reference Base of Soil Resources and their yield capacity were determined. Terrain attributes were derived using a digital elevation model, and they were assigned to soil data to be used as predictors for second level units of the World Reference Base for Soil Resources (SLU) maps. A comparison was made of prediction accuracy. Both the discriminant analysis and the classification tree-based prediction were able to derive SLU maps; however, the classification accuracies were uneven. The methods used provided 63–65% average classification accuracy for dominant SLUs, but only 0–18% in the case of less common SLUs. One of the major issues of digital soil mapping that needs to be addressed is that the same inputs may result in different output maps depending on the use of spatial predictions. To overcome this problem we created a new combination of these methods in which the classification accuracies were used to select the most appropriate prediction. For each location, the method that gave higher prediction accuracy was used to extend the soil map to unknown areas. In this way we improved the overall accuracy of output maps as well as the prediction accuracies of individual SLUs.
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 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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| 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 teacher head, 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".