Reducing Uncertainties in Estimates of Organic Carbon Sequestration Rates of Temperate Inland Wetland Soils Using Statistical Learning Techniques
Bibliographic record
Abstract
Wetlands play an integral role as natural climate solutions due to their potential to sequester carbon dioxide (CO₂) from the atmosphere. However, myriad factors influence the spatial heterogeneity of organic carbon (OC) sequestration rates, necessitating techniques to reduce uncertainty in these rates if they are to guide policy decisions to meet national climate action targets. In this study, we combined expert knowledge with statistical learning techniques to derive place-based estimates of OC sequestration rates for wetlands on agricultural landscapes. Expert knowledge revealed complex relationships between process controls and OC sequestration rates, including carbon quantity, carbon quality, bulk density, cation exchange capacity, aggregate reactivity, redox potential, and temperature for wetlands. GIS and remotely sensed data were used as proxies for these process controls, which, along with field-based OC sequestration rates, were input into a statistical learning-based random forest (RF) model. This RF model predicted OC sequestration rates within reasonable error bounds, achieving adjusted coefficient of determination (R²) of 0.93, a mean absolute error of 0.05 Mg ha -1 yr -1 , and a root mean square error of 0.08 Mg ha -1 yr -1 . The variable importance analysis indicated that human impact index, various soil properties, and inundation probability were the most influential variables. Our findings suggest that statistical learning-based models grounded in an understanding of process controls and their interactions can reliably estimate OC sequestration rates, providing essential data to inform policy development and implementation for managing wetlands as natural climate solutions.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 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".