Modeling peat burned area and understanding its drivers with machine learning
Bibliographic record
Abstract
Peatland fires pose significant environmental and societal challenges. We recently advanced the Canadian Fire Weather Index (FWI) system for northern peatlands by integrating peatland-specific hydrological data derived from assimilating Soil Moisture and Ocean Salinity (SMOS) L-band brightness temperature observations into the NASA Catchment Land Surface model with its peatland modules, ‘PEATCLSM’. This novel FWIpeat (Mortelmans et al. 2024) was evaluated using satellite-based fire presence data over boreal peatlands from 2010 through 2018, demonstrating improved estimation of peatland fire presence.Here, we extend the use of this renewed FWIpeat system by integrating it into a machine learning framework to gain deeper insights into when, where, and why peatlands burn. We utilize an XGBoost algorithm trained on peatland burned area data from 2012-2023, incorporating a suite of predictors, including (i) peatland distribution characteristics, (ii) peatland groundwater table, (iii) lightning occurrence, (iv) meteorological data, (v) vegetation properties, and (vi) socio-economic factors. This approach enables proactive fire risk management strategies and contributes to a comprehensive assessment of peatland fire vulnerability and resilience. Preliminary results indicate the importance of peatland groundwater table and lightning occurrence in estimating peat burned area.Mortelmans, J., Felsberg, A., De Lannoy, G. J. M., Veraverbeke, S., Field, R. D., Andela, N., and Bechtold, M.: Improving the fire weather index system for peatlands using peat-specific hydrological input data, Nat. Hazards Earth Syst. Sci., 24, 445–464, https://doi.org/10.5194/nhess-24-445-2024, 2024.
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 | 0.000 | 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) | 0.000 | 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".