Interpretable Models Capture the Complex Relationship Between Climate Indices and Fire Season Intensity in Maritime Southeast Asia
Bibliographic record
Abstract
There have been many extreme fire seasons in Maritime Southeast Asia (MSEA) over the last two decades, a trend which will likely continue or accelerate due to climate change. Fires, in turn, are a major driver of atmospheric carbon monoxide (CO) variability, especially in the Southern Hemisphere. Here we attempt to maximize the amount of CO variability that can be explained via human-interpretable statistical models that use only climate mode indices as predictor variables. We expand upon previous work through the complexity at which we study the connections between climate mode indices and atmospheric CO (a proxy for fire intensity). Specifically, we present three modeling advancements. First, we analyze five different climate modes at a weekly timescale, which increases explained variability by 15% over models on a monthly timescale. Second, we accommodate multiple lead times for each climate mode index, finding that some indices have very different effects on CO at different lead times. Finally, we model the interactions between climate mode indices at weekly timescales, which provides a framework for studying these interactions at a higher level of complexity than previous work. Furthermore, we perform a stability analysis and show that our model for the MSEA region is robust, which adds weight to the scientific interpretation of the selected model terms. We believe that the complex relationships quantified here will be useful for scientists studying modes of variability in MSEA and for forecasters looking to maximize the information they glean from climate modes.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".