Combining multi-spectral and thermal remote sensing to predict forest fire characteristics
Bibliographic record
Abstract
Forest fires preparedness strategies require the assessment of spatial and temporal variability of fire danger. While several tools have been developed to predict fire occurrence and behaviour from weather data, it is acknowledged that fire danger models may benefit from direct assessment of live fuel condition, as allowed by Earth Observation technologies. In this study, the performance of pre-fire observations of land surface temperature (LST) anomaly and of the Perpendicular Moisture Index (PMI) in predicting fire characteristics was evaluated against the Canadian Forest Fire Weather Index (FWI) System, a fire danger model adopted in several areas worldwide. To this purpose, a database of forest fires recorded in Campania (13,595 km2), Italy, was combined with MODIS retrievals of LST anomaly and PMI, and with FWI maps from NASA’s Global Fire Weather Database. Fires were grouped in decile bins of LST anomaly, PMI and FWI System components, and probability distribution functions of burned area, fire duration and rate of spread were fitted in each bin. The dependence of probability model parameters on LST anomaly, PMI and FWI System components was assessed by means of trend analysis (coefficient of determination and p-value of the linear fit, Sen’s slope and Mann-Kendall test) and likelihood ratio test versus the corresponding unconditional probability model. Finally, the probability of an extreme event, conditional to ignition, was modelled as a function of LST anomaly and PMI. Results show that the probability distribution function of burned area has a strong dependence on both LST anomaly and PMI, that the probability distribution function of fire duration has a strong dependence on LST anomaly but not on PMI, and that the probability distribution function of rate of spread has a weak dependence on LST anomaly and a strong dependence on PMI. These results are in line with expectations from models of the combustion and flames propagation processes. Trend analyses and likelihood ratio tests showed that the FWI System components are good predictors of burned area and fire duration, but not of rate of spread. They also confirmed that, where LST anomaly and PMI are covariates of the considered fire characteristic, their performance is similar or better than the FWI System components. Finally, the probability of an extreme event in terms of burned area as a joint function of LST anomaly and PMI shows a wider dynamic range than the same probability modelled as a function of these remote sensing variables individually.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 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 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".