A scalable fire danger index based on sentinel imagery
Bibliographic record
Abstract
The incidence of wildfires and megafires and their disastrous consequences is increasing all over the planet. According to the latest European Forest Fire Information System annual fire report, in 2021 alone wildfires burned a surface area more than twice the size of Luxembourg, including more than a thousand square kilometres of Natura 2000 protected areas. In addition, 2022 has registered the highest number of wildfires since 2006, and will also be recorded as one of the driest years on record. Assuming that the most efficient and cost-effective way limit the damage caused by wildfires consists in their prevention, building tools to allow the decision makers to allocate resources using state of the art technology and fresh data is of the utmost importance. To this end, the combined usage of data from weather and satellite platforms capable to provide data on a regional or national scale and at a high temporal frequency provides the optimal solution for assessing and monitoring the state of the vegetation. However, users of fire danger product users often complain about the resolution of the provided products. While moderate- or coarse-resolution products may be adequate to cover the regional or national scale, high-resolution products are required to properly describe the fire danger in relatively small-sized areas of high interest in fire danger modelling, such as wildland-urban interfaces, national parks or protected areas. Using a different fire danger product based on the spatial scale of the target may be impractical and increase the workload and training requirements for the personnel. For this reason, we propose a scalable fire danger index based on Sentinel imagery that is able to cover different spatial scales by exploiting the surface reflectances provided by different Sentinel products (i.e. Sentinel-2 and Sentinel-3). \n \nThis novel index, named Daily Fire Danger Index, exploits both weather and satellite data to estimate all the main variables of fire danger, such as the amount of dead fuel, moisture of the dead and live fuels, wind speed, evapotranspiration etc, and is calibrated using the historical records of wildfire occurrence in the target region. In particular, the live fuel moisture content is estimated using a state of the art procedure based on the inversion of radiative transfer models of the PROSAIL family. The index was tested in Sardinia, a region well-known for its proneness to wildfires and which is also regularly affected by megafires, and the performance comparison with the Canadian Fire Weather Index shows very significant improvements on the capability to discriminate fire danger even at a moderate resolution. Finally, the 2021 Planargia-Montiferru megafire was selected as a case study to showcase the added value of the high-resolution version of the index.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".