Development of a Satellite-Based Forest Fire Danger Forecasting System and its Implementation Over the Forest Dominant Regions in Alberta, Canada
Bibliographic record
Abstract
Forest fire is a natural phenomenon in many ecosystems across the world. One of the most important components of forest fire management is forecasting of fire danger conditions. My aim was to develop a daily-scale forest fire danger forecasting system (FFDFS) using remote sensing inputs over the northern part of Canadian province of Alberta during 2009-2011 fire seasons. In this research, I critically analyzed the current operational fire danger forecasting systems and other remote sensing-based methods in order to determine the knowledge gaps. In general, the operational systems use point-based measurements of meteorological variables and generate danger maps upon employing interpolation techniques. It is possible to overcome the uncertainty associated with the interpolation techniques by using remote sensing data. It was observed that most of the fire danger monitoring systems focused on determining the danger during and/or after the period of image acquisition, thus unable to forecast the fire danger accurately. A limited number of studies were conducted to forecast fire danger conditions, which could be adaptable. In this thesis, I developed FFDFS’s useful for mid-term (i.e., 8-day) and daily-scale forecasting. The newly developed 8-day scale FFDFS uses Moderate Resolution Imaging Spectroradiometer (MODIS)-derived 8-day composite of surface temperature (TS), normalized multiband drought index (NMDI), and normalized difference vegetation index (NDVI). In order to eliminate the data gaps in the input variables, I propose a gap-filling technique that considered both of the spatial and temporal dimensions. The input variables were calculated during the i period and then integrated to forecast the danger conditions into four categories during the i + 1 period. I observed that 90.94% of the fire fell under ‘very high’ to ‘moderate’ danger classes when compared with Alberta Environment and Sustainable Resource Development (ESRD) fire spots. As regards to operational perspective, I opted to develop daily-scale FFDFS comprised of MODIS-derived 8-day composite of TS, NDVI, and NMDI; and daily precipitable water (PW). The TS, NMDI, and NDVI variables were calculated during i period and PW during j day; and then integrated to forecast fire danger conditions into five categories during j+1 day. Results were significant with 95.51% of fires in the ‘extremely high’ to ‘moderate’ danger classes. Therefore, I infer that the refined FFDFS approach developed using remote sensing variables has operational value and can be routinely incorporated into meteorological based fire forecasting systems. Therefore, I apprehend that FFDFS could be used as an operational one; and has the potential to supplement information to the operational meteorological-based forecasting systems.
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".