THE RESULT
What the data shows
The largest computed metric is 1,384 for 6,5; the smallest is 0 for 5,5. Metric: hectares (Recorded hectares).
Coordinates are local source grid indices, not geographic coordinates. Repeated observations may describe related events.
| x | y | records | hectares | median hectares | cell |
|---|---|---|---|---|---|
| 6 | 5 | 49 | 1,384.05 | 2.14 | 6,5 |
| 8 | 6 | 52 | 1,265.30 | 1.175 | 8,6 |
| 7 | 4 | 45 | 474.4 | 1.38 | 7,4 |
| 2 | 2 | 25 | 462.6 | 0 | 2,2 |
| 4 | 4 | 36 | 397.4 | 1.42 | 4,4 |
| 4 | 5 | 25 | 287 | 0 | 4,5 |
| 1 | 2 | 19 | 219.9 | 0 | 1,2 |
| 6 | 3 | 25 | 192.8 | 0 | 6,3 |
| 8 | 8 | 1 | 185.8 | 185.8 | 8,8 |
| 9 | 4 | 4 | 185.6 | 39.16 | 9,4 |
| 4 | 3 | 22 | 172.9 | 2.345 | 4,3 |
| 1 | 3 | 10 | 157.1 | 3.025 | 1,3 |
THE METHOD
From source to answer
Grid-cell counts, sums and medians without inventing latitude or longitude.
The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.
THE NEXT DECISION
What follows from the finding
Obtain land-area exposure and event identifiers before using this as a spatial risk map.
Where the conclusion stops
The sample consists of recorded fire observations, not all places and times at risk. Zero recorded area is not evidence of no ignition. No precise dates or event identifiers are supplied. This is not an emergency forecasting system.
Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.