# 092. Burned-area concentration

**Question:** How much of the recorded burned area comes from the largest observations?

## Result

The largest computed metric is 1 for 1.0; the smallest is 0.4104 for 0.01. Metric: area_share (Share of recorded hectares).

A small number of large outcomes can dominate mean error; records are not guaranteed independent fire events.

![Burned-area concentration](outputs/chart.png)

| top_record_fraction | records | area_share |
| --- | --- | --- |
| 0.01 | 6 | 0.4104 |
| 0.05 | 26 | 0.6715 |
| 0.1 | 52 | 0.8051 |
| 0.2 | 104 | 0.914 |
| 0.5 | 259 | 0.9994 |
| 1 | 517 | 1 |

The chart shows 6 of 6 result rows; the table previews the first 6 in the analysis-defined order. [Download the full result table](outputs/results.csv). Numerical values are computed from the source; missing results stay unavailable.

## Method

Cumulative area shares at fixed top-observation fractions.

The study uses shared source preparation and reusable statistical routines. Its specific transformations are in [analysis.py](analysis.py), and common model/evaluation code is in [portfolio/methods.py](../../portfolio/methods.py). The [notebook](analysis.ipynb) executes the study and displays the saved results.

## Decision and limitations

Use the heavy-tailed outcome to choose regression metrics and uncertainty checks.

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 share observations or holdouts. These are focused analytical studies, not independent replications or deployed business systems. Any model refinements informed by these results need new untouched evaluation data. No commercial impact is inferred from an association or backtest.

## Reproduce

From the repository root, after installing `requirements.txt`:

```powershell
python projects/092-burned-area-concentration/analysis.py
```

Source data are downloaded automatically if absent. Original archives are retained unchanged and checked by SHA-256. The cleaned cache normalizes column names; field-specific changes are visible in [data preparation](../../portfolio/data.py). Runtime evidence is in [receipt.json](outputs/receipt.json).

## Source

[Forest Fires](https://archive.ics.uci.edu/dataset/162/forest+fires), Cortez and Morais (2007). [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Source data are transformed and aggregated in this study. [Source provenance](../../data/provenance/fires.json) and [prepared-data audit](../../data/provenance/fires_prepared.json) record the downloaded files, field coverage and hashes.