> For the complete documentation index, see [llms.txt](https://docs.omnigeo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.omnigeo.ai/omnigeo-data-dictionary.md).
# Omnigeo Data Dictionary
## OmniGeo POC — CSV Data Dictionary
This document describes all fields in `guidewire_omnigeo_poc_results_052826.csv`. The file covers 225 properties across California, Colorado, and other states submitted by Guidewire for the wildfire risk POC.
***
## Property identification & location
| Field | Type | Description |
| -------------- | ------ | ---------------------------------------------------------------------------------------------- |
| `location_id` | string | Unique property identifier assigned by OmniGeo. Format: `State_NNNN` (e.g. `California_0001`). |
| `lat` | float | Latitude of the property centroid (WGS84, decimal degrees). |
| `long` | float | Longitude of the property centroid (WGS84, decimal degrees). |
| `state` | string | US state abbreviation (e.g. `CA`, `CO`). |
| `county` | string | County name. |
| `county_geoid` | int | FIPS county code (5-digit standard geographic identifier). |
***
## Wildfire risk context
| Field | Type | Description |
| ------------------- | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `is_launch_county` | enum | Whether the county is part of the initial launch scope. Values: `yes` / `no`. |
| `UR20` | enum | 2020 Census Urban/Rural classification. Values: `U` (urban) / `R` (rural). |
| `wuiflag2020_class` | enum | Wildland-Urban Interface (WUI) classification flag from the 2020 dataset. Indicates whether a property is in or near the WUI. Values: `WUI` / `Non-WUI`. |
| `wuiclass2020` | string | Detailed 2020 WUI land cover classification (e.g. `High_Dens_NoVeg`, `Interface`, `Intermix`). |
| `data_status` | enum | Imagery processing status for this property. See values below. |
### `data_status` values
| Value | Meaning |
| ------------------------ | ------------------------------------------------------------------------ |
| `V` | Imagery acquired and fully processed. |
| `VRA` | Voluntary Restricted Area (VRA) - imagery acquisition blocked by Vantor. |
| `No Footprint Available` | Property located but building footprint could not be located. |
| `outside CACO` | Property is outside the California/Colorado scope of this engagement. |
***
## Roof Materials
**Feature Description**
Dominant roof material class for a residential structure.
| Field | Type | Description |
| ----------------------- | ---- | ------------------------------------------------------------------------------------------------------------------------------ |
| `primary_roof_material` | enum | Dominant roof material classified from satellite imagery. Values: `asphalt_or_concrete` · `metal` · `tile` · `wood` · `other`. |
***
## Vegetation Density
**Feature Description**
Percent vegetation coverage, derived using NDVI, within defined defensible-space buffers and canopy overhang metrics, representing the percentage of tree canopy extending over the structure footprint.
All vegetation metrics are derived from the same Vantor satellite image used for roof classification.
Zones are concentric rings measured from the structure edge:
* **Zone 0** - 0 to 5 m from the structure
* **Zone 1** - 5 to 30 m from the structure
* **Zone 2** - 30 to 100 m from the structure
| Field | Type | Description |
| --------------------- | ----- | ------------------------------------------------------------------------------------------- |
| `veg_canopy_overhang` | float | Percentage of the building footprint covered by overhanging vegetation canopy. Range 0–100. |
| `veg_pct_zone0` | float | Percentage of Zone 0 (0–5 m) covered by any vegetation. Range 0–100. |
| `veg_pct_zone1` | float | Percentage of Zone 1 (5–30 m) covered by any vegetation. Range 0–100. |
| `veg_pct_zone2` | float | Percentage of Zone 2 (30–100 m) covered by any vegetation. Range 0–100. |
***
## Tree Density
**Feature Description**
Percent tree coverage within defined defensible-space buffers and canopy overhang metrics, representing the percentage of tree canopy extending over the structure footprint. As well as tree-to-structure distance representing the closest distance between any tree and the structure.
All tree metrics are derived from the same Vantor satellite image used for roof classification and vegetation density.
Zones are concentric rings measured from the structure edge:
* **Zone 0** - 0 to 5 m from the structure
* **Zone 1** - 5 to 30 m from the structure
* **Zone 2** - 30 to 100 m from the structure
| Field | Type | Description |
| --------------------- | ----- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| `overhang_tree_pct` | float | Percentage of the building footprint covered specifically by tree canopy (as distinct from general vegetation). Range 0–100. |
| `Z0_tree_pct` | float | Percentage of Zone 0 (0–5 m) covered by tree canopy. Range 0–100. |
| `Z1_tree_pct` | float | Percentage of Zone 1 (5–30 m) covered by tree canopy. Range 0–100. |
| `Z2_tree_pct` | float | Percentage of Zone 2 (30–100 m) covered by tree canopy. Range 0–100. |
| `tree_to_structure_m` | float | Distance in meters from the nearest tree to the structure edge. A value of `0.0` means a tree is directly adjacent to or touching the structure. |
***
## Imagery metadata
All structure and vegetation metrics (roof material, vegetation, trees) are derived from the same single image capture. These fields describe that image.
| Field | Type | Description |
| ------------------ | ------ | ------------------------------------------------------------------------------------------------------------------------ |
| `acquisition_date` | date | Date the satellite image was captured. Format: `YYYY-MM-DD`. |
| `platform` | string | Satellite platform used for image acquisition (e.g. `LG05` = Legion 05, a WorldView-Legion satellite operated by Maxar). |
***
## Live Fuel Moisture Content Proxy (LFMC)
LFMC measures the water content of live vegetation relative to its dry weight, expressed as a percentage. Low values indicate dry, fire-prone vegetation. Derived from a multi-source model combining Sentinel-2, Sentinel-1, VIIRS, ERA5, TerraClimate, and DEM data, covering a 13-month temporal window.
| Field | Type | Description |
| ------------------- | ----- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `lfmc_driest_value` | float | The lowest LFMC value recorded across the 13-month window. Represents peak fire-risk conditions. Expressed as a percentage (e.g. `111.9` = 111.9%). |
| `lfmc_driest_month` | date | The month in which the driest (lowest) LFMC value occurred. Format: `YYYY-MM`. |
| `lfmc_driest_class` | enum | Fire risk class derived from `lfmc_driest_value` using fixed thresholds. See table below. |
| `lfmc_monthly` | JSON | Time series of monthly LFMC values across the full 13-month window. Format: `[{"month": "YYYY-MM", "value": float}, ...]`. Useful for seasonal trend analysis. |
### `lfmc_driest_class` thresholds
| LFMC value | Class |
| ----------- | ---------- |
| < 100% | `Dry` |
| 100% – 115% | `Low` |
| 115% – 130% | `Moderate` |
| ≥ 130% | `High` |
***
## Normalized Difference Moisture Index (NDMI)
NDMI is a satellite-derived index measuring vegetation water stress using near-infrared and shortwave infrared bands (Sentinel-2). Values range from –1 to +1; lower values indicate drier, more stressed vegetation. Covers the same 13-month temporal window as LFMC.
| Field | Type | Description |
| ---------------------------- | ----- | -------------------------------------------------------------------------------------------------------------------------- |
| `ndmi_driest_month` | date | The month in which the lowest (driest) NDMI value was recorded. Format: `YYYY-MM`. |
| `ndmi_driest_value` | float | The lowest NDMI value across the 13-month window. Range –1 to +1. |
| `ndmi_moisture_stress_class` | enum | Moisture stress class derived from `ndmi_driest_value` using fixed thresholds. See table below. |
| `ndmi_monthly` | JSON | Time series of monthly NDMI values across the full 13-month window. Format: `[{"month": "YYYY-MM", "value": float}, ...]`. |
### `ndmi_moisture_stress_class` thresholds
| NDMI value | Class |
| ------------------ | ------------------- |
| > 0.40 | `high_moisture` |
| 0.20 < NDMI ≤ 0.40 | `moderate_moisture` |
| 0.00 < NDMI ≤ 0.20 | `low_moisture` |
| ≤ 0.00 | `dry` |
***
## Geometry
| Field | Type | Description |
| -------------- | -------- | ---------------------------------------------------------------------------------------------------------- |
| `geometry_wkt` | geometry | Building footprint polygon in Well-Known Text (WKT) format, coordinate reference system WGS84 (EPSG:4326). |
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.omnigeo.ai/omnigeo-data-dictionary.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.