> For the complete documentation index, see [llms.txt](https://docs.os.uk/osngd/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.os.uk/osngd/using-os-ngd-data/os-ngd-structures/field-boundary/known-limitations.md).

# Known limitations

OS carries out a flying programme each year, capturing each area of Great Britain at least once every three years. The aerial imagery derived from this capture programme can be impacted by seasonal variances, that is, the time of year when the area was flown over, or even the time of day. Earlier in the year, vegetated features may be captured with 'leaf-off', and long shadows are also created which may impact the quality of the feature’s classification and its width measurements.

Additionally, the automated process uses aerial imagery as a top-down view to classify Field Boundary features, so some features may have their true nature obscured by overhanging trees. For example, fences running through woodland can be obscured by trees and can therefore be mistakenly classified as Tree Canopy.

Limitations exist with existing OS NGD Structure Lines, which are output in Field Boundary data:

1. Where the OS NGD Structure Line data is an ‘Edge or Limit’ of vegetation change rather than ‘Built Obstruction’, the Field Boundary is not classified.
2. Where features are close together and parallel (for example, a Ditch and a Hedge), the capture specification for OS NGD features will generalise and select one of the features; in this example, the Ditch rather than the Built Obstruction Line would be captured. This generalisation results in no Field Boundary features being classified and this can commonly occur in low-lying areas. Additionally, where Built Obstruction Lines are closely aligned, only one of these is picked up by the automated process and classified as a Field Boundary feature.
3. Moorland areas have a positional accuracy (RMSE) of 4.09m. The automated process has a search buffer of 2m to find potential vegetated Field Boundary features and 3m buffer for wall features. A search buffer any higher than this will result in numerous false positive classifications with the surrounding area; therefore, some features in Moorland areas may be inaccurately positioned.
4. Field Boundary features are classified through areas of woodland. This can occur when Built Obstruction Lines exist across areas of woodland and were classified when still visible from aerial imagery. Due to progressive changes in the natural environment, the trees have grown over time and obscured the underlying Built Obstruction Line. Classification from aerial imagery will always classify the Field Boundary feature as 'Tree Canopy’, even if in the real world the feature is actually a fence.

## Data quality 

There are known areas of Great Britain where the data quality may be lower. See the [OS NGD Improvements page](/osngd/os-ngd-news/os-ngd-improvements.md#march-2026-improvements-to-the-field-boundary-feature-type) for additional information.


---

# 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.os.uk/osngd/using-os-ngd-data/os-ngd-structures/field-boundary/known-limitations.md?ask=<question>&goal=<endgoal>
```

`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.