The lost historic woodland 1891-1914 (AI predicted) dataset for England shows land where woodland was mapped between approximately 1891 and 1914 but is no longer present. The dataset has been generated using an artificial intelligence (AI) model applied to historic 2nd edition Ordnance Survey (OS) maps and provides an indication of the extent and type of historic woodland. This historic woodland has been compared to the 2024 version of the National Forest Inventory (NFI) to see where areas of woodland no longer survive. The dataset is intended to support the development of forestry projects, analysis, interpretation and decision making by providing an indication of where historic woodland was mapped but no longer exists. It can help inform strategy, planning and research. To use this data appropriately, it may be necessary to apply additional quality assurance, filtering or validation processes.
Historic OS map tiles were processed and analysed using an image segmentation model trained to recognise woodland symbols and patterns initially within Wales. The model was trained using manually labelled historic OS map data and designed to detect different types of woodland based on their cartographic representation. Comparison was then made between these detections and the 2024 NFI to see which areas of woodland survive and which areas of woodland had been ‘lost’ since 1891-1914.
Access to the historic mapping used in this dataset was provided by the National Library of Scotland. The dataset was developed in partnership between the Welsh Government Data Science Unit and the Forestry Commission. The AI predictions were subject to post processing to create a consistent, usable national dataset for England published under an Open Government Licence.
The dataset consists of polygons representing areas where woodland was mapped on historic OS maps but no longer exists according to the 2024 NFI. Each polygon includes confidence scores that indicate how strongly the model predicts the presence of different woodland types that previously existed within that area.
In some cases, more than one woodland type may be associated with a single polygon, reflecting uncertainty or mixed woodland characteristics in the underlying historic map.
Woodland types included in the dataset are:
• broadleaf
• brushwood
• bushes
• conifer
• mixed woodland
• orchard
• osiers
This dataset is derived from the predictions of an AI model and therefore includes a degree of uncertainty. It does not necessarily represent a definitive or complete record of lost historic woodland and should not be interpreted as such.
Accuracy is influenced by the quality and consistency of the underlying historic OS maps, as well as the ability of the AI model to correctly interpret different map symbols. Some areas of England have lower map quality or use alternative symbology, which can affect prediction accuracy.
The outputs should not be relied on in isolation and should be interpreted alongside other available evidence, including modern datasets, local records and specialist knowledge. To use this data appropriately, it may be necessary to apply additional quality assurance, filtering or validation processes. Therefore, the dataset is not suitable for precise measurement of lost woodland extent or for use in statutory or regulatory decisions without supporting evidence or acknowledgement of these limitations. Attribution statement: © Forestry Commission & Ordnance Survey copyright and/or database right 2026. All rights reserved.
