The currency of the data is;GB Overview Maps - 12/2014MiniScale - 01/2015OS 250K Raster - 06/2014Vector Map District Raster - 09/2014StreetView - 10/2014The coverage of the map service is GB.The map projection is British National Grid.The service is appropriate for viewing down to a scale of approximately 1:5,000.Updated: 10/04/2015

Slick, quick vector maps for use as a customisable, contextual base, with a focus on web and mobile apps.

Benefit from unrivalled levels of detail in your web or mobile app. OS Vector Tile API contains OS MasterMap Topography Layer including building heights.

Integrate Ordnance Survey's up-to-date, detailed maps in your applications, enabling you to make location-based decisions with confidence. You can customise the content and style to make your perfect map.

OS Open Raster stack of GB for use as base mapping from national scale through to street level data.The currency of the data is: GB Overview Maps - 12/2014 MiniScale - 01/2024 OS 250K Raster - 06/2024Vector Map District Raster - 05/2024Open Map Local Raster - 10/2024The coverage of the map service is GB. The map projection is British National Grid. The service is appropriate for viewing down to a scale of approximately 1:2,500. Updated: 29/10/2024

OS NGD API – Tiles offers you a vector tile service powered by the OS National Geographic Database (OS NGD). It provides a detailed and customisable basemap based on the latest OGC API – Tiles standard to help you create stunning and interactive web maps. It can be used with most web mapping libraries, including OpenLayers, MapLibre GL JS and Leaflet. A major benefit of vector tiles is that they are optimised for use across the internet and are great for building interactive web maps that allow users to zoom, pan, rotate, tilt and more.

As of the July 2021 basemap update, the raster basemaps (OS Open Carto, Background, Greyscale and Greyscale Labels) have now entered Mature Support. These four services will no longer be updated but will remain available to use for the foreseeable future. We encourage users to switch to the new GB Vector Basemaps. Read more in our blog.The OS Open Greyscale map service is designed to be used as background mapping providing a seamless map view from small to large scales with a consistent cartographic representation.The sources of data are Ordnance Survey Vector Map District and Open Map Local. The currency of the data is; Vector Map District - 05/2021Open Map Local - 04/2021 The coverage of the map service is GB. The map projection is British National Grid. The service is appropriate for viewing down to a scale of approximately 1:5,000. Updated: 17/07/2021

🇬🇧 영국

As of the July 2021 basemap update, the raster basemaps (OS Open Carto, Background, Greyscale and Greyscale Labels) have now entered Mature Support. These four services will no longer be updated but will remain available to use for the foreseeable future. We encourage users to switch to the new GB Vector Basemaps. Read more in our blog.The OS Open 'Carto' base map is designed to be used as background mapping providing a seamless map view from small to large scales with a consistent cartographic representation. The sources of data are Ordnance Survey Vector Map District data for small and mid-scales and Open Map Local for larger scales. The currency of the data is; Vector Map District - 05/2021Open Map Local - 04/2021The coverage of the map service is GB. The map projection is British National Grid. The service is appropriate for viewing down to a scale of approximately 1:2,500. Updated: 17/07/2021

🇬🇧 영국

This dataset links together all NEXTMap products by OS Grid tile - e.g. the sn60 directory brings together links various products from the OS Grid covering the Bristol Channel. These data products are on various resolutions and include the following products:

Difference model (dsm - dtm) Data Digital Surface Model (DSM) Data Digital Terrain 10m resolution (DTM10) Model Data Digital Terrain 50m resolution (DTM10) Model Data Digital Terrain (DTM) Model Data
Enhanced Digital Terrain (DTME) Model Data Orthorectified Radar Image (ORI)

The LIDAR DTM (Digital Terrain Model) Time Stamped Tiles product is an archive of raster elevation data produced by the Environment Agency. Site specific LIDAR surveys have been carried out across England since 1998, with certain areas, such as the coastal zone, being surveyed multiple times. Data is available at varying resolutions of 25cm, 50cm, 1m and 2m, depending on project requirements. The DTM (Digital Terrain Model) is produced from the last return LIDAR signal. We remove surface objects from the Digital Surface Model (DSM), using bespoke algorithms and manual editing of the data, to produce a terrain model of just the surface. Available to download as GeoTiff rasters in 5km zipfiles, data is presented in metres, referenced to Ordnance Survey Newlyn and data aligned to the OS Grid. All LIDAR data has a vertical accuracy of +/-15cm RMSE. The transformation used on the data is specific to the time period of survey. Please refer to the metadata index catalogue which show, for any location, what time stamped data is available, the specific dates of survey, resolution of product and what transformation and geoidal model used. Attribution statement: © Environment Agency copyright and/or database right 2020. All rights reserved.

This tile layer contains the GB Base OS Outdoor style which is based on the style provided by the Ordnance Survey. The labels are in local language providing Welsh, Scottish Gaelic and local English names where they are available. The web map version of this dataset can be seen here.The cartography is similar to the that provided by the Ordnance Survey in their stylesheets on Github for the OS Zoomstack data. The GB Os Outdoors tile layer was updated simply by changing the "text-field" value for a few layers in the map from '_name' to '_name_local'. This service contains data supplied by the Ordnance Survey in their Zoomstack product (data last updated June 2025) The map projection is British National Grid.Customise this MapBecause this is a vector tile layer, you can customise the map to change its content and symbology. You are able to turn on and off layers and change their symbols. You can open this style in the vector tile style editor, make your changes and save a copy of your modified style to use yourself.Please send any feedback to VectorTiles@esriuk.com

A spatial tiling index designed for storage of file-based image and other raster (i.e., LiDAR elevation, landcover) data sets. An irregular grid of overlapping polygons, each enclosing its respective Public Land Survey System (PLSS) township in an orthogonal polygon minimally encompassing all portions of that township, i.e., minimum bounding rectangle. The amount of overlap between adjacent tiles varies depending on the geometry of the underlying township. Currently extended to include all townships within or partially within King County as well as those townships in the southwestern portion of Snohomish County included within King County's ESA/SAO project area. The name of the spatial index is derived from the acronym (I)n(D)e(X) (P)olygons for (T)ownship-(R)ange, (M)inimum (B)ounding (R)ectangle, or idxptrmbr. Tile label is the t(township number)r(range number)as in t24r02. The meridian zone identifiers, N for townships and E for range is inferred as this index is intended as a local index for ease of use by the majority of users of GIS data. Lowercase identifiers are used for consistency between Unix and Windows OS storage. This index or tile level is the primary user-access level for most LiDAR elevation, orthoimagery and high-resolution raster landcover data. However, not all image and raster data is stored at the tiling level if a given data's resolution does not justify storing the data as multiple tiles.

Map, visualise, and truly understand your data at street level. The most detailed street-level open data vector mapping product available, OS Open Map – Local is a great backdrop over which to display and analyse your data.

Quickly identify hotspots in data like crime location or property prices. The muted colours of this detailed backdrop map let your information really stand out. Get greater insights into land use for local planning. OS OpenMap - Local doesn't just pinpoint schools, hospital and other major facilities, it maps the grounds they occupy.

Includes a raster image option, carefully styled in the light of customer feedback. This is easy to load in a GIS and lets you start analysing quicker. Easily get national coverage of Britain at 1:10:000 scale. Download the vector and raster versions of this data as single zip files. if you only need a smaller area, we’ll still offer the single-tile option.

Map, visualise, and truly understand your data at street level. The most detailed street-level open data vector mapping product available, OS Open Map – Local is a great backdrop over which to display and analyse your data. Quickly identify hotspots in data like crime location or property prices. The muted colours of this detailed backdrop map let your information really stand out. Get greater insights into land use for local planning. OS OpenMap - Local doesn't just pinpoint schools, hospital and other major facilities, it maps the grounds they occupy. Includes a raster image option, carefully styled in the light of customer feedback. This is easy to load in a GIS and lets you start analysing quicker. Easily get national coverage of Britain at 1:10:000 scale. Download the vector and raster versions of this data as single zip files. if you only need a smaller area, we’ll still offer the single-tile option.

Egyszerű, gyors vektoros térképek testreszabható, kontextuális alapként való használatra, különös tekintettel a webes és mobilalkalmazásokra.

Profitáljon a webes vagy mobilalkalmazás páratlan részletességéből. Az OS Vector Tile API tartalmazza az OS MasterMap topográfiai réteget, beleértve az épületmagasságokat is.

Integrálja az Ordnance Survey naprakész, részletes térképeit alkalmazásaiba, így magabiztosan hozhat helyalapú döntéseket. Testreszabhatja a tartalmat és a stílust, hogy tökéletes térképet készítsen.

# FireSR Dataset

## Overview

**FireSR** is a dataset designed for the super-resolution and segmentation of wildfire-burned areas. It includes data for all wildfire events in Canada from 2017 to 2023 that exceed 2000 hectares in size, as reported by the National Burned Area Composite (NBAC). The dataset aims to support high-resolution daily monitoring and improve wildfire management using machine learning techniques.

## Dataset Structure

The dataset is organized into several directories, each containing data relevant to different aspects of wildfire monitoring:

- **S2**: Contains Sentinel-2 images.
- **pre**: Pre-fire Sentinel-2 images (high resolution).
- **post**: Post-fire Sentinel-2 images (high resolution).

- **mask**: Contains NBAC polygons, which serve as ground truth masks for the burned areas.
- **pre**: Burned area labels from the year before the fire, using the same spatial bounds as the fire events of the current year.
- **post**: Burned area labels corresponding to post-fire conditions.

- **MODIS**: Contains post-fire MODIS images (lower resolution).

- **LULC**: Contains land use/land cover data from ESRI Sentinel-2 10-Meter Land Use/Land Cover (2017-2023).

- **Daymet**: Contains weather data from Daymet V4: Daily Surface Weather and Climatological Summaries.

### File Naming Convention

Each GeoTIFF (.tif) file is named according to the format: `CA_

### Directory Structure

The dataset is organized as follows:

```
FireSR/
│
├── dataset/
│ ├── S2/
│ │ ├── post/
│ │ │ ├── CA_2017_AB_204.tif
│ │ │ ├── CA_2017_AB_2418.tif
│ │ │ └── ...
│ │ ├── pre/
│ │ │ ├── CA_2017_AB_204.tif
│ │ │ ├── CA_2017_AB_2418.tif
│ │ │ └── ...
│ ├── mask/
│ │ ├── post/
│ │ │ ├── CA_2017_AB_204.tif
│ │ │ ├── CA_2017_AB_2418.tif
│ │ │ └── ...
│ │ ├── pre/
│ │ │ ├── CA_2017_AB_204.tif
│ │ │ ├── CA_2017_AB_2418.tif
│ │ │ └── ...
│ ├── MODIS/
│ │ ├── CA_2017_AB_204.tif
│ │ ├── CA_2017_AB_2418.tif
│ │ └── ...
│ ├── LULC/
│ │ ├── CA_2017_AB_204.tif
│ │ ├── CA_2017_AB_2418.tif
│ │ └── ...
│ ├── Daymet/
│ │ ├── CA_2017_AB_204.tif
│ │ ├── CA_2017_AB_2418.tif
│ │ └── ...
```

### Spatial Resolution and Channels

- **Sentinel-2 (S2) Images**: 20 meters (Bands: B12, B8, B4)
- **MODIS Images**: 250 meters (Bands: B7, B2, B1)
- **NBAC Burned Area Labels**: 20 meters (1 channel, binary classification: burned/unburned)
- **Daymet Weather Data**: 1000 meters (7 channels: dayl, prcp, srad, swe, tmax, tmin, vp)
- **ESRI Land Use/Land Cover Data**: 10 meters (1 channel with 9 classes: water, trees, flooded vegetation, crops, built area, bare ground, snow/ice, clouds, rangeland)

**Daymet Weather Data**: The Daymet dataset includes seven channels that provide various weather-related parameters, which are crucial for understanding and modeling wildfire conditions:

| Name | Units | Min | Max | Description |

|------|-------|-----|-----|-------------|

| dayl | seconds | 0 | 86400 | Duration of the daylight period, based on the period of the day during which the sun is above a hypothetical flat horizon. |

| prcp | mm | 0 | 544 | Daily total precipitation, sum of all forms converted to water-equivalent. |

| srad | W/m^2 | 0 | 1051 | Incident shortwave radiation flux density, averaged over the daylight period of the day. |

| swe | kg/m^2 | 0 | 13931 | Snow water equivalent, representing the amount of water contained within the snowpack. |

| tmax | °C | -60 | 60 | Daily maximum 2-meter air temperature. |

| tmin | °C | -60 | 42 | Daily minimum 2-meter air temperature. |

| vp | Pa | 0 | 8230 | Daily average partial pressure of water vapor. |

**ESRI Land Use/Land Cover Data**: The ESRI 10m Annual Land Cover dataset provides a time series of global maps of land use and land cover (LULC) from 2017 to 2023 at a 10-meter resolution. These maps are derived from ESA Sentinel-2 imagery and are generated by Impact Observatory using a deep learning model trained on billions of human-labeled pixels. Each map is a composite of LULC predictions for 9 classes throughout the year, offering a representative snapshot of each year.

| Class Value | Land Cover Class |

|-------------|------------------|

| 1 | Water |

| 2 | Trees |

| 4 | Flooded Vegetation |

| 5 | Crops |

| 7 | Built Area |

| 8 | Bare Ground |

| 9 | Snow/Ice |

| 10 | Clouds |

| 11 | Rangeland |

## Usage Tutorial

To help users get started with FireSR, we provide a comprehensive tutorial with scripts for data extraction and processing. Below is an example workflow:

### Step 1: Extract FireSR.tar.gz

```bash
tar -xvf FireSR.tar.gz
```

### Step 2: Tiling the GeoTIFF Files

The dataset contains high-resolution GeoTIFF files. For machine learning models, it may be useful to tile these images into smaller patches. Here's a Python script to tile the images:

```python
import rasterio
from rasterio.windows import Window
import os

def tile_image(image_path, output_dir, tile_size=128):
with rasterio.open(image_path) as src:
for i in range(0, src.height, tile_size):
for j in range(0, src.width, tile_size):
window = Window(j, i, tile_size, tile_size)
transform = src.window_transform(window)
outpath = os.path.join(output_dir, f"{os.path.basename(image_path).split('.')[0]}_{i}_{j}.tif")
with rasterio.open(outpath, 'w', driver='GTiff', height=tile_size, width=tile_size, count=src.count, dtype=src.dtypes[0], crs=src.crs, transform=transform) as dst:
dst.write(src.read(window=window))

# Example usage
tile_image('FireSR/dataset/S2/post/CA_2017_AB_204.tif', 'tiled_images/')
```

### Step 3: Loading Data into a Machine Learning Model

After tiling, the images can be loaded into a machine learning model using libraries like PyTorch or TensorFlow. Here's an example using PyTorch:

```python
import torch
from torch.utils.data import Dataset
from torchvision import transforms
import rasterio

class FireSRDataset(Dataset):
def _init_(self, image_dir, transform=None):
self.image_dir = image_dir
self.transform = transform
self.image_paths = [os.path.join(image_dir, f) for f in os.listdir(image_dir) if f.endswith('.tif')]

def _len_(self):
return len(self.image_paths)

def _getitem_(self, idx):
image_path = self.image_paths[idx]
with rasterio.open(image_path) as src:
image = src.read()
if self.transform:
image = self.transform(image)
return image

# Example usage
dataset = FireSRDataset('tiled_images/', transform=transforms.ToTensor())
dataloader = torch.utils.data.DataLoader(dataset, batch_size=16, shuffle=True)
```

## License

This dataset is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You are free to share and adapt the material as long as appropriate credit is given.

## Contact

For any questions or further information, please contact:
- Name: Eric Brune
- Email: ebrune@kth.se

WWNP Combined Woodland Planting Potential is our best estimate of locations where tree planting may be possible on the floodplain, close to flow pathways and across the wider catchment. It is made up of three layers:WWNP Floodplain Woodland Planting Potential is our best estimate of locations where tree planting on the floodplain may be possible, and effective to attenuate flooding. The dataset is designed to support signposting of areas of floodplain not already wooded. The dataset is based upon fluvial Flood Zone 2 of the Flood Map for Planning. A set of open access constraints data was used to erase areas which contained existing woodland, watercourses, peat, roads, rail and urban locations.The information provided is largely based on modelled data and open constraints data, and is therefore indicative rather than specific. Locations identified may have more recent building or land use than available data indicates. It is important to note that land ownership and change to flood risk have not been considered, and it may be necessary to model the impacts of significant planting.The Environment Agency’s Flood Map for Planning (2016) - Flood Zone 2 (0.1% AEP) was used to delineate areas close to the watercourse in the floodplain which may be suitable for tree planting. The ‘Woodland Constraints’ data was then applied, masking existing woodland, watercourses, peat, roads, rail and urban areas.WWNP Riparian Woodland Potential is our best estimate of locations where tree planting may be possible on smaller floodplains close to flow pathways, and effective to attenuate flooding. The dataset is designed to support signposting of riparian areas not already wooded. The dataset is based upon a 50m buffer of available OS Open Data river networks. A set of open access constraints data was used to erase areas which contained existing woodland, watercourses, peat, roads, rail and urban locations.The information provided is largely based on open data, and is indicative rather than specific. Locations identified may have more recent building or land use than available data indicates. It is important to note that land ownership and change to flood risk have not been considered, and it may be necessary to model the impacts of significant planting.A 50m buffer was created around OS river network datasets to identify potential locations for riparian tree planting. This data used included: OS OpenMap - Surface Water Line, OS OpenMap - Surface Water Area and OS Open Rivers (2016). The ‘Woodland Constraints’ data was then applied, masking existing woodland, watercourses, peat, roads, rail and urban areas.WWNP Wider Catchment Woodland Potential is our best estimate of locations where there are slowly permeable soils, where scrub and tree planting may be most effective to increase infiltration and hydrological losses. The dataset is designed to support signposting of areas not already wooded. The dataset is based upon the 1:50k BGS geology survey, and relies upon identifying drift and bedrock geologies that are characteristic of slowly permeable soils. A set of open access constraints data was used to erase areas which contained existing woodland, watercourses, peat, roads, rail and urban locations.The information provided is largely based on a 100m gridded version of the BGS 1:50k superficial and bedrock data, along with open constraints data, and is indicative rather than specific. Locations identified may have more recent building or land use than available data indicates. It is important to note that land ownership and change to flood risk have not been considered, and it may be necessary to model the impacts of significant planting.The ‘Superficial Deposits’ and ‘Bedrock Geology’ themes from the BGS Geology 50k map data were used to identify areas of slowly permeable soils where tree planting may increase infiltration and hydrological losses. The ‘Woodland Constraints’ data was then applied, masking existing woodland, watercourses, peat, roads, rail and urban areas.

A spatial tiling index designed for storage of file-based image and other raster (i.e., LiDAR elevation, landcover) data sets. An irregular grid of overlapping polygons, each enclosing its respective Public Land Survey System (PLSS) township in an orthogonal polygon minimally encompassing all portions of that township, i.e., minimum bounding rectangle. The amount of overlap between adjacent tiles varies depending on the geometry of the underlying township. Currently extended to include all townships within or partially within King County as well as those townships in the southwestern portion of Snohomish County included within King County's ESA/SAO project area. The name of the spatial index is derived from the acronym (I)n(D)e(X) (P)olygons for (T)ownship-(R)ange, (M)inimum (B)ounding (R)ectangle, or idxptrmbr. Tile label is the t(township number)r(range number)as in t24r02. The meridian zone identifiers, N for townships and E for range is inferred as this index is intended as a local index for ease of use by the majority of users of GIS data. Lowercase identifiers are used for consistency between Unix and Windows OS storage. This index or tile level is the primary user-access level for most LiDAR elevation, orthoimagery and high-resolution raster landcover data. However, not all image and raster data is stored at the tiling level if a given data's resolution does not justify storing the data as multiple tiles.

Highly accurate, professionally designed, enterprise-grade maps available worldwide.

Maps that receive 5 million updates on average per day across the globe for reliable navigation and data visualization.

Vector Tile API Use the freshest, daily updated HERE map data through tiles containing vector data and customize the map style to support your user needs.

Personalize your maps Configure the look and feel of your map by changing color, icon size, width, length and other properties of objects such as buildings, land features and roads. Display it all at the desired zoom level.

Pre-rendered map images Pre-rendered map images in multiple styles, such as base and aerial, optimized for various devices and OS’s. Request an image around a specific area, or at a specified location and zoom level.

Map Tile API Display server-rendered, raster 2D map tiles at different zoom levels, display options, views and schemes. Request tiles that highlight congestion and environmental zones.

Built-in fleet maps Integrate maps designed especially for fleet management applications with accentuated country borders and highways, toll roads within congestion charging zones and highway exits along routes.

Truck attributes layer Provide simple visual cues so that areas with truck restrictions are easily identifiable. Display truck restrictions such as height, weight or environmental restrictions on a variety of map styles.

Map Feedback Offer your users the possibility to edit the HERE map or report errors.

These data are the urban woodland habitat networks of eleven different cities: Nottingham, Plymouth, Stoke-on-Trent, Milton Keynes, Coventry, Wolverhampton, Northampton, Birkenhead, Derby, Luton and Kingston-Upon-Hull.Three types of data are used to create the shape files:The OS MasterMap Topography (EDINA Digimap Ordnance Survey Service, 2024) ‘Natural Environment’ layer.This was overlain upon the latest version of the LandCover Map (EDINA Environment Digimap Service, 2022) for each urban area using QGIS (https://qgis.org/). Urban area boundaries were determined and clipped using the experimental urban extent polygons for the UK (ONS, 2019).ReferencesEDINA Digimap Ordnance Survey Service (2024) OS MasterMap® Topography Layer [GeoPackage geospatial data], Scale 1:1250, Tiles: GB, Updated: 1 February 2024, Ordnance Survey (GB). Available at: https://digimap.edina.ac.uk (Accessed: 10 July 2024).EDINA Environment Digimap Service (2022) Land Cover Map 2021 [FileGeoDatabase geospatial data], Scale 1:250000, Tiles: GB, Updated: 10 August 2022, CEH. Available at: https://digimap.edina.ac.uk (Accessed: 10 July 2024).ONS (2019) Experimental urban extent for UK - Office for National Statistics. Available at: https://www.ons.gov.uk/aboutus/transparencyandgovernance/experimentalurbanextentforuk (Accessed: 26 August 2024).