@prefix dcat: <http://www.w3.org/ns/dcat#> .
@prefix dct: <http://purl.org/dc/terms/> .
@prefix foaf: <http://xmlns.com/foaf/0.1/> .
@prefix vcard: <http://www.w3.org/2006/vcard/ns#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947> a dcat:Dataset ;
    dct:description """The Postcode Context Classification provides a national measure of urban spatial structure from high-resolution satellite imagery derived by cutting-edge convolutional neural network (CNN) techniques. By harnessing the power of the European Space Agency’s Copernicus Sentinel-2 satellites, combined with georeferenced postcodes, this data product offers unparalleled insights into the built environment across Great Britain.\r
\r
Theses data presents a new method of measuring local context that could be flexibly applied within different settings to meet several definitions of neighbourhood. While the method is implemented within the context of Great Britain, given the global coverage of satellite imagery, the approach can also be applied to any location in the world. The limits of the technique are centred around the resolution of the satellite data used and the interaction between the geography of the input data and the learned structure.\r
\r
## Content\r
\r
This data are open to access, available below as ‘Data: Cluster Labels’. Detailed descriptions of the clusters are available through the pen portraits. A FAQ sheet is also provided. For detailed description of the columns contained within the data, see the Variable Dictionary; and for an overview of the characteristics of the data, see the Data Summary. These files can be downloaded from the bottom of this page.\r
\r
## Quality, Representation and Bias\r
\r
The source data was subject to intense cleaning to prepare for classification. These techniques may introduce biases. Please see the published paper in the 'Related Content' section for full details.""" ;
    dct:identifier "3e2d3588-2d12-4a59-9b8c-a18f8d093947" ;
    dct:issued "2024-11-28T14:44:59.914560"^^xsd:dateTime ;
    dct:modified "2025-06-05T08:29:07.577842"^^xsd:dateTime ;
    dct:publisher <https://data.geods.ac.uk/organization/70965cee-2ecf-46bc-afd1-3f79ec275c5c> ;
    dct:title "Postcode Context Classification" ;
    dcat:contactPoint [ a vcard:Organization ;
            vcard:fn "Alex Singleton" ;
            vcard:hasEmail <mailto:data@geods.ac.uk> ] ;
    dcat:distribution <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/1e7333e7-0bb6-4738-80da-237b7782f06e>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/3e4a913e-e2e5-430e-9f3d-51e4659d4b9b>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/43fb1d9a-631f-4c2f-af95-e9600d4787ac>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/56969884-9183-4e40-a1ac-8f146fb48a5a>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/582f6678-a540-429e-9c4a-a78400c868d3>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/6ce00149-232c-4e51-a950-fe4c57619179>,
        <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/f2fa53f3-baee-4663-896b-e59483436e0c> ;
    dcat:keyword "imagery and earth cover",
        "postcode",
        "urban form",
        "urban function" ;
    dcat:landingPage <Sentinel-2> .

<Sentinel-2> a foaf:Document .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/1e7333e7-0bb6-4738-80da-237b7782f06e> a dcat:Distribution ;
    dct:format "CSV" ;
    dct:issued "2024-11-28T14:46:41.793418"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206513"^^xsd:dateTime ;
    dct:title "Variable Dictionary" ;
    dcat:accessURL <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/1e7333e7-0bb6-4738-80da-237b7782f06e/download/pcc_variabledesc.csv> ;
    dcat:byteSize "96"^^xsd:nonNegativeInteger ;
    dcat:mediaType "text/csv" .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/3e4a913e-e2e5-430e-9f3d-51e4659d4b9b> a dcat:Distribution ;
    dct:format "HTML" ;
    dct:issued "2024-11-28T14:59:57.281035"^^xsd:dateTime ;
    dct:modified "2025-06-05T08:29:07.582617"^^xsd:dateTime ;
    dct:title "Map: Mapmaker" ;
    dcat:accessURL <https://mapmaker.geods.ac.uk/#/postcode-context-classification> .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/43fb1d9a-631f-4c2f-af95-e9600d4787ac> a dcat:Distribution ;
    dct:format "HTML" ;
    dct:issued "2024-11-28T14:51:49.940259"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206655"^^xsd:dateTime ;
    dct:title "Paper: Alex Singleton, Dani Arribas-Bel, John Murray, Martin Fleischmann, Estimating generalized measures of local neighbourhood context from multispectral satellite images using a convolutional neural network, Computers, Environment and Urban Systems, Volume 95, 2022, 101802, ISSN 0198-9715" ;
    dcat:accessURL <https://doi.org/10.1016/j.compenvurbsys.2022.101802> .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/56969884-9183-4e40-a1ac-8f146fb48a5a> a dcat:Distribution ;
    dct:format "PDF" ;
    dct:issued "2024-11-28T14:46:08.990271"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206363"^^xsd:dateTime ;
    dct:title "Flyer: Postcode Classification.pdf" ;
    dcat:accessURL <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/56969884-9183-4e40-a1ac-8f146fb48a5a/download/postcode-classification.pdf> ;
    dcat:byteSize "401672"^^xsd:nonNegativeInteger ;
    dcat:mediaType "application/pdf" .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/582f6678-a540-429e-9c4a-a78400c868d3> a dcat:Distribution ;
    dct:description """Q: What is the main objective of the research presented in the paper?\r
A: The research develops a new national measure of urban spatial structure, focusing on the built environment through innovative analysis of high-resolution satellite-derived imagery using a convolutional neural network.\r
\r
Q: What data sources were used for measuring local spatial structure?\r
A: High-resolution multispectral imagery from the European Space Agency’s Copernicus Sentinel 2 satellites and georeferenced postcodes from the Office for National Statistics.\r
\r
Q: How was the convolutional neural network model designed and trained?\r
A: The model, a convolutional autoencoder (CAE), was trained to compress the dimensionality of the satellite data, preserving discriminative features of the area surrounding each GB postcode.\r
\r
Q: What method was used to represent the salient context of the data?\r
A: A k-means clustering algorithm was applied to the latent vectors produced by the CAE, identifying postcodes with similar characteristics.\r
\r
Q: What was the outcome of the national classification of context case study?\r
A: The study produced a classification covering the full extent of Great Britain, identifying different urban and rural areas with distinct characteristics in the Liverpool City Region.\r
\r
Q: What are the main conclusions and future research directions from this study?\r
A: The study introduced a novel method to extract local contextual measures from satellite data. It suggests further exploration in the use of higher resolution data and different geographic extents to improve model performance and representation of urban context.\r
\r
""" ;
    dct:format "TXT" ;
    dct:issued "2024-11-28T14:46:27.666425"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206440"^^xsd:dateTime ;
    dct:title "Contextual Note: Frequently Asked Questions" .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/6ce00149-232c-4e51-a950-fe4c57619179> a dcat:Distribution ;
    dct:description """The classification for each postcode.\r
\r
""" ;
    dct:format "CSV" ;
    dct:issued "2024-11-28T14:45:46.460525"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206257"^^xsd:dateTime ;
    dct:title "Data: Cluster Labels" ;
    dcat:accessURL <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/6ce00149-232c-4e51-a950-fe4c57619179/download/pcc.csv> ;
    dcat:byteSize "17875241"^^xsd:nonNegativeInteger ;
    dcat:mediaType "text/csv" .

<https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/f2fa53f3-baee-4663-896b-e59483436e0c> a dcat:Distribution ;
    dct:description """Including pen portraits (cluster names and descriptions).\r
\r
""" ;
    dct:format "CSV" ;
    dct:issued "2024-11-28T14:47:06.948212"^^xsd:dateTime ;
    dct:modified "2025-05-05T23:08:39.206585"^^xsd:dateTime ;
    dct:title "Data Summary" ;
    dcat:accessURL <https://data.geods.ac.uk/dataset/3e2d3588-2d12-4a59-9b8c-a18f8d093947/resource/f2fa53f3-baee-4663-896b-e59483436e0c/download/pcc_datasummary.csv> ;
    dcat:byteSize "2470"^^xsd:nonNegativeInteger ;
    dcat:mediaType "text/csv" .

<https://data.geods.ac.uk/organization/70965cee-2ecf-46bc-afd1-3f79ec275c5c> a foaf:Agent ;
    foaf:name "GeoDS" .