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

<https://data.amerigeoss.org/dataset/75c26bf0-c475-4c13-8782-744c110dda58> a dcat:Dataset ;
    dct:description "Multiple modeling frameworks were used to predict daily temperatures at 0.5m depth intervals for a set of diverse lakes in the U.S. states of Minnesota and Wisconsin. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added physical constraint for energy conservation as a loss term. These models were pre-trained with uncalibrated Process-Based model outputs (PB0) before training on actual temperature observations." ;
    dct:identifier "USGS:5d915cb2e4b0c4f70d0ce523" ;
    dct:issued "2025-11-22T18:17:49.355453"^^xsd:dateTime ;
    dct:modified "20200820"^^xsd:gYear ;
    dct:publisher <https://data.amerigeoss.org/organization/727dbdd5-3f98-4ac0-9d28-5e344558139b> ;
    dct:spatial [ a dct:Location ;
            locn:geometry "POLYGON ((-89.4837 43.0771, -89.4837 43.1520, -89.3674 43.1520, -89.3674 43.0771, -89.4837 43.0771))"^^gsp:wktLiteral ] ;
    dct:title "Process-guided deep learning water temperature predictions: 5a Lake Mendota detailed prediction data" ;
    dcat:contactPoint [ a vcard:Organization ;
            vcard:fn "Jordan S. Read" ;
            vcard:hasEmail <mailto:jread@usgs.gov> ] ;
    dcat:distribution <https://data.amerigeoss.org/dataset/75c26bf0-c475-4c13-8782-744c110dda58/resource/024566f2-e3bd-4172-af99-07f9f8b71545>,
        <https://data.amerigeoss.org/dataset/75c26bf0-c475-4c13-8782-744c110dda58/resource/89b4d920-3186-4277-9fe8-42e89bff87ed> ;
    dcat:keyword "007",
        "012",
        "amerigeo",
        "amerigeoss",
        "ckan",
        "climate-change",
        "deep-learning",
        "environment",
        "geo",
        "geoss",
        "hybrid-modeling",
        "inlandwaters",
        "machine-learning",
        "modeling",
        "national",
        "north-america",
        "reservoirs",
        "temperate-lakes",
        "temperature",
        "thermal-profiles",
        "united-states",
        "us",
        "usgs-5d915cb2e4b0c4f70d0ce523",
        "water",
        "wi",
        "wisconsin" ;
    dcat:theme <%7Bgeospatial%7D> .

<https://data.amerigeoss.org/dataset/75c26bf0-c475-4c13-8782-744c110dda58/resource/024566f2-e3bd-4172-af99-07f9f8b71545> a dcat:Distribution ;
    dct:description "The metadata original format" ;
    dct:format "XML" ;
    dct:issued "2022-07-28T20:59:17.423868"^^xsd:dateTime ;
    dct:modified "2025-11-22T18:17:49.340925"^^xsd:dateTime ;
    dct:title "Original Metadata" ;
    dcat:accessURL <https://data.usgs.gov/datacatalog/metadata/USGS.5d915cb2e4b0c4f70d0ce523.xml> ;
    dcat:mediaType "text/xml" .

<https://data.amerigeoss.org/dataset/75c26bf0-c475-4c13-8782-744c110dda58/resource/89b4d920-3186-4277-9fe8-42e89bff87ed> a dcat:Distribution ;
    dct:description "Landing page for access to the data" ;
    dct:format "XML" ;
    dct:issued "2022-07-28T20:59:17.423878"^^xsd:dateTime ;
    dct:modified "2025-11-22T18:17:49.341328"^^xsd:dateTime ;
    dct:title "Digital Data" ;
    dcat:accessURL <http://dx.doi.org/10.5066/P9AQPIVD> ;
    dcat:mediaType "application/http" .

<https://data.amerigeoss.org/organization/727dbdd5-3f98-4ac0-9d28-5e344558139b> a foaf:Agent ;
    foaf:name "US Migrating" .