<?xml version="1.0" encoding="UTF-8"?>

<?xml-stylesheet type="text/xsl" href="/static/oaitohtml.xsl"?>

<!--
<?xml-stylesheet type="text/xsl" href="/oaitohtml.xsl"?>
-->

<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
    <responseDate>2026-10-13T18:56:20Z</responseDate>
    <request verb="GetRecord" metadataPrefix="oai_dc" identifier="10.57760/sciencedb.36169" >https://www.scidb.cn/oai</request>
<GetRecord>
    <record>
    <header >
    <identifier>10.57760/sciencedb.36169</identifier>
    <datestamp>2026-07-24T17:41:52Z</datestamp>
</header>
    <metadata>
        
<oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:date>2026-07-24</dc:date>
  <dc:title>TPHH: A long-term (1901--2023) high-resolution (1/30&amp;deg;) near-surface humidity dataset for the Tibetan Plateau generated via spatial downscaling based on hybrid-structure deep learning</dc:title>
  <dc:identifier>doi:10.57760/sciencedb.36169</dc:identifier>
  <dc:language>en</dc:language>
  <dc:description># TPHH Dataset: Long-term High-resolution Meteorological Reconstruction over the Tibetan Plateau (1901-1978)## OverviewThis dataset (TPHH v1.0) provides reconstructed monthly meteorological fields over the Tibetan Plateau at a high spatial resolution (1/30 degree x 1/30 degree, approx. 3 km x 3 km) for the extended period of 1901&amp;ndash;2023. The reconstruction is generated using a FourCastNet-based deep learning framework, fusing the long-term historical consistency of CRU TS 4.08 with the high-resolution spatial patterns of the modern TPMFD dataset.And this dataset also provides spatial evaluation metrics outputs from two experimental settings: a baseline model (No-DEM Input) and a model with DEM input. Furthermore, based on the No-DEM model, it also provides long-term trend analyses and climate mutation tests.This dataset accompanies the paper:&amp;nbsp;&amp;quot;TPHH: A long-term (1901&amp;ndash;2023) high-resolution (1/30&amp;deg;) near-surface humidity dataset for the Tibetan Plateau generated via spatial downscaling based on hybrid-structure deep learning&amp;quot;&amp;nbsp;## File Description1. **TPHH_1901-1978_monthly.nc**&amp;nbsp;&amp;nbsp;- Content: The main reconstructed historical dataset.&amp;nbsp;&amp;nbsp;- Period: Jan 1901 - Dec 1978.&amp;nbsp;&amp;nbsp;- Format: NetCDF4.&amp;nbsp;&amp;nbsp;- Resolution: 1/30 degree (~3 km).2. **TPHH_validation_1979-2023_monthly.nc**&amp;nbsp;&amp;nbsp;- Content: The reconstruction results for the modern period (validation set) generated via K-Fold cross-validation.&amp;nbsp;&amp;nbsp;- Period: Jan 1979 - Dec 2023.&amp;nbsp;&amp;nbsp;- Use case: For validation and comparison purposes.3. **TPHH_1901_2023.nc**&amp;nbsp;&amp;nbsp;- Content: The complete 123-year reconstructed historical dataset (Model without DEM input).&amp;nbsp;&amp;nbsp;- Period: Jan 1979 - Dec 2023.&amp;nbsp;&amp;nbsp;- Use case: For reconstruction,&amp;nbsp;validation and comparison purposes.4. **TPHH_1901_2023_dem.nc**&amp;nbsp;&amp;nbsp;- Content: The complete 123-year reconstructed historical dataset (Model with DEM input).&amp;nbsp;&amp;nbsp;- Period: Jan 1901 - Dec 2023.&amp;nbsp;&amp;nbsp;- Use case: For reconstruction, validation and comparison purposes.5. **TPHH_monthly_output_and_tpmfd_maps_1979_2023.nc**&amp;nbsp;&amp;nbsp;- Content: The cross-validation outputs (Model without DEM input) paired with the original TPMFD target maps for the modern period.&amp;nbsp;&amp;nbsp;- Period: Jan 1979 - Dec 2023.&amp;nbsp;&amp;nbsp;- Use case: For validation and comparison purposes.6. **TPHH_monthly_output_and_tpmfd_maps_1979_2023_dem.nc**&amp;nbsp;&amp;nbsp;- Content: The cross-validation outputs (Model with DEM input) paired with the original TPMFD target maps for the modern period.&amp;nbsp;&amp;nbsp;- Period: Jan 1979 - Dec 2023.&amp;nbsp;&amp;nbsp;- Use case: For validation and comparison purposes.7. **Metrics_30yr.zip**- Content: NetCDF files containing gridded spatial evaluation metrics (RMSE, MAE, R&amp;sup2;, IOA) calculated over different 30-year climatological windows (e.g., 1979-2008, 1994-2023). Includes comparisons between No-DEM and DEM outputs.8. **Monthly_Panel_Trends_30yr.zip**- Content: NetCDF files containing gridded spatial linear trend patterns computed over 30-year periods, revealing regional warming or wetting/drying tendencies.9. **Pettitt_Mutation_30yr.zip**- Content: NetCDF files containing the results of the Pettitt test, designed to detect abrupt climate shifts (mutations) at the grid scale over 30-year windows.10. **Auxiliary_Data.zip**&amp;nbsp;&amp;nbsp;- Contains the static DEM file, study area boundary shapefiles (TPBoundary_HF), and sample data used for the model inference code.## VariablesThe NetCDF files contain the following variables:| Variable Name | Description | Unit || :--- | :--- | :--- || **temp** | 2 m Air Temperature | K || **shum** | 2 m Specific Humidity | Kg/kg || **pres** | Surface Pressure | hPa || **time** | Time coordinate | Months since 1901-01-01 || **lat/lon** | WGS84 coordinates | Degrees |## Coordinate System- Projection: WGS 84 (EPSG:4326)- Spatial Extent: Tibetan Plateau (Lat: 25.75&amp;deg;-41.2&amp;deg;N, Lon: 72&amp;deg;-105.65&amp;deg;E).- Resolution: 1/30 degree x 1/30 degree (~3 km x 3 km)## Usage Notes- The data is provided in monthly means.## LicenseCreative Commons Attribution 4.0 International (CC-BY 4.0).</dc:description>
  <dc:subject> Tibetan Plateau;  Meteorology; Climate Reconstruction; Deep Learning; FourCastNet; TPHH</dc:subject>
  <dc:creator>Zezhou Chen</dc:creator>
  <dc:rights>PUBLIC</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/</dc:rights>
  <dc:type>dataset</dc:type>
  <dc:relation>http://www.doi.org/10.5194/essd-2026-180</dc:relation>
  <dc:publisher>Science Data Bank</dc:publisher>
</oai_dc:dc>

    </metadata>
</record>
</GetRecord>
</OAI-PMH>