@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://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d> a dcat:Dataset ;
    dct:creator [ a foaf:Agent ;
            dct:type "person" ;
            vcard:hasEmail <mailto:jianboqi@gmail.com> ;
            foaf:homepage <https://source.coop/jianbo> ;
            foaf:name "Jianbo Qi" ] ;
    dct:description """# GNDC-HiGLASS-LS20\r
\r
GNDC-compressed version of **HiGLASS-LS20** — the first gap-free, 20 m, 5-day\r
LAI / FAPAR product over China (2018–2024), derived from integrated\r
Landsat-8/9 and Sentinel-2 Analysis Ready Data.\r
\r
Files are stored as `.gndc` (a neural data cube format; see GeoNDC reference\r
below) instead of GeoTIFF to reduce size. **A decoder is required to read them.**\r
\r
## Decode\r
\r
```bash\r
pip install pygndc\r
```\r
\r
Documentation: https://github.com/jianboqi/pygndc/blob/main/TUTORIAL.md\r
\r
### Minimal example\r
\r
```python\r
import pygndc\r
\r
# Decode a .gndc file. The output is already in PHYSICAL values\r
# (no scale factor needs to be applied).\r
data = pygndc.read("HiGLASS_LS20_n018e108_2020_v01_LAI.gndc")\r
\r
print(data.shape)   # (73, rows, cols) — 73 five-day composites\r
print(data[0])      # first composite (DOY 001), LAI in m² m⁻²\r
```\r
\r
> Note: after decoding, values are already physical (LAI in m² m⁻²,\r
> FAPAR unitless). Do **not** multiply by the scale factors below — those\r
> apply only to the raw uint8 GeoTIFF source and are listed for reference.\r
\r
## File naming\r
\r
```\r
GNDC-HiGLASS_LS20_[lat][lon]_[year]_v01_LAI.gndc\r
GNDC-HiGLASS_LS20_[lat][lon]_[year]_v01_FAPAR.gndc\r
```\r
\r
- Tiles are 1° × 1° (WGS84 / EPSG:4326), centred at integer degree + 0.5°\r
  (e.g. `n018e108` = 18.5°N, 108.5°E, covering ~18–19°N, 108–109°E).\r
- 73 bands per file = 5-day composites: DOY 001, 006, 011, …, 361\r
  (Jan 1, Jan 6, …, Dec 22).\r
\r
## Physical values & ranges\r
\r
| Variable | Range | Unit |\r
|----------|-------|------|\r
| LAI      | 0 – 10.0 | m² m⁻² |\r
| FAPAR    | 0 – 1.0  | unitless |\r
\r
(For reference, the original uint8 GeoTIFF used scale factors LAI ×0.1 and\r
FAPAR ×0.004. pygndc returns decoded data already in the physical ranges above.)\r
\r
## Extend to other regions (2019–2024)\r
\r
Open-source pipeline (Google Colab):\r
https://colab.research.google.com/drive/1zGYbUkh4COoZqpWA2tfMLZHVfsGZ1nAo\r
\r
## Citation\r
\r
**For the GNDC compression format / decoder:**\r
\r
Qi, J., M. Li, B. Jiang, Y. Chen, and Q. Wang (2026).\r
"GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation."\r
arXiv:2603.25037 [cs.CV]. https://arxiv.org/abs/2603.25037\r
\r
```bibtex\r
@misc{qi2026geondc,\r
  title={GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation},\r
  author={Jianbo Qi and Mengyao Li and Baogui Jiang and Yidan Chen and Qiao Wang},\r
  year={2026},\r
  eprint={2603.25037},\r
  archivePrefix={arXiv},\r
  primaryClass={cs.CV},\r
  url={https://arxiv.org/abs/2603.25037}\r
}\r
```\r
\r
**For the underlying HiGLASS-LS20 product:**\r
\r
Ma, H., Q. Wang, W. Li, Y. Chen, J. Xu, Y. Ma, J. Huang, and S. Liang (2025).\r
"The first gap-free 20 m 5-day LAI/FAPAR products over China (2018–2023) from\r
integrated Landsat-8/9 and Sentinel-2 Analysis Ready Data."\r
*Remote Sensing of Environment*, 331, 115048.\r
DOI: 10.1016/j.rse.2025.115048\r
\r
## Contact\r
\r
- Original product: Dr. Han Ma — mahan@hku.hk\r
- GNDC packaging & pygndc decoder: Jianbo Qi — jianboqi@bnu.edu.cn\r
""" ;
    dct:identifier "1acaeee8-04e0-5a11-8698-62c7a7738c1d" ;
    dct:issued "2026-06-15T17:54:23.887000+00:00"^^xsd:dateTime ;
    dct:modified "2026-06-15T17:58:33.450000+00:00"^^xsd:dateTime ;
    dct:publisher <https://mldata.opendata.ai/organization/441e8055-15d1-45a6-b961-412973905554> ;
    dct:title "GNDC-HiGLASS-LS20: Gap-free 20 m 5-Day LAI/FAPAR over China, 2018–2023" ;
    dcat:distribution <https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/80ecd993-8893-4882-b494-63ef9887fe41>,
        <https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/ba331cf5-d536-4808-aa31-68d5dab632d5>,
        <https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/c5b9e30b-e066-4943-b24a-68172d8465ad> .

<https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/80ecd993-8893-4882-b494-63ef9887fe41> a dcat:Distribution ;
    dct:format "GNDC" ;
    dct:issued "2026-06-18T14:07:35.275159"^^xsd:dateTime ;
    dct:modified "2026-06-18T14:07:35.272136"^^xsd:dateTime ;
    dct:title "HiGLASS_LS20_n036e117_2018-2023_v01_LAI-FPAR.gndc" ;
    dcat:accessURL <https://data.source.coop/jianbo/gndc-higlass-ls20/HiGLASS_LS20_n036e117_2018-2023_v01_LAI-FPAR.gndc> ;
    dcat:byteSize "381132536"^^xsd:nonNegativeInteger .

<https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/ba331cf5-d536-4808-aa31-68d5dab632d5> a dcat:Distribution ;
    dct:format "GNDC" ;
    dct:issued "2026-06-18T14:07:35.275155"^^xsd:dateTime ;
    dct:modified "2026-06-18T14:07:35.272047"^^xsd:dateTime ;
    dct:title "HiGLASS_LS20_n036e091_2018-2023_v01_LAI-FPAR.gndc" ;
    dcat:accessURL <https://data.source.coop/jianbo/gndc-higlass-ls20/HiGLASS_LS20_n036e091_2018-2023_v01_LAI-FPAR.gndc> ;
    dcat:byteSize "13107200"^^xsd:nonNegativeInteger .

<https://mldata.opendata.ai/dataset/1acaeee8-04e0-5a11-8698-62c7a7738c1d/resource/c5b9e30b-e066-4943-b24a-68172d8465ad> a dcat:Distribution ;
    dct:format "GNDC" ;
    dct:issued "2026-06-18T14:07:35.275147"^^xsd:dateTime ;
    dct:modified "2026-06-18T14:07:35.271932"^^xsd:dateTime ;
    dct:title "HiGLASS_LS20_n034e106_2018-2023_v01_LAI-FPAR.gndc" ;
    dcat:accessURL <https://data.source.coop/jianbo/gndc-higlass-ls20/HiGLASS_LS20_n034e106_2018-2023_v01_LAI-FPAR.gndc> ;
    dcat:byteSize "326675800"^^xsd:nonNegativeInteger .

<https://mldata.opendata.ai/organization/441e8055-15d1-45a6-b961-412973905554> a foaf:Agent ;
    foaf:name "Source Cooperative" .

