Dataset · Tabular regression
alaska-arctic-hydrology-matrix
by Abdullah Ashraf abdullahashraf122/alaska-arctic-hydrology-matrix
The Alaska Arctic Hydrology Harmonization Matrix is a multi-source geospatial hydro-climatic dataset containing 50,000 spatial coordinate vectors sampled across sub-arctic and hydrological basins.
Dataset Card
By Abdullah Ashraf, published under cc-by-4.0, revision d51ed99e12a1.
Alaska Arctic Hydrology Harmonization Matrix
Dataset Summary
The Alaska Arctic Hydrology Harmonization Matrix is a multi-source geospatial hydro-climatic dataset containing 50,000 spatial coordinate vectors sampled across sub-arctic and hydrological basins. It unifies digital elevation models (DEM), permanent surface water occurrence percentages, seasonal water transition classifications, historical rainfall averages, and human demographic proxies into an aligned tabular feature matrix.
This dataset was generated in-house via the LocalDataHarmonizer engine in ALASKA_SANDBOX, utilizing high-throughput spatial sampling algorithms (rasterio.sample.sample_gen) to extract raster values at exact coordinate centroids.
Dataset Structure
- Total Records: 50,000
- Format: Apache Parquet
- Primary Split:
train
Feature Columns
| Column Name | Type | Unit / Description | Source Raster / Archive |
|---|---|---|---|
lat |
float64 | Latitude coordinates (decimal degrees) | Spatial coordinate grid |
lon |
float64 | Longitude coordinates (decimal degrees) | Spatial coordinate grid |
hydro_elevation |
float64 | Hydrographic topographic elevation (meters ASL) | HydroSHEDS 15-arcsec DEM (hyd_as_dem_15s.tif) |
water_occurrence_pct |
float64 | Historical surface water occurrence frequency (%) | JRC Global Surface Water (occurrence_80E_30Nv1_4_2021.tif) |
water_transition_class |
float64 | Seasonal water transition class code | JRC Global Surface Water Transitions |
historical_rainfall_avg |
float64 | Long-term annual mean precipitation (mm) | IMD Historical Rainfall Series |
pop_density_proxy |
float64 | Local demographic density indicator | Gridded urban demographic centers (cities_r2.csv) |
Quickstart & Usage
Loading via Hugging Face datasets
from datasets import load_dataset
dataset = load_dataset("abdullahashraf122/alaska-arctic-hydrology-matrix")
print(dataset)
print(dataset["train"][0])
Loading via Pandas / PyArrow
import pandas as pd
df = pd.read_parquet("https://huggingface.co/datasets/abdullahashraf122/alaska-arctic-hydrology-matrix/resolve/main/data/alaska_offline_training_matrix_v1.parquet")
print(df.head())
print(df.describe())
Data Curation & Provenance
- Sampling Engine:
ALASKA_SANDBOX/local_data_harmonizer.py - Coordinate Bounds: 25.0°N to 28.0°N, 79.0°E to 82.0°E
- Coordinate Projection: EPSG:4326 (WGS84)
License & Attribution
Distributed under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license.
Structure
default 50,000 rows
| Split | Rows | Size |
|---|---|---|
| train | 50,000 | 2.1 MB |
Details
- Repository
- abdullahashraf122/alaska-arctic-hydrology-matrix
- Publisher
- Abdullah Ashraf
- Task category
- Tabular regression
- Tags
- hydrology, remote-sensing, geospatial
- Size category
- 10K<n<100K
- Languages
- en
- Revision
- d51ed99e12a12182247a32d190f9ff9f2029f0f0
- Last updated
- 2026-10-01
Files
3 files, 2.1 MB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| data/alaska_offline_training_matrix_v1.parquet | Data | 2.1 MB | cb6cf4fc9d68 |
| README.md | Documentation | 3.6 KB | — |
| .gitattributes | Repository | 47 B | — |
License and Download
- License
- cc-by-4.0
- Access
- No access gate
Released by Abdullah Ashraf through its official repository on Hugging Face. Read the license.