Snow Water Equivalent (SWE) Forecasting Training Data: SNOTEL, gridMET, SRTM Terrain and MODIS Snow Cover (Western US)
- Provider
- Ziheng Sun, Justin Pflug, Nicoleta Cristea et al. (Geoweaver)
- License
- CC-BY-4.0 (source)
- Size
- 5 files
- Format
- CSV (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/Geoweaver/SnowWaterEquivalent_trainingdata)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://huggingface.co/datasets/Geoweaver/SnowWaterEquivalent_trainingdata
About this dataset
Machine-learning training data for forecasting snow water equivalent (SWE), the depth of water held in the snowpack, prepared by Ziheng Sun, Justin Pflug, Nicoleta Cristea and colleagues (Geoweaver, 2024). A single table (training_data.csv, about 3.9 GB) combines daily snowpack observations from NRCS SNOTEL stations with gridMET meteorology (minimum and maximum air temperature, precipitation, wind speed, relative humidity, vapor pressure deficit, potential evapotranspiration), terrain from USGS SRTM elevation, and MODIS MOD10A1 NDSI snow cover, including lagged values from previous days; a source column records where each field came from. Each row is one location and day with latitude, longitude, date, SWE in inches and its predictors, intended for hydrological forecasting of snowmelt runoff and water supply. A Python loader script and field dictionary are included. Load with pandas. Released under CC BY 4.0 by the authors; cite Sun et al. (2024) and the source data providers (NRCS SNOTEL, gridMET, USGS, NSIDC MODIS).
How to load this dataset in Python
import pandas as pd
df = pd.read_csv("hf://datasets/Geoweaver/SnowWaterEquivalent_trainingdata/training_data.csv")
df.head()Data structure
File types in sampled files: CSV
Files
Example file: training_data.csv
Analyze this dataset without downloading it
On Scigantic, Snow Water Equivalent (SWE) Forecasting Training Data: SNOTEL, gridMET, SRTM Terrain and MODIS Snow Cover (Western US) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Environmental Science datasets
- USGS 3D Hydrography Program (3DHP) Staged Products
- USGS NHDPlus High Resolution (NHDPlus HR): Flowlines, Catchments and Hydro-Enforced DEM Rasters by VPU
- ForestSignal California (1985–2025)
- Mesic Analysis Platform: Wet Meadow, Spring and Riparian Persistence across the Sagebrush Biome (H3, GeoParquet)
- METRAQ: Madrid Hourly Air Quality, Meteorology and Traffic Dataset (2001-2024)
- Sea Turtle Breathing Behavior Raw Video: 42 Daytime Recordings of Rehabilitating Turtles in Tanks (University of Zagreb LABUST and Israel Sea Turtle Rescue Center)
- USGS Ungulate Migrations
- Yukon River Chinook Salmon Spawning Migration: Radio-Archival Tag Swimming Depth and Temperature, 2002-2004