All water data sources
FreeAcademicUnited States, North America

LakeBeD-US: Computer Science Edition (Hugging Face)

Benchmark dataset harmonizing 500M+ lake water quality observations across 17 variables (chlorophyll a, DO, total phosphorus, DRP, phycocyanin, temperature, fDOM) from 21 US lakes monitored by NTL-LTER, NEON and Niwot Ridge LTER. Apache Parquet files.

huggingface.co

At a glance

Region
United States (North America)
Coverage
Regional (US lakes)
Access
Free
Category
Academic
Last updated
2025

What's inside

  • Water Quality
  • Lakes
  • Chlorophyll
  • Nutrients
  • Dissolved Oxygen
  • Benchmark Dataset

What you can do with it

Typical work that data of this type supports.

  1. 01

    Hotspots and trends

    Find where contamination is high and whether it is getting worse.

    Because it has: Water Quality

  2. 02

    Compliance checks

    Compare samples against drinking water and discharge standards.

  3. 03

    Storage tracking

    Follow storage and releases through the season.

    Because it has: Lakes

Where AI adds value

Ideas for machine learning and AI agents built on this kind of data.

  1. 01

    Risk maps

    Predict contamination where no samples exist, from geology, land use and climate.

  2. 02

    Anomaly alerts

    Catch sudden spikes in sensor or lab data automatically.

  3. 03

    Storage from space

    Estimate volume from satellite water area and altimetry.

Machine access and documentation

Open API

Hugging Face datasets API / direct Parquet download

Licence: Open data

Listed in our registry of open water APIs, which WaterDataGPT can query live.

All water data sources in the United States

Find more water data

Search and compare 1,900+ water data sources by region, type and access.