+
Skip to content

ipwgml/ipwgml

Repository files navigation

IPWG SatRain: A machine-learning-ready benchmark dataset for satellite precipitation estimation

The Satellite Precipitation Retrieval (SatRain) benchmark dataset develped by the International Precipitation Working Group (IPWG) is a benchmark dataset for machine-learning-based satellite precipitation retrievals, i.e., algorithms for detecting and quantifying precipitation from satellite imagery.

Features

  • Training, validation, and test splits derived from four years of overpasses of passive-microwave sensors over the conterminous united states (CONUS)
  • Multi-spectral input observations (microwave, infrared, and visible) from low-earth and geostationary platforms
  • Comprehensive ancillary data covering atmospheric parameters and surface properties
  • Independent evaluation datasets dervied from independent time periods, regions, and measurement techniques
  • Flexible evaluation framework

Documentation

For instructions on how to get starting using the dataset refer to the documentation available here.

About

Benchmark datasets for assessing satellite-based precipitation retrievals

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载