pySTEPS/pysteps

Python framework for short-term ensemble prediction systems.

What it solves

It provides a framework for probabilistic precipitation nowcasting, which is the creation of short-term ensemble prediction systems to forecast rainfall and other precipitation events.

How it works

The library implements optical flow methods and advanced stochastic generators to produce ensemble nowcasts. It supports standard input/output file formats and includes tools for visualizing, post-processing, and verifying forecasts using deterministic, probabilistic, and neighbourhood methods.

Who it’s for

It is designed for researchers developing new methods for nowcasting and stochastic space-time simulation, as well as practitioners such as weather forecasters and hydrologists.

Highlights

  • Modular and well-documented framework for precipitation simulation.
  • Support for multiple optical flow methods.
  • Stochastic generators for ensemble nowcasting.
  • Integrated tools for forecast verification and visualization.

Related

  • Project
    skforecast/skforecast

    A Python library for time series forecasting that integrates scikit-learn compatible models, statistical methods, and foundation models into a unified API.

  • Project
    Nixtla/neuralforecast

    A library of over 30 state-of-the-art neural forecasting models designed for high performance, usability, and efficiency in time-series forecasting.

  • Project
    mikekeith52/scalecast

    A time series forecasting library that provides a uniform interface for ML and deep learning models, simplifying model selection, validation, and pipeline creation.

  • Project
    AIStream-Peelout/flow-forecast

    An open-source deep learning framework for time series forecasting, classification, and anomaly detection featuring a wide array of state-of-the-art models.

  • Project
    quantgirluk/aleatory

    A Python library for simulating and visualizing a wide variety of one-dimensional and two-dimensional stochastic processes.