the nowcasting initiative

alt text

The pySTEPS initiative is a community that develops and maintains an easy to use, modular, free and open source python framework for short-term ensemble prediction systems.

The focus is on probabilistic nowcasting of radar precipitation fields, but pySTEPS is designed to allow a wider range of uses.

Download pysteps 0.2

The most recent release of pysteps is available here.

Change log for pysteps 0.2:


We are hosting a pysteps demo during the next UrbanRain conference in Pontresina (5-7 December 2018).

December 7, 14:00-15:00: Topical Workshop 2: Discover pysteps - the ensemble precipitation nowcasting library (demo session)

This short session will present how to install, configure and run the code. The goal is to provide an overview of some of the features in pysteps and demonstrate its potential for hydrological applications. This will be a demo session, participants are not required to bring their laptops.

ERAD2018 short-course

Our first workshop using pysteps took place during ERAD2018 in Ede-Wageningen, NL, on 1 July 2018. With over 30 participants, this was a very successful workshop! We would like to thank all the participants for their enthusiasm and commitment!

The short-course description and material are available on the ERAD2018 website (search for short-course 4: Radar-based Ensemble Precipitation Nowcasting).

Quick-start guide

It is very easy to start using pysteps! You simply need to install the dependencies, download the latest pysteps version and install it.

Please refer to the README document in our main github repository for the installation instructions.


The documentation is available at this link.

The same is also available as pdf here.

This FMI radar composite was imported and visualized with pysteps.

The reliability diagram for 0.1 mm/h threshold and a +60 minute ensemble nowcast with 20 members computed for the above FMI example.

The motion field estimated on a sequence of MeteoSwiss radar composites using DARTS.

The rank histogram of a 20-member nowcast at +60 minutes for the above MeteoSwiss event.