pypfda

Particle filter data assimilation in pure Python, with first-class support for paleoclimate Observing System Simulation Experiments.

Getting started

• Installation
• Quickstart

Theory

• The sequential importance resampling particle filter

Tutorials

• Tutorial: Lorenz-63 twin experiment
• Tutorial: paper claims reproduced on Lorenz-96

API reference

• API reference

Project

• Changelog
• Contributing

Why pypfda?

Sequential importance resampling particle filters are conceptually simple but easy to implement badly: log-domain weight underflow, inadvertent ensemble collapse, sensitivity to particle ordering. pypfda ships well-tested primitives (log-sum-exp weights, four resampling schemes, Gaspari–Cohn localization, max-weight degeneracy prevention) so you can focus on your science problem rather than debugging the filter.

Indices and tables

• Index

• Module Index

• Search Page