LibBi is used for state-space modelling and Bayesian inference on high-performance computer hardware, including multi-core CPUs, many-core GPUs (graphics processing units) and distributed-memory clusters.
The staple methods of LibBi are based on sequential Monte Carlo (SMC), also known as particle filtering. These methods include particle Markov chain Monte Carlo (PMCMC) and SMC2. Other methods include the extended Kalman filter and some parameter optimisation routines.
LibBi consists of a C++ template library, as well as a parser and compiler, written in Perl, for its own modelling language.
New LibBi mailing list
A mailing list has been set up for LibBi users over at Google Groups. Please subscribe to the list if you are interested in LibBi, and post there for help with installing or using it. 29 Nov 2013
LibBi 1.0.2 Released
LibBi version 1.0.2 is now available. It contains a number of bug and compatibility fixes, along with a few additional command-line options for configuring runs. 01 Nov 2013
NPZD package for marine biogeochemical modelling now available
A new NPZD package is now linked from the website. 02 Sep 2013
LibBi 1.0.1 Released
LibBi version 1.0.1 is now available. It contains a number of bug fixes and some additional material added to the manual. 16 Aug 2013
The initial release of LibBi was made today. 07 Jun 2013