Hidden Markov Models (HMM) can be used for downscaling daily rainfall occurrences and amounts from GCM simulations.  The HMM fits a model to observed rainfall records by introducing a small number of discrete rainfall states. These states allow a diagnostic interpretation of observed rainfall variability in terms of a few rainfall patterns. The states are ‘hidden’ from the observer, i.e., they are not directly observable. [Read More…]

Two software packages have been designed for rainfall downscaling using non-homogeneous HMMs (NHMMs). The MVNHMM stand-alone C++ package and its GUI interface, the HMMTool, provide a family of HMMs based on the maximum likelihood method. Recently, a new Bayesian NHMM has been developed in R that incorporates a generalized linear model for additional flexibility in constructing predictor-predictand relationships.

For assistance with HMM Tool, please see the HMM Tool User Guide. No additional support is currently available.