Bivariate modelling of precipitation and temperature using a non-homogeneous hidden Markov model

TL;DR

This paper introduces a non-homogeneous hidden Markov model to generate realistic synthetic bivariate time series of daily temperature and precipitation, accounting for non-stationarity and dependence structure across different European climates.

Contribution

The paper presents a novel non-homogeneous hidden Markov model with periodic transition probabilities and time-dependent emissions for weather variable simulation.

Findings

Model successfully simulates realistic bivariate weather time series.

Captures non-stationary behavior of temperature and precipitation.

Effective across diverse European climate zones.

Abstract

Aiming to generate realistic synthetic times series of the bivariate process of daily mean temperature and precipitations, we introduce a non-homogeneous hidden Markov model. The non-homogeneity lies in periodic transition probabilities between the hidden states, and time-dependent emission distributions. This enables the model to account for the non-stationary behaviour of weather variables. By carefully choosing the emission distributions, it is also possible to model the dependance structure between the two variables. The model is applied to several weather stations in Europe with various climates, and we show that it is able to simulate realistic bivariate time series.