Hidden markov models incorporating covariates for daily rainfall time series

Nadarajah Ramesh ^[1] ; Gayatri Rode ^[1]
1. [1] University of Greenwich
  
  University of Greenwich
  
  Reino Unido
Localización: Proceedings of the 35th International Workshop on Statistical Modelling : July 20-24, 2020 Bilbao, Basque Country, Spain / Itziar Irigoien Garbizu (ed. lit.), Dae-Jin Lee (ed. lit.), Joaquín Martínez Minaya (ed. lit.), María Xosé Rodríguez Álvarez (ed. lit.), 2020, ISBN 978-84-1319-267-3, págs. 402-405
Idioma: inglés
Enlaces
- Texto Completo Libro
Resumen
- Hidden Markov models provide a rich class of stochastic models that are very useful in hydrological studies. This paper describes a class of hidden Markov models that incorporate covariates in their state distributions to model daily rainfall time series. Greater emphasis is placed on nding a model that can reproduce the second-order properties of the observed rainfall sequences. We present the construction of the likelihood function incorporating time-dependent atmospheric covariates in rainfall distributions. The performance of the model is assessed using daily rainfall data from Leicester, East Midlands region of England.