Markov chain modeling of precipitation time series: Modeling waiting times between tipping bucket rain gauge tips

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


A very fine temporal and volumetric resolution precipitation time series is modeled using Markov models. Both 1st and 2nd order Markov models as well as seasonal and diurnal models are investigated and evaluated using likelihood based techniques. The 2nd order Markov model is found to be insignificant. The 1st order Markov model seems to be the most important, followed by the seasonal and diurnal ones. The final model is a continuous state-space 1st order Markov process with seasonal variation. Inclusion of seasonality in the continuous Markov chain model proved difficult, and with respect to likelihood it actually makes the model fit decrease.
Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Urban Drainage
Publication date2011
Publication statusPublished - 2011
Event12th International Conference on Urban Drainage - Porto Alegre, Brazil
Duration: 11 Sep 201116 Sep 2011
Conference number: 12


Conference12th International Conference on Urban Drainage
CityPorto Alegre
Internet address


  • Markov chain modeling
  • Continuous state-space Markov chain modeling
  • Seasonal precipitation modeling
  • Precipitation modeling
  • Tipping bucket rain gauges
  • Waiting times

Cite this