Probabilistic forecasting of drought: a hidden Markov model aggregated with the RCP 8.5 precipitation projection

The creeping characteristics of drought make it possible to mitigate drought’s effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, we proposed a new probabilistic scheme to forecast droughts that used a discrete-time finite state-space hidden Markov model (HMM) aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The standardized precipitation index (SPI) with a 3-month time scale was employed to represent the drought status over the selected stations in South Korea. The new scheme used a reversible jump Markov chain Monte Carlo algorithm for inference on the model parameters and performed an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to perform a probabilistic forecast of SPI at the 3-month time scale that considered uncertainties. The point forecasts which were derived as the HMM-RCP forecast mean values, as measured by forecasting skill scores, were much more accurate than those from conventional models and a climatology reference model at various lead times. We also used probabilistic forecast verification and found that the HMM-RCP provided a probabilistic forecast with satisfactory evaluation for different drought categories, even at long lead times. In a drought event analysis, the HMM-RCP accurately predicted about 71.19 % of drought events during the validation period and forecasted the mean duration with an error of less than 1.8 months and a mean severity error of <0.57. The results showed that the HMM-RCP had good potential in probabilistic drought forecasting.

[1]  Kunio Shimizu,et al.  A non-homogeneous hidden Markov model for predicting the distribution of sea surface elevation , 2014 .

[2]  Zoubin Ghahramani,et al.  An Introduction to Hidden Markov Models and Bayesian Networks , 2001, Int. J. Pattern Recognit. Artif. Intell..

[3]  W. Zucchini,et al.  Hidden Markov Models for Time Series: An Introduction Using R , 2009 .

[4]  V. Singh,et al.  Drought Forecasting Using a Hybrid Stochastic and Neural Network Model , 2007 .

[5]  Jenny A. Baglivo,et al.  Earthquake Forecasting Using Hidden Markov Models , 2012, Pure and Applied Geophysics.

[6]  S. Uhlenbrook,et al.  Hydrological drought forecasting and skill assessment for the Limpopo River basin, southern Africa , 2014 .

[7]  Andrew Gelman,et al.  General methods for monitoring convergence of iterative simulations , 1998 .

[8]  Jan Adamowski,et al.  Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models , 2014 .

[9]  A. Robertson,et al.  Seasonal predictability of daily rainfall statistics over Indramayu district, Indonesia , 2009 .

[10]  Mayank R. Mehta,et al.  Explicit-Duration Hidden Markov Model Inference of UP-DOWN States from Continuous Signals , 2011, PloS one.

[11]  Sergey Kirshner,et al.  Probabilistic Assessment of Drought Characteristics Using Hidden Markov Model , 2013 .

[12]  George Kuczera,et al.  A hidden Markov model for modelling long-term persistence in multi-site rainfall time series. 2. Real data analysis , 2003 .

[13]  Francis W. Zwiers,et al.  On the ROC score of probability forecasts , 2003 .

[14]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[15]  James P. Hughes,et al.  A hidden Markov model for downscaling synoptic atmospheric patterns to precipitation amounts , 2000 .

[16]  G. Di Mauro,et al.  Forecasting Palmer Index Using Neural Networks and Climatic Indexes , 2009 .

[17]  T. McKee,et al.  THE RELATIONSHIP OF DROUGHT FREQUENCY AND DURATION TO TIME SCALES , 1993 .

[18]  Ramón Díaz-Uriarte,et al.  A Flexible Statistical Method for Detecting Genomic Copy-Number Changes Using Hidden Markov Models with Reversible Jump MCMC , 2006 .

[19]  Baikunth Nath,et al.  A fusion model of HMM, ANN and GA for stock market forecasting , 2007, Expert Syst. Appl..

[20]  Edward S. Epstein,et al.  A Scoring System for Probability Forecasts of Ranked Categories , 1969 .

[21]  Mark J. F. Gales,et al.  Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..

[22]  C. Robert,et al.  Bayesian inference in hidden Markov models through the reversible jump Markov chain Monte Carlo method , 2000 .

[23]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[24]  Peter Guttorp,et al.  A Hidden Markov Model for Space‐Time Precipitation , 1991 .

[25]  Wim Cornelis,et al.  Seasonal Predictability of Daily Rainfall Characteristics in Central Northern Chile for Dry-Land Management , 2010 .

[26]  C. Lavergne,et al.  Optimal Prediction with Conditionally Heteroskedastic Factor Analysed Hidden Markov Models , 2009 .

[27]  Daniel S. Wilks,et al.  Statistical Methods in the Atmospheric Sciences: An Introduction , 1995 .

[28]  Saied Mostaghimi,et al.  Long-term analysis and short-term forecasting of dry spells by Palmer Drought Severity Index , 1998 .

[29]  G. Schneider,et al.  Advances in the prediction of protein targeting signals , 2004, Proteomics.

[30]  V. Singh,et al.  A review of drought concepts , 2010 .

[31]  R. Modarres.  Streamflow drought time series forecasting , 2007 .

[32]  Juan B. Valdés,et al.  NONLINEAR MODEL FOR DROUGHT FORECASTING BASED ON A CONJUNCTION OF WAVELET TRANSFORMS AND NEURAL NETWORKS , 2003 .

[33]  A. Sutera,et al.  Drought Monitoring and Forecasting at Large Scale , 2007 .

[34]  Balaji Rajagopalan,et al.  A hidden Markov model combined with climate indices for multidecadal streamflow simulation , 2014 .

[35]  A. Cancelliere,et al.  Drought forecasting using the Standardized Precipitation Index , 2007 .

[36]  Eric Moulines,et al.  Inference in Hidden Markov Models (Springer Series in Statistics) , 2005 .

[37]  Operational Prediction of Groundwater Fluctuation in South Florida using Sequence Based Markovian Stochastic Model , 2011 .

[38]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[39]  S. Harju.  Bayesian Data Analysis in Ecology Using Linear Models with R, BUGS, and Stan. F. Korner‐Nievergelt, T. Roth, S. von Felten, J. Guélat, B. Almasi, and P. Korner‐Nievergelt. 2015. Elsevier, London, U.K. 316 pp. $76.39 paperback. ISBN 978‐0‐12‐801370‐0. , 2016 .