Nonstationary Extreme Value Analysis (NEVA) Software Package, Version 2.0
By: Linyin Cheng, PhD, University of California, Irvine
Source Code: Matlab
The Nonstationary Extreme Value Analysis (NEVA) software package has been developed to facilitate extreme value analysis under both stationary and nonstationary assumptions. In a Bayesian approach, NEVA estimates the extreme value parameters with a Differential Evolution Markov Chain (DE-MC) approach for global optimization over the parameter space. NEVA includes posterior probability intervals (uncertainty bounds) of estimated return levels through Bayesian inference, with its inherent advantages in uncertainty quantification. The software presents the results of non-stationary extreme value analysis using various exceedance probability methods. We evaluate both stationary and non-stationary components of the package for a case study consisting of annual temperature maxima for a gridded global temperature dataset. The results show that NEVA can reliably describe extremes and their return levels.
NEVA includes two components:
(1) The Generalized Extreme Value (GEV) distribution for analysis of annual maxima (block maxima).
(2) The Generalized Pareto Distribution (GPD) for analysis of extremes above a certain threshold (i.e., peak-over-threshold (POT) approach).
Both NEVA GEV and NEVA GPD can be used for stationary (time-independent) and nonstationary (transient) extreme value analysis.
Cheng L., AghaKouchak A., Gilleland E., Katz R.W., 2014, Non-stationary Extreme Value Analysis in a Changing Climate , Climatic Change, doi: 10.1007/s10584-014-1254-5.
Download Reference Paper: http://amir.eng.uci.edu/publications/14_NEVA_CC.pdf
The toolbox includes a sample observation and simulation data sets. Run NEVA.m to see sample outputs.