STATIONARITY OF ANNUAL MAXIMUM DAILY STREAMFLOW TIME SERIES IN SOUTH-EAST BRAZILIAN RIVERS

• Main Authors: Jorge Machado Damázio, Fernanda da Serra Costa
• Format: Article
• Language: English
• Published: Universidade do Estado do Rio de Janeiro 2015-08-01
• Series: Cadernos do IME: Série Estatística
• Online Access: http://www.e-publicacoes.uerj.br/index.php/cadest/article/view/18302
• ISSN: 1413-9022; 2317-4536

<p class="CorpoTexto-itlico"><em>DOI: </em><a href="http://dx.doi.org/10.12957/cadest.2014.18302"><em>10.12957/cadest.2014.18302</em></a></p><p class="CorpoTexto-itlico"><span lang="EN-US">The paper presents a statistical analysis of annual maxima daily streamflow between 1931 and 2013 in South-East Brazil focused in detecting and modelling non-stationarity aspects. Flood protection for the large valleys in South-East Brazil is provided by multiple purpose reservoir systems built during 20th century, which design and operation plans has been done assuming stationarity of historical flood time series. Land cover changes and rapidly-increasing level of atmosphere greenhouse gases of the last century may be affecting flood regimes in these valleys so that it can be that nonstationary modelling should be applied to re-asses dam safety and flood control operation rules at the existent reservoir system. Six annual maximum daily streamflow time series are analysed. The time series were plotted together with fitted smooth loess functions and non-parametric statistical tests are performed to check the significance of apparent trends shown by the plots. Non-stationarity is modelled by fitting univariate extreme value distribution functions which location varies linearly with time. Stationarity and non-stationarity modelling are compared with the likelihood ratio statistic. In four of the six analyzed time series non-stationarity modelling outperformed stationarity modelling.</span></p><p class="CorpoTexto-itlico"><span lang="EN-US">Keywords<em>: Stationarity; Extreme Value Distributions; Flood Frequency Analysis; Maximum Likelihood Method.</em><br /></span></p>