Constructive neural networks in forecasting weekly river flow

Lower order periodic stochastic models such as periodic autoregressive (PAR) and periodic autoregressive moving average (PARMA) models with and without harmonics are fitted to the monthly streamflows into Krishnarajasagara (KRS) reservoir located at the upper reaches of the river Cauvery in South India and a comparison is done between these models in terms of preservation of periodic statistics as well as over-year drought characteristics. Further, the comparison has been extended to the Thomas-Fiering lognormal 3-parameter (TFLN3) model which is supposed to be quite simple in structure and at the same time efficient in preservation of low flows. It is found that TFLN3 is able to reproduce the first two moments very well but, not the skewness or periodic correlations. On the other hand, PAR(2) and PARMA(1,1) models are able to preserve the periodic correlations. The periodic models which are not subjected to Fourier fitting, report lower relative root mean square error in overall standard deviation and correlations, compared to the ones which are subjected to Fourier fitting. From the over-year drought analysis, it is observed that all the stochastic models fitted underestimate severe drought durations corresponding to higher truncation levels. The over-year drought characteristics are computed using the method suggested by Wang and Salas (1989), based on one hundred periodic synthetic flow sequences generated from the different models. A comparative study of the preservation of drought characteristics corresponding to various truncation levels and return periods is presented.

This paper studies correlation and partial autocorrelation properties of periodic autoregressive moving‐average (PARMA) time series models. An efficient algorithm to compute PARMA autocovariances is first derived. An innovations based algorithm to compute partial autocorrelations for a general periodic series is then developed. Finally, periodic moving averages and autoregressions are characterized as periodically stationary series whose autocovariances and partial autocorrelations, respectively, are zero at all lags that exceed some periodically varying threshold.

In this paper we study the weighted least absolute deviations estimator (WLADE) for Periodic ARMA (PARMA) models with unspecified noises, asymptotic normality of the estimator is derived. The random weighting approach is proposed to estimate the asymptotic covariance matrices of WLADE. Simulation study is carried out to examine the performance of the proposed procedure.

Streamflow forecasting is a fundamental tool in water resource studies. If information on the nature of the inflow is determinable in advance, then a given reservoir can be operated by some decision rule to minimize downstream flood damage and maximize the generated power with low costs. However, traditional methods such as linear time series models do not model the series properly, ignoring its dynamical behavior. This paper provides a method based on the Reservoir Computing (RC) technique combined with trend information extracted from the series for short-term streamflow forecasting. The model was tested in five hydroelectric plants located in different river basins in Brazil. Experimental results show that the proposed method is able to achieve better generalization performance than the traditional methods.

ABSTRACTResults involving correlation properties and parameter estimation for autoregressive‐moving average models with periodic parameters are presented. A multivariate representation of the PARMA model is used to derive parameter space restrictions and difference equations for the periodic autocorrelations. Close approximation to the likelihood function for Gaussian PARMA processes results in efficient maximum‐likelihood estimation procedures. Terms in the Fourier expansion of the parameters are sequentially included, and a selection criterion is given for determining the optimal number of harmonics to be included. Application of the techniques is demonstrated through analysis of a monthly streamflow time series.

Abstract. The aim of this article is to give a complete description of the spectral measure of periodic autoregressive moving‐average (PARMA) system in terms of its coefficients. In the analysis we use the spectral theory of strongly harmonizable sequences presented in Hurd [Journal of Multivariate Analysis(1989) Vol. 29, pp. 53–67] and the form of the unique bounded solution of ARMA model with periodic coefficients. As an application of the theoretical results, we present some examples of the spectral measures for PARMA models.

For analysis and design of water resource systems, it is sometimes useful to generate high-resolution (e.g., weekly) synthetic river flows. Periodic autoregressive moving average (PARMA) time series models provide a powerful tool for generating synthetic flows. Periodically stationary models are indicated when the basic statistics (mean, variance, and autocorrelation) of the time series exhibit significant seasonal variations. Parameter estimation for high-resolution PARMA models involves numerous parameters, which can lead to overfitting. Thus, this paper develops a parsimonious method of parameter fitting for high-resolution PARMA models, using discrete Fourier transforms to represent the set of periodic autoregressive and moving average model coefficients. Model parameters are computed via the innovations algorithm, and the asymptotic distributions of the discrete Fourier transform coefficients are obtained. Those asymptotic results are useful to determine the statistically significant Fourier coeffici...

Species of the genus Rineloricaria from the Paraguay River basin were revised, the following species and geographic distributional patterns were found: R. aurata, Paraguay River basin in Brazil and Paraguay, rio Guaporé in Brazil; R. cacerensis, Paraguay River near Cáceres in Brazil; R. lanceolata, Paraguay River basin in Brazil and Paraguay, Guaporé, Ji-Paraná, Purus, Solimões, and Araguaia rivers in Brazil, Marañón and Madre de Dios rivers in Peru; R. parva, Paraguay River basin in Brazil and Paraguay, Paraná River in Argentina, Uruguay River in Brazil. Loricaria hoehnei is proposed as a new junior synonym of R. lanceolata. A key to the species of Rineloricaria from the Paraguay River basin is provided.

In this article, we derive the asymptotic distributions of residual and normalized residual empirical autocovariances and autocorrelations of (parsimonious) periodic autoregressive moving‐average (PARMA) models under the assumption that the errors are uncorrelated but not necessarily independent. We then deduce the modified portmanteau statistics. We establish the asymptotic behavior of the proposed statistics. It is shown that the asymptotic distribution of the modified portmanteau tests is that of a weighted sum of independent chi‐squared random variables, which can be different from the usual chi‐squared approximation used under independent and identically distributed assumption on the noise. We also propose another test based on a self‐normalization approach to check the adequacy of PARMA models. A set of Monte Carlo experiments and an application to financial data are presented.

Despite advances in water resources management and planning, the São Francisco River Basin in Brazil has suffered from systematic drought problems in recent years, leading to severe human and environmental water security threats. This paper aims to track the water security for different periods and its relations with the changes in physical and natural asset conditions. The paper explores how investment planning to mitigate the water security threats and explore opportunities to increase the value of investments. The paper finds that grey infrastructure has regulated threats from increasing in the downstream of the river basin, however, continuous increase in water security threats in the upstream of the basin threatens water security downstream. This is evident from the spatial connectivity and unidirection externalities. As the capacity to further increase in grey investment is reaching its limit in the downstream, the increases in green infrastructure investment upstream, especially in the Grande River basin, could be one the way to reduce the externalities and minimise the water security risks.

Water monitoring programs are essential tools for planning and management, but their associated costs can present challenges, especially in the developing world where funding is tight. This paper addresses the use of data mining techniques in the periodic review of monitoring programs by analyzing the capacity of these techniques to reduce the number of monitored variables. This methodology was evaluated in two river basins in a southern Brazilian metropolis. The results demonstrated wide applicability that was not dependant on the level of anthropic influence within the basins. In addition, with complete databases and the use of automatic probes, periodic laboratory analyses may be used less frequently, saving human and financial resources and extending the effective water quality monitoring network. Of ten variables assessed, mathematical models were able to very accurately estimate nine and six in an urbanized basin and seven in a non-urbanized basin, demonstrating the effectiveness of this approach.

Estimations of reservoir bathymetry and storage are of great significance due to their substantial impacts on hydrological processes and water resource management. However, existing approaches for reservoir bathymetry construction often rely on field measurements, which restricts their application at regional and global scales. This study proposes a novel Approach for Determining the BAthymetry and water storage of channel‐type Reservoirs, hereafter referred to as ADBAR, for which only open‐access digital elevation model (DEM) and satellite images are required. The basic idea of ADBAR is to utilize the geomorphological similarity and topographical continuity of the reservoir inundation area with its lateral valleys and upstream/downstream regions to predict underwater bathymetry. Forty‐eight reservoirs with different topographic and geometric characteristics were selected for method validation. The selected reservoirs were all impounded after the year 2000, so the modeled reservoir bathymetry can be validated by the “reference” reservoir storage calculated using the exposed topography in SRTM DEM and the mapped water extents from spectral images. The difference between the estimated and reference storages is about 13% on average. Furthermore, the modeled results in two selected basins with dense reservoir distributions, the Upper Yellow River Basin in China and the Tocantins River Basin in Brazil, are comparable with the documented effective storage capacities. The validations for both individual reservoirs and the two large basins demonstrate that ADBAR is a robust tool for estimating reservoir bathymetries and storage capacities and thus facilitates the modeling of reservoir impacts on water budgets at large and global scales.

This paper presents an adaptive neural fuzzy network model for seasonal stream flow forecasting. The model is based on a constructive learning method that adds neurons to the network structure whenever new knowledge is necessary so that it learns the fuzzy rules and membership functions essential for modeling a fuzzy system. The model was implemented to forecast monthly average inflow on an one-step-ahead basis. It was tested on three hydroelectric plants located in different river basins in Brazil. When the results were compared with those of a multilayer feedforward neural network model, the present model revealed at least a 50% decrease in the forecasting error.

Peltocephalus dumerilianus (Schweigger) is a diurnal freshwater turtle widely distributed in the Orinoco and Amazon River basins in Brazil, Colombia, Peru, Ecuador, Venezuela, and French Guiana. During a helminthological survey of freshwater turtles from the Brazilian Amazon, numerous nematodes with characteristics of the genus Orientatractis Petter, 1966 were recovered from the stomach of Peltocephalus dumerilianus. These nematodes were different from all congeneric species, and we describe herein. Orientatractis bowseri n. sp. differs from all known species of the genus by having dorsal cuticular projections on the posterior region of the females, distribution of caudal papillae and by having papilla-like ornamentations on the cuticle distributed from the mid-esophagus to the mid portion of the body. This study represents the fourth specie of the genus Orientatractis reported in Brazil, the seventh species of Orientatractis in the Neotropical region, and the third found infecting freshwater turtles in Brazil.

An abstract is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.