Forecasting multivariate time series under present-value-model short- and long-run co-movement restrictions

Using a sequence of nested multivariate models that are VAR-based, we discuss different layers of restrictions imposed by present-value models (PVM hereafter) on the VAR in levels for series that are subject to present-value restrictions. Our focus is novel - we are interested in the short-run restrictions entailed by PVMs (Vahid and Engle, 1993, 1997) and their implications for forecasting. Using a well-known database, kept by Robert Shiller, we implement a forecasting competition that imposes different layers of PVM restrictions. Our exhaustive investigation of several different multivariate models reveals that better forecasts can be achieved when restrictions are applied to the unrestricted VAR. Moreover, imposing short-run restrictions produces forecast winners 70% of the time for the target variables of PVMs and 63.33% of the time when all variables in the system are considered.

Automatic model selection for forecasting brazilian stock returns

This study aims to contribute on the forecasting literature in stock return for emerging markets. We use Autometrics to select relevant predictors among macroeconomic, microeconomic and technical variables. We develop predictive models for the Brazilian market premium, measured as the excess return over Selic interest rate, Itaú SA, Itaú-Unibanco and Bradesco stock returns. We nd that for the market premium, an ADL with error correction is able to outperform the benchmarks in terms of economic performance. For individual stock returns, there is a trade o between statistical properties and out-of-sample performance of the model.

Automatic model selection for forecasting Brazilian stock returns

This study aims to contribute on the forecasting literature in stock return for emerging markets. We use Autometrics to select relevant predictors among macroeconomic, microeconomic and technical variables. We develop predictive models for the Brazilian market premium, measured as the excess return over Selic interest rate, Itaú SA, Itaú-Unibanco and Bradesco stock returns. We find that for the market premium, an ADL with error correction is able to outperform the benchmarks in terms of economic performance. For individual stock returns, there is a trade o between statistical properties and out-of-sample performance of the model.

Robust Bayesian analysis of heavy-tailed stochastic volatility models using scale mixtures of normal distributions

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Towards forecasting and mitigating ionospheric scintillation effects on GNSS

The effect of the ionosphere on the signals of Global Navigation Satellite Systems (GNSS), such as the Global Positionig System (GPS) and the proposed European Galileo, is dependent on the ionospheric electron density, given by its Total Electron Content (TEC). Ionospheric time-varying density irregularities may cause scintillations, which are fluctuations in phase and amplitude of the signals. Scintillations occur more often at equatorial and high latitudes. They can degrade navigation and positioning accuracy and may cause loss of signal tracking, disrupting safety-critical applications, such as marine navigation and civil aviation. This paper addresses the results of initial research carried out on two fronts that are relevant to GNSS users if they are to counter ionospheric scintillations, i.e. forecasting and mitigating their effects. On the forecasting front, the dynamics of scintillation occurrence were analysed during the severe ionospheric storm that took place on the evening of 30 October 2003, using data from a network of GPS Ionospheric Scintillation and TEC Monitor (GISTM) receivers set up in Northern Europe. Previous results [1] indicated that GPS scintillations in that region can originate from ionospheric plasma structures from the American sector. In this paper we describe experiments that enabled confirmation of those findings. On the mitigation front we used the variance of the output error of the GPS receiver DLL (Delay Locked Loop) to modify the least squares stochastic model applied by an ordinary receiver to compute position. This error was modelled according to [2], as a function of the S4 amplitude scintillation index measured by the GISTM receivers. An improvement of up to 21% in relative positioning accuracy was achieved with this technnique.

Spatial electric load forecasting using a local movement approach

An agent based model for spatial electric load forecasting using a local movement approach for the spatiotemporal allocation of the new loads in the service zone is presented. The density of electrical load for each of the major consumer classes in each sub-zone is used as the current state of the agents. The spatial growth is simulated with a walking agent who starts his path in one of the activity centers of the city and goes to the limits of the city following a radial path depending on the different load levels. A series of update rules are established to simulate the S growth behavior and the complementarity between classes. The results are presented in future load density maps. The tests in a real system from a mid-size city show a high rate of success when compared with other techniques. The most important features of this methodology are the need for few data and the simplicity of the algorithm, allowing for future scalability. © 2009 IEEE.

The bias in reversing the Box-Cox transformation in time series forecasting: An empirical study based on neural networks

The Box-Cox transformation is a technique mostly utilized to turn the probabilistic distribution of a time series data into approximately normal. And this helps statistical and neural models to perform more accurate forecastings. However, it introduces a bias when the reversion of the transformation is conducted with the predicted data. The statistical methods to perform a bias-free reversion require, necessarily, the assumption of Gaussianity of the transformed data distribution, which is a rare event in real-world time series. So, the aim of this study was to provide an effective method of removing the bias when the reversion of the Box-Cox transformation is executed. Thus, the developed method is based on a focused time lagged feedforward neural network, which does not require any assumption about the transformed data distribution. Therefore, to evaluate the performance of the proposed method, numerical simulations were conducted and the Mean Absolute Percentage Error, the Theil Inequality Index and the Signal-to-Noise ratio of 20-step-ahead forecasts of 40 time series were compared, and the results obtained indicate that the proposed reversion method is valid and justifies new studies. (C) 2014 Elsevier B.V. All rights reserved.

Determining spatial resolution in spatial load forecasting using a grid-based model

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

This paper addressed the problem of water-demand forecasting for real-time operation of water supply systems. The present study was conducted to identify the best fit model using hourly consumption data from the water supply system of Araraquara, Sa approximate to o Paulo, Brazil. Artificial neural networks (ANNs) were used in view of their enhanced capability to match or even improve on the regression model forecasts. The ANNs used were the multilayer perceptron with the back-propagation algorithm (MLP-BP), the dynamic neural network (DAN2), and two hybrid ANNs. The hybrid models used the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called ANN-H and DAN2-H, respectively. The tested inputs for the neural network were selected literature and correlation analysis. The results from the hybrid models were promising, DAN2 performing better than the tested MLP-BP models. DAN2-H, identified as the best model, produced a mean absolute error (MAE) of 3.3 L/s and 2.8 L/s for training and test set, respectively, for the prediction of the next hour, which represented about 12% of the average consumption. The best forecasting model for the next 24 hours was again DAN2-H, which outperformed other compared models, and produced a MAE of 3.1 L/s and 3.0 L/s for training and test set respectively, which represented about 12% of average consumption. DOI: 10.1061/(ASCE)WR.1943-5452.0000177. (C) 2012 American Society of Civil Engineers.

Analysis of eruptive and seismic sequences to improve the short-and long-term eruption forecasting

Forecasting the time, location, nature, and scale of volcanic eruptions is one of the most urgent aspects of modern applied volcanology. The reliability of probabilistic forecasting procedures is strongly related to the reliability of the input information provided, implying objective criteria for interpreting the historical and monitoring data. For this reason both, detailed analysis of past data and more basic research into the processes of volcanism, are fundamental tasks of a continuous information-gain process; in this way the precursor events of eruptions can be better interpreted in terms of their physical meanings with correlated uncertainties. This should lead to better predictions of the nature of eruptive events. In this work we have studied different problems associated with the long- and short-term eruption forecasting assessment. First, we discuss different approaches for the analysis of the eruptive history of a volcano, most of them generally applied for long-term eruption forecasting purposes; furthermore, we present a model based on the characteristics of a Brownian passage-time process to describe recurrent eruptive activity, and apply it for long-term, time-dependent, eruption forecasting (Chapter 1). Conversely, in an effort to define further monitoring parameters as input data for short-term eruption forecasting in probabilistic models (as for example, the Bayesian Event Tree for eruption forecasting -BET_EF-), we analyze some characteristics of typical seismic activity recorded in active volcanoes; in particular, we use some methodologies that may be applied to analyze long-period (LP) events (Chapter 2) and volcano-tectonic (VT) seismic swarms (Chapter 3); our analysis in general are oriented toward the tracking of phenomena that can provide information about magmatic processes. Finally, we discuss some possible ways to integrate the results presented in Chapters 1 (for long-term EF), 2 and 3 (for short-term EF) in the BET_EF model (Chapter 4).

Analysis and developments of uncertainty processors for real time flood forecasting

The hydrologic risk (and the hydro-geologic one, closely related to it) is, and has always been, a very relevant issue, due to the severe consequences that may be provoked by a flooding or by waters in general in terms of human and economic losses. Floods are natural phenomena, often catastrophic, and cannot be avoided, but their damages can be reduced if they are predicted sufficiently in advance. For this reason, the flood forecasting plays an essential role in the hydro-geological and hydrological risk prevention. Thanks to the development of sophisticated meteorological, hydrologic and hydraulic models, in recent decades the flood forecasting has made a significant progress, nonetheless, models are imperfect, which means that we are still left with a residual uncertainty on what will actually happen. In this thesis, this type of uncertainty is what will be discussed and analyzed. In operational problems, it is possible to affirm that the ultimate aim of forecasting systems is not to reproduce the river behavior, but this is only a means through which reducing the uncertainty associated to what will happen as a consequence of a precipitation event. In other words, the main objective is to assess whether or not preventive interventions should be adopted and which operational strategy may represent the best option. The main problem for a decision maker is to interpret model results and translate them into an effective intervention strategy. To make this possible, it is necessary to clearly define what is meant by uncertainty, since in the literature confusion is often made on this issue. Therefore, the first objective of this thesis is to clarify this concept, starting with a key question: should be the choice of the intervention strategy to adopt based on the evaluation of the model prediction based on its ability to represent the reality or on the evaluation of what actually will happen on the basis of the information given by the model forecast? Once the previous idea is made unambiguous, the other main concern of this work is to develope a tool that can provide an effective decision support, making possible doing objective and realistic risk evaluations. In particular, such tool should be able to provide an uncertainty assessment as accurate as possible. This means primarily three things: it must be able to correctly combine all the available deterministic forecasts, it must assess the probability distribution of the predicted quantity and it must quantify the flooding probability. Furthermore, given that the time to implement prevention strategies is often limited, the flooding probability will have to be linked to the time of occurrence. For this reason, it is necessary to quantify the flooding probability within a horizon time related to that required to implement the intervention strategy and it is also necessary to assess the probability of the flooding time.

Development of parallelizable flood inundation models for large scale analysis

Flood disasters are a major cause of fatalities and economic losses, and several studies indicate that global flood risk is currently increasing. In order to reduce and mitigate the impact of river flood disasters, the current trend is to integrate existing structural defences with non structural measures. This calls for a wider application of advanced hydraulic models for flood hazard and risk mapping, engineering design, and flood forecasting systems. Within this framework, two different hydraulic models for large scale analysis of flood events have been developed. The two models, named CA2D and IFD-GGA, adopt an integrated approach based on the diffusive shallow water equations and a simplified finite volume scheme. The models are also designed for massive code parallelization, which has a key importance in reducing run times in large scale and high-detail applications. The two models were first applied to several numerical cases, to test the reliability and accuracy of different model versions. Then, the most effective versions were applied to different real flood events and flood scenarios. The IFD-GGA model showed serious problems that prevented further applications. On the contrary, the CA2D model proved to be fast and robust, and able to reproduce 1D and 2D flow processes in terms of water depth and velocity. In most applications the accuracy of model results was good and adequate to large scale analysis. Where complex flow processes occurred local errors were observed, due to the model approximations. However, they did not compromise the correct representation of overall flow processes. In conclusion, the CA model can be a valuable tool for the simulation of a wide range of flood event types, including lowland and flash flood events.

Bayesian space-time data fusion for real-time forecasting and map uncertainty

Environmental computer models are deterministic models devoted to predict several environmental phenomena such as air pollution or meteorological events. Numerical model output is given in terms of averages over grid cells, usually at high spatial and temporal resolution. However, these outputs are often biased with unknown calibration and not equipped with any information about the associated uncertainty. Conversely, data collected at monitoring stations is more accurate since they essentially provide the true levels. Due the leading role played by numerical models, it now important to compare model output with observations. Statistical methods developed to combine numerical model output and station data are usually referred to as data fusion. In this work, we first combine ozone monitoring data with ozone predictions from the Eta-CMAQ air quality model in order to forecast real-time current 8-hour average ozone level defined as the average of the previous four hours, current hour, and predictions for the next three hours. We propose a Bayesian downscaler model based on first differences with a flexible coefficient structure and an efficient computational strategy to fit model parameters. Model validation for the eastern United States shows consequential improvement of our fully inferential approach compared with the current real-time forecasting system. Furthermore, we consider the introduction of temperature data from a weather forecast model into the downscaler, showing improved real-time ozone predictions. Finally, we introduce a hierarchical model to obtain spatially varying uncertainty associated with numerical model output. We show how we can learn about such uncertainty through suitable stochastic data fusion modeling using some external validation data. We illustrate our Bayesian model by providing the uncertainty map associated with a temperature output over the northeastern United States.

Study of a wind-wave numerical model and its integration with ocean and oil-spill numerical models

The ability to represent the transport and fate of an oil slick at the sea surface is a formidable task. By using an accurate numerical representation of oil evolution and movement in seawater, the possibility to asses and reduce the oil-spill pollution risk can be greatly improved. The blowing of the wind on the sea surface generates ocean waves, which give rise to transport of pollutants by wave-induced velocities that are known as Stokes’ Drift velocities. The Stokes’ Drift transport associated to a random gravity wave field is a function of the wave Energy Spectra that statistically fully describe it and that can be provided by a wave numerical model. Therefore, in order to perform an accurate numerical simulation of the oil motion in seawater, a coupling of the oil-spill model with a wave forecasting model is needed. In this Thesis work, the coupling of the MEDSLIK-II oil-spill numerical model with the SWAN wind-wave numerical model has been performed and tested. In order to improve the knowledge of the wind-wave model and its numerical performances, a preliminary sensitivity study to different SWAN model configuration has been carried out. The SWAN model results have been compared with the ISPRA directional buoys located at Venezia, Ancona and Monopoli and the best model settings have been detected. Then, high resolution currents provided by a relocatable model (SURF) have been used to force both the wave and the oil-spill models and its coupling with the SWAN model has been tested. The trajectories of four drifters have been simulated by using JONSWAP parametric spectra or SWAN directional-frequency energy output spectra and results have been compared with the real paths traveled by the drifters.

Dynamics of coastal aquifers: data-driven forecasting and risk analysis

This work is focused on the study of saltwater intrusion in coastal aquifers, and in particular on the realization of conceptual schemes to evaluate the risk associated with it. Saltwater intrusion depends on different natural and anthropic factors, both presenting a strong aleatory behaviour, that should be considered for an optimal management of the territory and water resources. Given the uncertainty of problem parameters, the risk associated with salinization needs to be cast in a probabilistic framework. On the basis of a widely adopted sharp interface formulation, key hydrogeological problem parameters are modeled as random variables, and global sensitivity analysis is used to determine their influence on the position of saltwater interface. The analyses presented in this work rely on an efficient model reduction technique, based on Polynomial Chaos Expansion, able to combine the best description of the model without great computational burden. When the assumptions of classical analytical models are not respected, and this occurs several times in the applications to real cases of study, as in the area analyzed in the present work, one can adopt data-driven techniques, based on the analysis of the data characterizing the system under study. It follows that a model can be defined on the basis of connections between the system state variables, with only a limited number of assumptions about the "physical" behaviour of the system.