The thesis focuses on the yield curve modeling using the dynamic Nelson-Siegel approach. We propose two models of the yield curve and apply them on four currency areas - USD, EUR, GBP and CZK. At first, we distill the entire yield curve into the time-varying level, slope and curvature factors and estimate the parameters for individual currencies. Subsequently, we build a novel model investigating to what extent unobservable factors of the dynamic Nelson-Siegel model are determined by macroeconomic drivers. The main contribution of this thesis resides in the innovative approach to yield curve modeling with the application of advanced technical tools. Our primary objective was to increase the accuracy and the estimation power of the model. Moreover, we applied both models across different currency areas, which enabled us to compare the dynamics of the yield curves as well as the influence of the macroeconomic drivers. Interestingly, the results proved that both models we developed not only demonstrate strong validity, but also produce powerful estimates across all examined currencies. In addition, the incorporated macroeconomic factors contributed to reach higher precision of the modeling. JEL Classification: C51, C53, G17 Keywords: Nelson-Siegel, Kalman filter, Kalman smoother, Stace space formulation...

A rapidly melting ice sheet produces a distinctive geometry of sea level (SL) change. Thus, a network of SL observations may, in principle, be used to infer sources of meltwater flux. We outline a new method, based on a Kalman smoother, for using tide gauge observations to estimate the individual sources of global SL change. The Kalman smoother technique iteratively calculates the maximum likelihood estimate of Greenland and West Antarctic ice sheet melt rates at each time step, and it allows for data gaps while also permitting the estimation of non-linear trends. We have also implemented a fixed multi-model Kalman filter that allows us to rigorously account for additional contributions to SL changes, such as glacial isostatic adjustment and thermal expansion. We report on a series of detection experiments based on synthetic SL data that explore the feasibility of extracting source information from SL records before applying the new methodology to historical tide gauge records. In the historical tide gauge study we infer a global mean SL rise of ~1.5 ± 0.5 mm/yr up to 1970, followed by an acceleration to a rate of ~2.0 ± 0.5 mm/yr in 2008. In addition to its connection to SL, Greenland and its large ice sheet act as a barrier to storm systems traversing the North Atlantic. As a result of the interaction with Greenland, low-pressure systems located in the Irminger Sea, between Iceland and Greenland, often produce strong low-level winds. Through a combination of modeling and the analysis of rare in-situ observations, we explore the evolution of a lee cyclone that resulted in three high-speed-wind events in November 2004. Understanding Greenland’s role in these events is critical in our understanding of local weather in this region.

A rapidly melting ice sheet produces a distinctive geometry of sea level (SL) change. Thus, a network of SL observations may, in principle, be used to infer sources of meltwater flux. We outline a new method, based on a Kalman smoother, for using tide gauge observations to estimate the individual sources of global SL change. The Kalman smoother technique iteratively calculates the maximum likelihood estimate of Greenland and West Antarctic ice sheet melt rates at each time step, and it allows for data gaps while also permitting the estimation of non-linear trends. We have also implemented a fixed multi-model Kalman filter that allows us to rigorously account for additional contributions to SL changes, such as glacial isostatic adjustment and thermal expansion. We report on a series of detection experiments based on synthetic SL data that explore the feasibility of extracting source information from SL records before applying the new methodology to historical tide gauge records. In the historical tide gauge study we infer a global mean SL rise of ~1.5 ± 0.5 mm/yr up to 1970, followed by an acceleration to a rate of ~2.0 ± 0.5 mm/yr in 2008. In addition to its connection to SL, Greenland and its large ice sheet act as a barrier to storm systems traversing the North Atlantic. As a result of the interaction with Greenland, low-pressure systems located in the Irminger Sea, between Iceland and Greenland, often produce strong low-level winds. Through a combination of modeling and the analysis of rare in-situ observations, we explore the evolution of a lee cyclone that resulted in three high-speed-wind events in November 2004. Understanding Greenland’s role in these events is critical in our understanding of local weather in this region.

Ce mémoire de thèse vise à proposer de nouvelles méthodes robustes pour l'estimation de la fréquence respiratoire (FR) à partir des signaux physiologiques souvent utilisés dans la clinique comme l'électrocardiogramme (ECG) ou le photoplethysmogramme (PPG), tout en évitant de porter des capteurs encombrants et inconfortables. En effet, la respiration influence les signaux ECG et/ou PPG. Plusieurs modulations qui décrivent la respiration sont extraites basée principalement sur l'amplitude, la fréquence et la ligne de base. Il est toutefois difficile de déterminer la combinaison optimale des modulations pour obtenir une estimation précise de la FR en raison du bruit, la spécificité de chaque patient et de l'activité. Après une revue de la littérature, il ressort que peu de travaux ont étudié la qualité de ces modulations. Nous proposons donc de quantifier la qualité des modulations à l'aide d'indices de qualité respiratoire (IQR), un nouvel indice basé sur une modulation sinusoïdale est introduit. Puis, deux méthodes sont proposées: la première sélectionne automatiquement la modulation avec l'IQR le plus élevé pour une estimation de la FR, la seconde combine les deux meilleurs modulations avec le lisseur de Kalman (LK). Une nouvelle approche de fusion de modulations basée sur un modèle multimodale est également explorée. Ces méthodes sont évaluées sur trois bases de données de différents contextes cliniques: la surveillance dans les soins postopératoires (où les patients sont immobiles), le suivi pendant les activités physiques quotidiennes et la surveillance néonatale. Les résultats expérimentaux montrent que les IQRs associés à un algorithme de fusion augmentent la précision de l'estimation de la FR à partir des modulations dérivées et montrent des résultats supérieurs aux travaux issus de la littérature. / The presented work in this dissertation concerns the development of approaches to estimate the breathing rate (BR) accurately from the electrocardiogram (ECG) and photoplethysmogram (PPG), to avoid wearing cumbersome and uncomfortable sensors for direct measurements. In fact, the respiration influences ECG and PPG signals. Several modulations are extracted to describe breathing cycles based on amplitude, frequency and baseline. However, it is difficult to determine the optimal combination to estimate the BR due to the noise and patient-dependency. Since few works have studied the quality of these modulations, we propose to study the quality of modulations using respiratory quality indices (RQI). To do so, we present two methods: the first automatically selects the modulations with the highest RQI for BR estimation, the second tracks the respiration signal using Kalman smoother. The obtained results show superior performance comparing to the methods in the literature. In addition, an extension of fusion approach is presented based on a multi-mode model. These proposed methods are tested on several datasets with different clinical contexts: monitoring post-operative care (where patients are immobile), daily physical activities and neonatal monitoring. The experimental results show that the RQIs coupled with a fusion algorithm increase the accuracy of the BR estimation from the derived modulations.

Tsunami concerns have increased in the world after the 2004 Indian Ocean tsunami and the 2011 Tohoku tsunami. Consequently, tsunami models have been developed rapidly in the last few years. One of the advanced tsunami models is the GeoClaw tsunami model introduced by LeVeque (2011). This model is adaptive and consistent. Because of different sources of uncertainties in the model, observations are needed to improve model prediction through a data assimilation framework. Model inputs are earthquake parameters and topography. This thesis introduces a real-time tsunami forecasting method that combines tsunami model with observations using a hybrid ensemble Kalman filter and ensemble Kalman smoother. The filter is used for state prediction while the smoother operates smoothing to estimate the earthquake parameters. This method reduces the error produced by uncertain inputs. In addition, state-parameter EnKF is implemented to estimate earthquake parameters. Although number of observations is small, estimated parameters generates a better tsunami prediction than the model. Methods and results of prediction experiments in the Red Sea are presented and the prospect of developing an operational tsunami prediction system in the Red Sea is discussed.

Le filtre de Kalman est largement utilisé pour l'assimilation de données en océanographie opérationnelle, notamment dans le cadre de prévisions. Néanmoins, à l'heure où les applications de l'assimilation de données tendent à se diversifier, notamment avec les réanalyses, la formulation tridimensionnelle (3D) du filtre n'utilise pas de façon optimale les observations. L'extension de ces méthodes 3D (filtre) à une formulation 4D (appelés lisseurs), permet de mieux tirer partie des observations en les assimilant de façon rétrograde. Nous étudions dans cette thèse la mise en place et les effets d'un lisseur de rang réduit sur les réanalyses, dans le cadre d'une configuration réaliste de la circulation océanique en Atlantique tropical. Ce travail expose dans un premier temps les aspects sensibles mais nécessaires de l'implémentation du lisseur, avec notamment la paramétrisation des statistiques d'erreur et leur évolution temporelle. Les apports du lissage sur les réanalyses sont ensuite étudiés, en comparant la qualité de la solution lissée par rapport à la solution filtrée. Ces résultats permettent d'exposer les bienfaits d'une assimilation 4D. On observe notamment une diminution de l'erreur globale de environ 15% sur les variables assimilées, ainsi qu'une bonne capacité du lisseur à fournir une solution cohérente avec la dynamique de référence. Ce point est illustré par le rephasage de certaines structures sensibles comme les anneaux du Brésil. Enfin, un cas moins en accord avec la théorie mais plus facile à mettre en pratique (et plus souvent utilisé dans les centres opérationnels), l'interpolation optimale, a permis d'étudier les apports du lissage et ses limites dans une telle configuration. L'évolution temporelle des erreurs pour le lissage s'est ainsi révélée nécessaire pour garder un maximum de cohérence avec les erreurs réelles. Néanmoins, le lisseur montre tout de même des résultats encourageant avec l'interpolation optimale en abaissant le niveau global d'erreur (de 10 à 15%). / The Kalman filter is widely used in data assimilation for operational oceanography, in particular for forecasting problems. Yet, now that data assimilation applications tend to diversify, with reanalysis problems for instance, the three-dimensional (3D) formulation of the filter doesn't allow an optimal use of the observations. The four-dimensional extention of the 3D methods, called smoothers, allows a better use of the observations, assimilating them on a retrospective way. We study in this work the implementation and the effects of a reduced-rank smoother on reanalysis, with a realistic tropical Atlantic ocean circulation model. First we expose some sensitive steps required for the smoother implementation, most notably the covariances evolution parametrisation of the filter. The smoother's benefits for reanalysis are then exposed, compare to a 3D reanalysis. It shows that the global error can be reduced by 15% on assimilated variables (like temperature). The smoother also leads to an analyzed solution dynamically closer to the reference (compare to the filter), as we can observe with phasing of Brazil rings for instance. Finally, we studied a case of smoothing based on optimal interpolation (instead of the filter). This case is inconsistent with the theory but often used in operational centers. Results shows that the smoother can improve the reanalysis solution in an OI case (reducing the global error from 10 to 15%), but still the dynamical evolution of error covariances (filter) are needed to get a correction according with the real error structures.

With the growing popularity of business analytics, companies experience an increasing need of reliable data. Although the availability of behavioural data showing what the consumers do has increased, the access to data showing consumer mentality, what the con- sumers actually think, remain heavily dependent on tracking surveys. This thesis inves- tigates the performance of a Dynamic Factor Model using respondent-level data gathered through repeated cross-sectional surveys. Through Monte Carlo simulations, the model was shown to improve the accuracy of brand tracking estimates by double digit percent- ages, or equivalently reducing the required amount of data by more than a factor 2, while maintaining the same level of accuracy. Furthermore, the study showed clear indications that even greater performance benefits are possible.

No description available.