Libros y capítulos de libros INAMAT2 - INAMAT2 liburuak eta liburuen kapituluak
Permanent URI for this collection
Browse
Recent Submissions
Publication Open Access Polyoxometalates in catalysis(Jenny Stanford Publishing, 2022) Alcañiz Monge, Juan; Reinoso, Santiago; Ciencias; Zientziak; Institute for Advanced Materials and Mathematics - INAMAT2This chapter will focus on providing a basis for understanding the mechanisms involved in the catalysis carried out by selected polyoxometalate (POM)-based compounds. The catalysts discussed herein will be either insoluble POM salts or POM clusters heterogenized on porous solid supports, including activated carbon materials and metallic oxides such as zirconia. The influence on the catalytic activity of both the POM catalytic species and the active porous support will be the main aspects to be commented and analyzed in detail within the chapter.Publication Open Access Machine learning procedures for daily interpolation of rainfall in Navarre (Spain)(Springer, 2023) Militino, Ana F.; Ugarte Martínez, María Dolores; Pérez Goya, Unai; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute for Advanced Materials and Mathematics - INAMAT2Kriging is by far the most well known and widely used statistical method for interpolating data in spatial random fields. The main reason is that it provides the best linear unbiased predictor and it is an exact interpolator when normality is assumed. The robustness of this method allows small departures from normality, however, many meteorological, pollutant and environmental variables have extremely asymmetrical distributions and Kriging cannot be used. Machine learning techniques such as neural networks, random forest, and k-nearest neighbor can be used instead, because they do not require specific distributional assumptions. The drawback is that they do not take account of the spatial dependence, and for an optimal performance in spatial random fields more complex machine learning techniques could be considered. These techniques also require a relatively large amount of training data and they are computationally challenging to implement. For a reduced number of observations, we illustrate the performance of the aforementioned procedures using daily rainfall data of manual meteorological gauge stations in Navarre, where the only auxiliary variables available are the spatial coordinates and the altitude. The quality of the predictions is carefully checked through three versions of the relative root mean squared error (RRMSE). The conclusion is that when we cannot use Kriging, random forest and neural networks outperform k-nearest neighbor technique, and provide reliable predictions of rainfall daily data with scarce auxiliary information.Publication Open Access Detecting change-points in the time series of surfaces occupied by pre-defined NDVI categories in continental Spain from 1981 to 2015(Springer, 2018) Militino, Ana F.; Ugarte Martínez, María Dolores; Pérez Goya, Unai; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute for Advanced Materials and Mathematics - INAMAT2The free access to satellite images since more than 40 years ago has provoked a rapid increase of multitemporal derived information of remote sensing data that should be summarized and analyzed for future inferences. In particular, the study of trends and trend changes is of crucial interest in many studies of phenology, climatology, agriculture, hydrology, geology or many other environmental disciplines. Overall, the normalized dierence vegetation index (NDVI), as a satellite derived variable, plays a crucial role because of its usefulness for vegetation and landscape characterization, land use and land cover mapping, environmental monitoring, climate change or crop prediction models. Since the eighties, it can be retrieved all over the world from dierent satellites. In this work we propose to analyze its temporal evolution, looking for breakpoints or change-points in trends of the surfaces occupied by four NDVI classications made in Spain from 1981 to 2015. The results show a decrease of bare soils and semi-bare soils starting in the middle nineties or before, and a slight increase of middle-vegetation and high-vegetation soils starting in 1990 and 2000 respectively.Publication Open Access Open questions in utility theory(Springer, 2020) Campión Arrastia, María Jesús; Induráin Eraso, Esteban; Estatistika, Informatika eta Matematika; Institute for Advanced Research in Business and Economics - INARBE; Institute for Advanced Materials and Mathematics - INAMAT2; Estadística, Informática y MatemáticasThroughout this paper, our main idea is to explore different classical questions arising in Utility Theory, with a particular attention to those that lean on numerical representations of preference orderings. We intend to present a survey of open questions in that discipline, also showing the state-of-art of the corresponding literature.Publication Open Access Searching for a Debreu’s open gap lemma for semiorders(Springer, 2020) Estevan Muguerza, Asier; Estatistika, Informatika eta Matematika; Institute for Advanced Materials and Mathematics - INAMAT2; Estadística, Informática y MatemáticasIn 1956 R. D. Luce introduced the notion of a semiorder to deal with indifference relations in the representation of a preference. During several years the problem of finding a utility function was studied until a representability characterization was found. However, there was almost no results on the continuity of the representation. A similar result to Debreu’s Lemma, but for semiorders was never achieved. In the present paper we propose a characterization for the existence of a continuous representation (in the sense of Scott-Suppes) for bounded semiorders. As a matter of fact, the weaker but more manageable concept of ε-continuity is properly introduced for semiorders. As a consequence of this study, a version of the Debreu’s Open Gap Lemma is presented (but now for the case of semiorders) just as a conjecture, which would allow to remove the open-closed and closed-open gaps of a subset S ⊆ R, but now keeping the constant threshold, so that x + 1 < y if and only if g(x) + 1 < g(y) (x, y ∈ S).