Bournemouth University

About: Bournemouth University is a education organization based out in Poole, United Kingdom. It is known for research contribution in the topics: Tourism & Population. The organization has 3032 authors who have published 9672 publications receiving 220403 citations. The organization is also known as: Bournemouth Municipal College.

Advances in Monitoring and Modelling Climate at Ecologically Relevant Scales

Abstract: Most ecological studies of the effects of climate on species are based on average conditions above ground level (measured by meteorological stations) averaged across 100 km2 or larger areas. However, most terrestrial organisms experience conditions in a much smaller area at the ground surface or within vegetation canopies, the climate of which can be very different to large-scale averages. Therefore, to accurately characterise the climatic conditions suitable for species, it is essential to include microclimate information. Microclimates are affected by the shape of the landscape, including the steepness and aspect of slopes, height above sea level, proximity to the sea or inland water, and whether a site is in a valley or at the top of a hill. Plants also modify the conditions found within or below their canopies, with the structure of vegetation playing an important role. The recent increase in the availability of microsensors and remotely sensed data at appropriate resolutions has led some ecologists to begin to include microclimate information within a variety of contexts; however the field can be confusing and intimidating and mistakes are often made along the way. In this chapter, we provide an overview of microclimatic processes and summarise the available methods of measuring and modelling microclimate data for incorporation in ecological research. We highlight pitfalls to avoid emerging novel methods and the limitations of some techniques. We also consider future research directions and opportunities within this emerging field.

Local learning‐based adaptive soft sensor for catalyst activation prediction

Abstract: This work presents an algorithm for the development of adaptive soft sensors. The method is based on the local learning framework, where locally valid models are built and maintained. In this framework, it is possible to model nonlinear relationship between the input and output data by the means of a combination of linear models. The method provides the possibility to perform adaptation at two levels: (i) recursive adaptation of the local models and (ii) the adaptation of the combination weights. The dataset used for evaluation of the algorithm describes a polymerization reactor where the target value is a simulated catalyst activity in the reactor. This dataset is also used to evaluate the performance of the proposed algorithm. The results show that the traditional recursive partial least squares algorithm struggles to deliver accurate predictions. In contrast to this, by exploiting the two-level adaptation scheme, the proposed algorithm delivers more accurate results. © 2010 American Institute of Chemical Engineers AIChE J, 57, 2011