Logo des Repositoriums

Auflistung nach Autor:in "Grimvall, Anders"

1 - 5 von 5
  • Konferenzbeitrag
    A Bayesian Approach to Estimation of Metal Flows in Waste Streams
    (Environmental Communication in the Information Society - Proceedings of the 16th Conference, 2002) Löfving, Erik; Grimvall, Anders
    Metal contents in waste are normally presented without any measures of uncertainty, and, if such measures are given, they are normally based on subjective judgements. Moreover, it is difficult to analyse existing data sets by employing traditional statistical procedures. The number of analysed samples can be very small and the sampling strategy is often unknown. Outliers are common and it is not unusual that the standard deviation is larger than the mean. In this paper, we propose a method that combines subjective judgement of uncertainty with actual observations to establish uncertainty bounds. The Bayesian statistical framework is used to set up a probability model that reflects our scientific problem, and this provides a theoretical basis for the inference problem.
  • Konferenzbeitrag
    A Generic Procedure for Simultaneous Estimation of Monotone Trends and Seasonal Patterns in Time Series of Environmental Data
    (The Information Society and Enlargement of the European Union, 2003) Hussian, Mohamed; Grimvall, Anders
    Most of the currently used methods for time series analysis have been developed for official statistics and economic forecasting. This article is devoted to new non-parametric procedures that take into account some very widespread features of environmental data. In particular, we propose an algorithm for simultaneous estimation of monotone temporal trends and smooth seasonal patterns. Similar algorithms may also be used to combine the extraction of trend and seasonal components with removal of natural fluctuations that can be attributed to meteorological and other physical forcings of the environmental system under consideration.
  • Konferenzbeitrag
    Data Models for Physical Flow
    (The Information Society and Enlargement of the European Union, 2003) Löfving, Erik; Grimvall, Anders
    The systems used to handle data on physical flows need to be harmonised to enable joint analyses of data from different sources. We propose an integrated system in which a relational model is used to ensure compact storage, and a data cube is employed to support statistical analysis of the collected data. In addition, we show that matrix operations on ordinary 2-dimensional flow matrices can easily be generalised to operations on data cubes of arbitrary dimension.
  • Konferenzbeitrag
    Estimation of Human Impact in the Presence of Natural Fluctuations
    (Environmental Communication in the Information Society - Proceedings of the 16th Conference, 2002) Grimvall, Anders
    Natural fluctuations in weather conditions can long conceal or distort important trends in the human impact on the environment. The EU-IST project IMPACT provides methods and tools that will facilitate extraction of anthropogenic signals from collected data. In this paper, we show how deterministic, process-oriented models can be incorporated into statistical procedures for the estimation of anthropogenic trends in air and water quality.
  • Konferenzbeitrag
    Normalisation of Environmental Quality Data
    (Sustainability in the Information Society, 2001) Grimvall, Anders; Wackernagel, Hans; Lajaunie, Christian
    Normalisation of environmental data aims at clarifying the human impact on the environment by suppressing meteorologically driven fluctuations and other natural variation in the collected data. This paper shows that the procedures presently used to adjust ai r and water quality data have a common probabilistic framework. Furthermore, this framework can support a number of new techniques for the normalisation of both temporal and spatial patterns in environmental data. In particular, it is shown that deterministic, physics-based models can be incorporated into statistical normalisation procedures.