View Spat. Interp. Comparison 2004 (public)

2011-01-04 18:21 by cong | Version 1 | Rating Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star
Rating
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Overall (based on 0 votes)
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Interesting
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Documentation
Summary

Spatial Interpolation Comparison 2004, a geostatistical data set. Automatic mapping with prior knowledge in situations of routine and emergency

License
CC0
Dependencies
Tags
comparison geostatistics GIS interpolation spatial
Attribute Types
Download
zip (437.9 KB)

Files are converted on demand and the process can take up to a minute. Please wait until download begins.

Completeness of this item currently: 100%.
You can edit this item to add more meta information and make use of the site's premium features.
Original Data Format
zip
Name
Version mldata
Comment
Names
Data (first 10 data points)
    ZIP archive SIC2004_README.pdf, 1st_file_true_values.csv, 2nd_file_true_values.csv, sic2004_01.csv, sic2004_02.csv, sic2004_03.csv, sic2004_04.csv, sic2004_05.csv, sic2004_06.csv, sic2004_07.csv, sic2004_08.csv, sic2004_09.csv, sic2004_10.csv, SIC2004_input.csv, SIC2004_Introduction_AGIS.pdf, SIC2004_joker.csv, SIC2004_out.csv
Description

Automatic mapping with prior knowledge in situations of routine and emergency

Spatial Interpolation Comparison 2004 The data and the whole international statistical exercise are described in the "Events" section of AI-GEOSTATS.

Excerpt from the description: The Spatial Interpolation Comparison (SIC) 2004 exercise was organised during the summer 2004 to assess the current know-how in the field of “automatic mapping”. The underlying idea was to explore the way algorithms designed for spatial interpola- tion can automatically generate maps on the basis of information collected regularly by monitoring networks. Participants to this exercise were invited to use some prior information to design their algorithms and to test them by applying the software code to two given datasets. Estimation errors were used to assess the relative perform- ances of the algorithms proposed. Participants were not only invited to minimize estimation errors but also to design the algorithms so as to render them suitable for decision-support systems used in emergency situations. The data used in this exer- cise were daily mean values of gamma dose rates measured in Germany. This paper presents the exercise and the data used more in detail.

URLs
https://wiki.52north.org/bin/view/AI_GEOSTATS/EventsSIC2004
Publications
    Data Source
    Applied GIS (AGIS) published the accepted papers in a special issue (Vol. 1, No. 2). See http://publications.epress.monash.edu/loi/ag/index.html A hardcopy version including selected papers published online as well as unpublished material written by invited authors has been published in: Reference: Automatic mapping algorithms for routine and emergency monitoring data. EUR 21595 EN EC. Dubois G. (Ed.), Office for Official Publications of the European Communities, Luxembourg, 150 p., November 2005.
    Measurement Details
      The data used in the frame of SIC2004 are measurements of gamma dose rates that have
    

    been extracted from the European Radiological Data Exchange Platform (EURDEP, see http://eurdeppub.jrc.it/) database (De Cort and De Vries, 1997). EURDEP is a system developed by the Radioactivity Environmental Monitoring (REM) group to make European radiological monitoring data available to decision-makers. From this database, 10 sets of mean daily values were selected from 2003, by drawing roughly one day at random from each month. A further filtering of these data was applied to select only measurements reported by the German national automatic monitoring network (IMIS) of the Federal Office for Radiation Protection (BfS, http://www.bfs.de/). This selection ensured that the data were homogeneous in terms of measurement technique and that the densest monitoring network in Europe, i.e. the German one, was included. From around 2000 monitoring stations in Germany, 1008 stations (their relative locations are shown in the right part of Figure 1) were selected by drawing a rectangular window. These stations were common to each of the 10 datasets, and all values reported for each day were selected. Two types of data were provided: 1) coordinates and observations made of the variable X at n fixed locations, 2) and geographical coordinates only for the N-n locations at which values of X should be estimated through the mapping algorithm.

    Usage Scenario
     Computational objectives of SIC2004
    The framework in which participants had to design their algorithms was defined by the
    

    following computational objectives. The mapping algorithms had to generate results: * in a minimum amount of time (e.g. a few hours); * without any human intervention, in the sense that only manual downloading and uploading of the data used for the exercise were allowed; * that were “reasonable”, that is the Root Mean Squared Error (RMSE) and the Mean Absolute Error (MAE) had to be kept as low as possible.

    revision 1
    by cong on 2011-01-04 18:21

    No one has posted any comments yet. Perhaps you would like to be the first?

    Leave a comment

    To post a comment, please sign in.

    This item was downloaded 1604 times and viewed 383 times.

    No Tasks yet on dataset Spat. Interp. Comparison 2004

    Submit a new Task for this Data item

    Data

    Sort by

    Disclaimer

    We are acting in good faith to make datasets submitted for the use of the scientific community available to everybody, but if you are a copyright holder and would like us to remove a dataset please inform us and we will do it as soon as possible.

    Data | Task | Method | Challenge

    Acknowledgements

    This project is supported by PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning)
    PASCAL Logo
    http://www.pascal-network.org/.