liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Image Based Visualization Methods for Meteorological Data
Linköping University, Department of Science and Technology. Linköping University, The Institute of Technology.
2004 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Visualization is the process of constructing methods, which are able to synthesize interesting and informative images from data sets, to simplify the process of interpreting the data. In this thesis a new approach to construct meteorological visualization methods using neural network technology is described. The methods are trained with examples instead of explicitely designing the appearance of the visualization.

This approach is exemplified using two applications. In the fist the problem to compute an image of the sky for dynamic weather, that is taking account of the current weather state, is addressed. It is a complicated problem to tie the appearance of the sky to a weather state. The method is trained with weather data sets and images of the sky to be able to synthesize a sky image for arbitrary weather conditions. The method has been trained with various kinds of weather and images data. The results show that this is a possible method to construct weather visaualizations, but more work remains in characterizing the weather state and further refinement is required before the full potential of the method can be explored. This approach would make it possible to synthesize sky images of dynamic weather using a fast and efficient empirical method.

In the second application the problem of computing synthetic satellite images form numerical forecast data sets is addressed. In this case a mode is trained with preclassified satellite images and forecast data sets to be able to synthesize a satellite image representing arbitrary conditions. The resulting method makes it possible to visualize data sets from numerical weather simulations using synthetic satellite images, but could also be the basis for algorithms based on a preliminary cloud classification.

Place, publisher, year, edition, pages
Institutionen för teknik och naturvetenskap , 2004. , 92 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1137
Keyword [en]
Visualization, Meteorological Data, Artificial Neural Networks, High-Dynamic-Range images, Satellite Data, Classification
National Category
Computer Science
Identifiers
URN: urn:nbn:se:liu:diva-4325ISBN: 91-85297-00-3 (print)OAI: oai:DiVA.org:liu-4325DiVA: diva2:20599
Presentation
2004-12-17, K3, Campus Norrköping, Linköpings universitet, Linköping, 10:15 (English)
Opponent
Supervisors
Note
Report code: LiU-Tek-Lic-2004:66.Available from: 2005-10-14 Created: 2005-10-14 Last updated: 2016-08-31
List of papers
1. Eigenskies: a method of visualizing weather prediction data
Open this publication in new window or tab >>Eigenskies: a method of visualizing weather prediction data
2003 (English)In: Proceedings of SPIE - IS&T Electronic Imaging, Visualization and Data Analysis / [ed] Robert F. Erbacher; Philip C. Chen; Jonathan C. Roberts; Matti T. Groehn; Katy Boerner, 2003Conference paper, Published paper (Other academic)
Abstract [en]

Visualizing a weather prediction data set by actually synthesizing an image of the sky is a difficult problem. In this paper we present a method for synthesizing realistic sky images from weather prediction and climate prediction data. Images of the sky are combined with a number of weather parameters (like pressure and temperature) to train an artificial neural network (ANN) to predict the appearance of the sky from certain weather parameters. Hourly measurements from a period of eight months are used. The principal component analysis (PCA) method is used to decompose images of the sky into their eigen components -- the eigenskies. In this way the image information is compressed into a small number of coefficients while still preserving the main information in the image. This means that the fine details of the cloud cover cannot be synthesized using this method. The PCA coefficients together with measured weather parameters at the same time form a data point that is used to train the ANN. The results show that the method gives adequate results and although some discrepancies exist, the main appearance is correct. It is possible to distinguish between different types of weather. A rainy day looks rainy and a sunny day looks sunny.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-13392 (URN)10.1117/12.473931 (DOI)
Available from: 2005-10-14 Created: 2005-10-14 Last updated: 2016-08-31
2. SkyVis, an Application of MATLAB in Meteorological Visualization
Open this publication in new window or tab >>SkyVis, an Application of MATLAB in Meteorological Visualization
2003 (English)In: Proceedings of Nordic Matlab Conference 2003, 2003, 295-300 p.Conference paper, Published paper (Other academic)
Abstract [en]

We present a work in progress, Sky Vis, which makes it possible to synthesize realistic images of the sky using data from weather parameter data sets. A neural-network-based model is trained to predict the appearance of the sky from a weather parameter vector. Hourly measurements of weather parameters (like temperature and pressure) and corresponding images are used as training data. The images are decomposed into their eigen components using the principal component analysis (PCA) method. The image information is thus represented using a small number of coefficients. The results show that the main appearance is correct and that it is possible to distinguish between different types of weather. A limitation is that the method is not able to synthesize images with cloud details. This method is in contrast to many previous methods able to synthesize a sky image which varies with the current weather situation.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-13393 (URN)
Conference
Nordic Matlab Conference, Copenhagen, October the 21st - 22nd, 2003
Available from: 2005-10-14 Created: 2005-10-14 Last updated: 2016-08-31
3. Visualizing weather with synthetic high-dynamic range images
Open this publication in new window or tab >>Visualizing weather with synthetic high-dynamic range images
2004 (English)In: Proceedings of SPIE-IS&T Electronic Imaging, Visualization and Data Analysis / [ed] Robert F. Erbacher; Philip C. Chen; Jonathan C. Roberts; Matti T. Gr÷hn; Katy B÷rner, 2004, 107-116 p.Conference paper, Published paper (Other academic)
Abstract [en]

The appearance of the sky has a fundamental effect on the way human beings perceive an environment. This paper presents a method to compute synthetic high-dynamic-range fisheye images from weather parameter data sets. These images can then be used in global-illumination systems (e. g. Radiance) to define the lighting conditions at an arbitrary weather state. Applications of this technology can be found in flight simulators and in architectural visualization. The method combines artificial neural networks and principal component analysis to associate the appearance of the sky with the state of a weather parameter vector. A model is trained with examples of sky images and weather data from a period of seven months. This model is then used to generate artificial sky images corresponding to a specific weather parameter vector. This is a novel method which contrary to many previous methods is able to synthesize a sky image which varies with the current weather state. The results show that, although it is not possible to represent the cloud details, it is possible to distinguish between different weather states.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-13394 (URN)10.1117/12.525997 (DOI)
Available from: 2005-10-14 Created: 2005-10-14 Last updated: 2016-08-31
4. Computing synthetic satellite images from weather prediction data
Open this publication in new window or tab >>Computing synthetic satellite images from weather prediction data
2004 (English)In: Proceedings of SPIE - IS and T Electronic Imaging, VIsualization and Data Analysis / [ed] Robert F. Erbacher; Philip C. Chen; Jonathan C. Roberts; Matti T. Gr÷hn; Katy B÷rner, 2004, 296-304 p.Conference paper, Published paper (Other academic)
Abstract [en]

Satellite images are important sources of information for meteorologists to predict rapid weather changes, for example storms, now and in the near-future (Nowcasting). It is not possible to use traditional numerical weather forecasts for this purpose since these are computed with a time-lag of several hours. This means that the most recent weather changes are not taken into account. This paper presents a method to compute synthetic satellite images from simulated forecast files. The cloud information in numerical forecast data sets is of much more interest if it can be visualized with a well-known representation like the satellite image. The proposed method uses artificial neural network technology to construct a model which is trained with data from numerical forecasts and classified satellite data captured at the same points in time. The cloud cover parameters in the forecast data set are tied to the cloud classification in the satellite image using a point-to-point representation. The results show that this is a useful method to compute synthetic satellite images. The level of detail in the resulting images is lower than in a real satellite image, but detailed enough to provide information about the principal features of the cloud cover.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-13395 (URN)10.1117/12.526829 (DOI)
Available from: 2005-10-14 Created: 2005-10-14 Last updated: 2016-08-31

Open Access in DiVA

fulltext(3830 kB)286 downloads
File information
File name FULLTEXT01.pdfFile size 3830 kBChecksum MD5
1346a3b44800b192a6bd3626797acb9af297499a5a3effab36e262155e7cecf24c32311a
Type fulltextMimetype application/pdf

Authority records BETA

Olsson, Björn

Search in DiVA

By author/editor
Olsson, Björn
By organisation
Department of Science and TechnologyThe Institute of Technology
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 286 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 578 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf