Grant: Discovery Grants Program - Individual
Queen's University
$15,000.00
Multi-scale classification error and uncertainty modeling on categorical maps from remotely sensed data
EF 2010-11
Résumé
Environmental modeling often requires inputs of detailed land cover and vegetation data at different spatial and temporal scales. Airborne and satellite remotely-sensed data play a key role in generating categorical maps such as land cover because of its capacity of collecting data over broad expanses of land. With widespread use of remote sensing and geographical information system (GIS) technologies, a great deal of earth observation data has been accumulated along with a wide range of spatial, spectral and temporal scales. These developments demand significant changes in the approach of analyzing and integrating these earth observation data. The effects of spatial, spectral and temporal resolutions on the classification accuracy of land cover and other categorical maps have received growing attention. Compared with rapidly growing data availability, there is a clear lag in the development of analysis methods and efficient error models for handling multi-scale data of increasing complexity and quantity.
The objectives of this project are: a) to examine the sensitivity of classification errors and uncertainty on land cover classification procedures at different resolutions and landscapes; b) to evalute the accuracy of different sub-pixel mapping approaches; and c) to develop error models and calibration approaches for linking classification errors across different resolutions. The long-term goal is to understand error and uncertainty on categorical maps generated from remotely sensed data. This project will develop a theoretical framework for modeling classification errors contained in categorial maps across scales and and using them to develop better and more robust parameter sets for a variety of environmental applications such as regional and global climate change, hydrological, land use/cover and other environmental modeling. Within the proposed budget and research scope at least two graduate students and two undergraduate students will be trained each year.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
250400-2008
Name nom
Chen, DongMei
Department département
Geography
Organization id
29
Institution établissement
Queen's University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2008
Award amount
15000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
9
Committee name en
Environmental Earth Sciences
Committee name fr
Sc. de la Terre : environ.
Area of application code
1203
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Earth sciences
Area of application fr
Sciences de la terre
Research subject code
4102
Research subject group en
Geographical information
Research subject group fr
Information géographique
Research subject en
Remote sensing
Research subject fr
Télédétection
Partie
3
Nb partie
5
Application title
Multi-scale classification error and uncertainty modeling on categorical maps from remotely sensed data
Keyword
NSERC
Application summary
Environmental modeling often requires inputs of detailed land cover and vegetation data at different spatial and temporal scales. Airborne and satellite remotely-sensed data play a key role in generating categorical maps such as land cover because of its capacity of collecting data over broad expanses of land. With widespread use of remote sensing and geographical information system (GIS) technologies, a great deal of earth observation data has been accumulated along with a wide range of spatial, spectral and temporal scales. These developments demand significant changes in the approach of analyzing and integrating these earth observation data. The effects of spatial, spectral and temporal resolutions on the classification accuracy of land cover and other categorical maps have received growing attention. Compared with rapidly growing data availability, there is a clear lag in the development of analysis methods and efficient error models for handling multi-scale data of increasing complexity and quantity.
The objectives of this project are: a) to examine the sensitivity of classification errors and uncertainty on land cover classification procedures at different resolutions and landscapes; b) to evalute the accuracy of different sub-pixel mapping approaches; and c) to develop error models and calibration approaches for linking classification errors across different resolutions. The long-term goal is to understand error and uncertainty on categorical maps generated from remotely sensed data. This project will develop a theoretical framework for modeling classification errors contained in categorial maps across scales and and using them to develop better and more robust parameter sets for a variety of environmental applications such as regional and global climate change, hydrological, land use/cover and other environmental modeling. Within the proposed budget and research scope at least two graduate students and two undergraduate students will be trained each year.