• Home
• Organization
• Business solutions
• For governments
• Our Research
  • Energy technology
  • Environmental modelling
  • Environmental risk and health
  • Materials Technology
  • Remote Sensing
  • Separation and conversion technology
  • Transition energy and environment
• Events
• Jobs
• News
• Contact
• Links

Description

Project Objectives
In ecosystems where two or more vegetation types or plant species co-exist, the success of remote sensing (RS) based applications is still limited. This is because image interpretation is complicated by the high spectral similarity between the different plant species which is strengthened by the composite nature of the reflectance signals obtained by the RS sensor. The main objective of this project is to explore the potential of hyperspectral image analysis for individual plant species mapping. The potential of Spectral Mixture Analysis (SMA) and multi-temporal image classification is evaluated. It is anticipated that by assimilating both techniques the spectral similarity problem in intimately mixed vegetation systems can be addressed effectively. A multi-temporal unmixing based feature extraction technique is therefore proposed. The basic hypothesis is that the spectral similarity and spectral mixture problem can effectively be mitigated by integration of iterative mixture analysis cycles and automated feature selection in a hyperdimensional spectro-temporal feature space.

Methodology
The developed multi-temporal SMA approach is characterized by three well-defined processing steps: (i) Spectral Mixture Modeling Supported by ray-tracing simulations the extent and nature of multiple photon scattering will be characterized; (ii) Spectral Endmember Extraction Well-established endmember selection techniques will be evaluated and compared; (iii)  Variable Endmember Model Develop a modified SMA integrating iterative mixture analysis cycles and automated feature selection in a hyperdimensional spectro-temporal feature space. Time-series of Hyperion imagery will be evaluated. However, given the low signal-to-noise ratio, AVIRIS data convoluted up to lower spatial resolution and ray tracing simulations will be used for algorithm development and testing phases. Results will be compared to traditional SMA and multi-temporal classification techniques.

(Expected) Results
Spectral mixture modeling – (i) novel insights in the effects of multiple scattering and nonlinear mixing in mixed forest stands; (ii) a mathematical mixture model for mixed forest stands.
Spectral endmember extraction –  an endmember extraction technique to built multi-temporal time series of spectral properties of individual plant species in mixed vegetation systems.
Variable Endmember model –  (i) a modified multi-temporal unmixing approach providing improved unmixing capabilities compared to traditional techniques. Benefits are expected to be high in mixed vegetation stands; (ii) report on validation results of the multi-temporal unmixing approach for invasive species mapping; (iii) based on the analysis, a report on preferred data acquisition windows and spectral requirements for future sensors and image tasking schemes.

VITO Contribution
Project coordination and Principal Investigator (Ben Somers). KULeuven will assist in implementing nonlinear mixture events while CIS will provide data and overall guidance/input on ecological processes.

Partners

• Carnegie Institution of Science & Stanford University (U.S.A.)
• KULeuven (Belgium)

Contact:

Ben Somers
Tel. + 32 14 33 67 68
Fax + 32 14 32 27 95
Send a message to Ben Somers