Discussion: Urban terrain segmentation for the Marmara Region

1
Discussion Urban terrain segmentation for the
Marmara Region

• Speaker Akarun
• Discussant Lerner-Lam

2
Classic Geophysical Inverse Problem

• Forward Problem
• Image F Classifications segments
• Segments geographic basis functions, change
  with time.
• Useful for hypothesis testing and examining prior
  assumptions about geographic variation.

3
Inverse Problem

• Classifications segments F-1 Image
• F-1 F
• Inverse generalized inverse (approximate)
• Treated by Stochastic Techniques and
• Genetic or Evolutionary Algorithms, AI
  (training), matched filtering, wavelets,
  empirical orthogonal eigenfunctions analysis, etc.

4
Basic Issues

• Uniqueness of derived classifications. Do
  different combinations of classifications fit the
  data equally well?
• Error model, including covariance. Uncertainties
  as input to further calculations.
• Resolving power of data.
• Geographical resolution (function of instrument)
• Ability to distinguish between classifications
• Optimizing a penalty function, including prior
  knowledge

5
Other issues

• Proxy set
• What needs to be quantified?
• Relate to multidisciplinary needs
• What is measurable/detectable?
• Collateral data sets
• Groundtruth minimum (necessary and sufficient)
  tests
• Baselining time dimension
• Background and causal changes
• Global experience database
• EOF ( t) time variation of geographic basis
  functions