Application of Geostatistical Methods and Wavelets to the Analysis of Hyperspectral Imagery and the Testing of a Moving Variogram

Abstract

This is the third report of the project. It is a short one, but it is a stand-alone piece of work. It is an aide memoire for sampling. It embraces both design-based sampling, which is based on classical statistics, and model-based sampling which is underpinned by geostatistics. This work is a guide for sampling in the field or pixels from images. It starts with what the user should consider before sampling, i.e. the target population, the sample support (volume of sample), the individuals, what the data are to be used for, what kind of predictions are required. Based on the kind of predictions required the user will decide either to have a sample design for design- based estimation or one for model-based prediction.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 16, 2001
Accession Number
ADA389700

Entities

People

  • Margaret A. Oliver

Organizations

  • University of Reading

Tags

DTIC Thesaurus Topics

  • Analysis Of Variance
  • Data Science
  • Ecology
  • Errors
  • Geographic Regions
  • Grids
  • Hyperspectral Imagery
  • Information Science
  • Intervals
  • Measurement
  • Random Variables
  • Sampling
  • Soil Surveys
  • Statistical Sampling
  • Statistics
  • Stochastic Processes
  • Surveys

Readers

  • Image Processing and Computer Vision.
  • Statistical inference.
  • Systems Analysis and Design