Abstract
The problem of inferring information about the Earth can be described as a data integration problem, where the solutions a probability distribution that combines all available information. This chapter presents the methods for probabilistic characterization of different kinds of geo-information. Then a number of methods that allow inferring information from the probability distribution that combines all available information are discussed. Straight forward application of classic sampling algorithms such as the rejection sampler and the Metropolis algorithm will in most cases lead to computationally intractable problems. A wide range of statistical methods, providing varying degrees of information content, are currently available that can be used with the extended Metropolis algorithm and that allow characterization of probability distributions describing quite complex and geologically realistic spatial features. These methods allow building statistical models that assume, in principle, a lot more than is typically known.
| Original language | English |
|---|---|
| Title of host publication | Integrated imaging of the earth : Theory and Applications |
| Number of pages | 24 |
| Publisher | Wiley |
| Publication date | 1 Apr 2016 |
| Pages | 93-116 |
| ISBN (Print) | 978-1-118-92905-6 |
| ISBN (Electronic) | 9781118929063 |
| DOIs | |
| Publication status | Published - 1 Apr 2016 |
| Externally published | Yes |
Keywords
- Data integration problem
- Geo-information
- Metropolis-Hastings Algorithm
- Probability distribution
- Rejection sampler