A weighted normalized likelihood procedure for empirical land change modeling
- Resource Type
- Authors
- J. Ronald Eastman; Kaixi Zhang; Stefano C. Crema; Hannah R. Rush
- Source
- Modeling Earth Systems and Environment. 5:985-996
- Subject
- Land change
Pixel
Computer science
Pooling
Posterior probability
0211 other engineering and technologies
Sampling (statistics)
021107 urban & regional planning
02 engineering and technology
010501 environmental sciences
Perceptron
01 natural sciences
Statistics
Covariate
Computers in Earth Sciences
Statistics, Probability and Uncertainty
General Agricultural and Biological Sciences
0105 earth and related environmental sciences
General Environmental Science
- Language
- ISSN
- 2363-6211
2363-6203
A critical foundation for empirical land change modeling is the mapping of transition potentials—quantitative evaluations of the readiness or suitability of land to go through a transition. This paper presents a procedure based on empirically determined normalized likelihoods of transition. It shows that these normalized likelihoods equate to posterior probabilities if case–control sampling is carried out among historical instances of change and persistence. The posterior probabilities can then be aggregated at the pixel level across multiple covariates using linear opinion pooling where the pixel-specific weight for each covariate is determined locally by its ability to distinguish between the alternatives of change or persistence. Thus, covariates with spatially varying diagnostic ability can be productively incorporated. The resulting algorithm is shown to have a skill comparable to that of a multi-layer perceptron approach with the advantage of high efficiency and amenability to distributed processing in a cloud environment.