GIMAS9AD1 - Master IMSD - Mines Nancy
Statistique spatiale
| Crédits : 2 ECTS Durée : 21 heures | Semestre : S9 |
Responsable(s) : Radu Stoica, professeur radu-stefan.stoica@univ-lorraine.fr |
Mots clés : Data Mining, data science, spatial data analysis |
Pré requis : master M1 in mathematics or equivalent (measure theory, probability theory, statistics, stochastic simulation)
|
Objectif général : describe and characterize structured information hidden but available in spatial-data |
Programmes et contenus : Description: Point processes (Poisson, Cox, Gibbs). Markovianity and integrability. Hammersley Clifford theorem. Campbell Mecke theorem. Palm distributions. Exploratory statistics tools. Simulation algorithms (Metropolis-Hastings, Gibbs, CFTP). Bayesian inference. Applications : geosciences, image analysis, astrophysics.
Learning outcomes: Understanding some of the most known and some of the very recent models for spatial data. Identifying which type of the model may be applied to certain types of situations described by spatial data. Using and building appropriate algorithms to be applied for real data analysis.
Targeted competencies: Knowing how to chose models and appropriate simulation algorithms adapted to real situations described by spatial data. Being able to implement a mathematical methodology for spatial data analysis, validate and intepret the obtained results.
|
Compétences : |
Niveaux | Description et verbes opérationnels |
Connaître |
|
Comprendre |
|
Appliquer | |
Analyser |
|
Synthétiser |
|
Évaluer
|
|
Évaluations : |
| | | | |