Objectives and Contextualisation
At the end of the course, the student will be able to:
Basic aspects of digitization and advanced aspects of topological structuring, as well as modeling tools, obtaining thematic cartography and quantification of the reliability of the products obtained.
Proper use of the statistical concepts that underpin the automatic classification of multivariate data, and in particular those provided by satellite images as well as the most appropriate criteria for the visual interpretation of remote sensor images.
Content
PHOTOINTERPRETATION
Visual techniques for identifying land uses and land covers.
Recognition of different types of land uses and land covers.
Photointerpretation: Main applications in the study of the natural and artificial environment.
Interpretation of multispectral images.
Cartography of support for photointerpretation.
STATISTICAL METHODS
Introduction to multivariate data. Characterization of distributions. Normality test. Correlation. Implications in Remote Sensing. Standardization. Principal Component Analysis.
Statistical distances between individuals, populations and between individuals and populations. Implications of the scaling of the variables. Divergence measures.
Obtaining new information (multitemporality, collateral data, indexes and transformations). Information reduction from the samples and from the variables. Introduction to obtaining continuous variables and categorical variables: linear and non-linear, simple and multiple regression, classification, etc.
Multiple regression applied to the interpolation of climatic surfaces.
Generalized linear models applied to obtaining suitability surfaces based on the ecological niche modelling.
Hierarchical and non-hierarchical classification. Supervised, unsupervised and hybrid classification; fuzzy classification.
Segmentation of images. Scales and scene models. Processing methods that take spatial information into account. Segmentation methods. Classification by segments.
Neural networks.
Generalization of results in categorical cartography. Direct methods and smart methods.
Verification of results in binary cartography. Sampling.
Verification of results in categorical cartography. Sampling.
Competences
Continue the learning process, to a large extent autonomously.
Identify and propose innovative, competitive applications based on the knowledge acquired.
Integrate knowledge and use it to make judgements in complex situations, with incomplete information, while keeping in mind social and ethical responsibilities.
Use acquired knowledge as a basis for originality in the application of ideas, often in a research context.
Use different specialised GIS and remote sensing software, and other related software.
Use the different techniques for obtaining information from remote images.
Write up and publicly present work done individually or in a team in a scientific, professional context.
Learning Outcomes
Continue the learning process, to a large extent autonomously.
Identify and propose innovative, competitive applications based on the knowledge acquired.
Integrate knowledge and use it to make judgements in complex situations, with incomplete information, while keeping in mind social and ethical responsibilities.
Show expertise in using digitalisation and topological structuring tools, modelling tools, and tools for supervised, unsupervised and mixed image classification.
Use acquired knowledge as a basis for originality in the application of ideas, often in a research context.
Work with the statistical concepts underpinning the automatic classification of satellite images, and the most suitable criteria for visually interpreting remote images.
Write up and publicly present work done individually or in a team in a scientific, professional context.