Geostatistics and Remote Sensing

Lecture 1: Course overview; Digital mapping: Geoids, local and global coordinate systems, coordinate transformations; Map projections;

Lecture 2: Electromagnetic spectrum, spectral data, false color images, resolution, photogrammetry

Lecture 3: Errors in measurements; Global Navigation Satellite System data

Lecture 4: Deterministic interpolation, distance, spatial continuity, Inverse distance, LiDAR data

Lecture 5: Convex hull, Voronoi diagrams, Delaunay triangulation, Triangulated Irregular Networks,

Lecture 6: Terrain classification. Band data, feature space, Supervised classification, training data, decision tree, linear separation, nearest centroid classification, Spectral angular mapping or Support Vector Machines, Maximum likelihood classification. Unsupervised classification, K-means clustering, Confusion matrix

Lecture 7: Least squares: mean, variance, covariance, correlation, Random function, minimizing the least squares error, least squares geometry

Lecture 8: Stochastic interpolation. Kriging the mean, Simple Kriging equations, experimental covariance function, Positive definiteness, variogram, Sill, Range, Nugget.

Lecture 9: Quality en Digital Terrain Analysis. plane fitting, variance, roughness, surface normals, slope, aspect, orientation, gradient, Quality assessment. Robust methods, RANSAC, Monte Carlo simulation.