TY  - GEN
AU  - Neitzel,Frank
AU  - Neitzel,Frank
TI  - Stochastic Models for Geodesy and Geoinformation Science
SN  - books978-3-03943-982-9
PY  - 2021///
CY  - Basel, Switzerland
PB  - MDPI - Multidisciplinary Digital Publishing Institute
KW  - History of engineering & technology
KW  - bicssc
KW  - EM-algorithm
KW  - multi-GNSS
KW  - PPP
KW  - process noise
KW  - observation covariance matrix
KW  - extended Kalman filter
KW  - machine learning
KW  - GNSS phase bias
KW  - sequential quasi-Monte Carlo
KW  - variance reduction
KW  - autoregressive processes
KW  - ARMA-process
KW  - colored noise
KW  - continuous process
KW  - covariance function
KW  - stochastic modeling
KW  - time series
KW  - elementary error model
KW  - terrestrial laser scanning
KW  - variance-covariance matrix
KW  - terrestrial laser scanner
KW  - stochastic model
KW  - B-spline approximation
KW  - Hurst exponent
KW  - fractional Gaussian noise
KW  - generalized Hurst estimator
KW  - very long baseline interferometry
KW  - sensitivity
KW  - internal reliability
KW  - robustness
KW  - CONT14
KW  - Errors-In-Variables Model
KW  - Total Least-Squares
KW  - prior information
KW  - collocation vs. adjustment
KW  - mean shift model
KW  - variance inflation model
KW  - outlierdetection
KW  - likelihood ratio test
KW  - Monte Carlo integration
KW  - data snooping
KW  - GUM analysis
KW  - geodetic network adjustment
KW  - stochastic properties
KW  - random number generator
KW  - Monte Carlo simulation
KW  - 3D straight line fitting
KW  - total least squares (TLS)
KW  - weighted total least squares (WTLS)
KW  - nonlinear least squares adjustment
KW  - direct solution
KW  - singular dispersion matrix
KW  - laser scanning data
N1  - Open Access
N2  - In geodesy and geoinformation science, as well as in many other technical disciplines, it is often not possible to directly determine the desired target quantities. Therefore, the unknown parameters must be linked with the measured values by a mathematical model which consists of the functional and the stochastic models. The functional model describes the geometrical–physical relationship between the measurements and the unknown parameters. This relationship is sufficiently well known for most applications. With regard to the stochastic model, two problem domains of fundamental importance arise: 1. How can stochastic models be set up as realistically as possible for the various geodetic observation methods and sensor systems? 2. How can the stochastic information be adequately considered in appropriate least squares adjustment models? Further questions include the interpretation of the stochastic properties of the computed target values with regard to precision and reliability and the use of the results for the detection of outliers in the input data (measurements). In this Special Issue, current research results on these general questions are presented in ten peer-reviewed articles. The basic findings can be applied to all technical scientific fields where measurements are used for the determination of parameters to describe geometric or physical phenomena
UR  - https://mdpi.com/books/pdfview/book/3387
UR  - https://directory.doabooks.org/handle/20.500.12854/68374
ER  -