eduzhai > Applied Sciences > Engineering >

Lateral land movement prediction from GNSS position time series in a machine learning aided algorithm

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: We investigate the accuracy of conventional machine learning aided algorithmsfor the prediction of lateral land movement in an area using the preciseposition time series of permanent GNSS stations. The machine learningalgorithms that are used are tantamount to the ones used in [1], except for theradial basis functions, i.e. multilayer perceptron, Bayesian neural network,Gaussian processes, k-nearest neighbor, generalized regression neural network,classification and regression trees, and support vector regression. Acomparative analysis is presented in which the accuracy level of the mentionedmachine learning methods is checked against each other. It is shown that themost accurate method for both of the components of the time series is theGaussian processes, achieving up to 9.5 centimeters in accuracy.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×