Two new methods for solving large scale least squares in geodetic surveying computations

Ch. Murigande, Ph.L. Toint, P. Pâquet

Research output: Contribution to journalArticlepeer-review

Abstract

This paper considers the solution of linear least squares problems arising in space geodesy, with a special application to multi-station adjustment by a short arc method based on Doppler observations. We recall briefly the widely used second-order regression algorithm due to Brown for reducing the normal equations system. Then we propose two algorithms which avoid the use of the normal equations. The first one is a direct method that applies orthogonal transformations to the observation matrix directly, in order to reduce it to upper triangular form. The solution is then obtained by backsubstitution. The second method is iterative and uses a preconditioned conjugate gradient technique. A comparison of the three procedures is provided on data of the second European Doppler Observation Campaign (EDOC-2). © 1986 Bureau Central de L'Association Internationale de Géodésie.
Original languageEnglish
Pages (from-to)311-328
Number of pages18
JournalBulletin Géodésique
Volume60
DOIs
Publication statusPublished - 1 Dec 1986

Fingerprint

Dive into the research topics of 'Two new methods for solving large scale least squares in geodetic surveying computations'. Together they form a unique fingerprint.
  • Linear least-squares in geodesy

    Author: Murigande, C., 1986

    Supervisor: Toint, P. (Supervisor), Golub, G. (External person) (Jury) & Paquet, P. (External person) (Jury)

    Student thesis: Doc typesDoctor of Sciences

Cite this