Prediction of Earth orientation

cracklegulleyAI and Robotics

Oct 19, 2013 (3 years and 11 months ago)

82 views

Prediction of Earth orientation
parameters

by artificial neural networks


Kalarus Maciej and Kosek Wiesław

Space Research Centre, Polish Academy of Sciences

Annual Seminar of Commission of Satellite Geodesy,


EARTH ROTATION AND SATELLITE GEODESY

-

FROM ASTROMETRY TO GNSS

Warsaw, 18
-
19 September 2003



In

this

poster

the

Neural

Network

Toolbox

version

3
.
0
.
1

software

of

Matlab

ver
.
5
.
3

was

used

to

predict

the

IERS

EOPC
04

x,

y

pole

coordinates

data

and

obtained

results

were

compared

to

the

predictions

of

the

IERS

Sub
-
Bureau

for

Rapid

Service

and

Prediction
.

Prediction of x, y pole coordinates data by combination of the LS extrapolation and
Neural Network prediction


x, y

LS extrapolation

residuals

Prediction of

x, y

LS extrapolation

residuals

LS extrapolation

of x, y

Prediction of

x, y

Neural Network

x, y

EOPC04


pole coordinates
data

x
,
y
LS model

Polar motion model




linear trend


Chandler oscillation

annual oscillation




Prediction of the x, y pole coordinates data by combination of
the LS extrapolation and the NN prediction




Fig. 10.

The absolute values of the difference between x, y pole coordinates data and
their prediction being the combination of the LS extrapolation and the NN prediction of
the LS extrapolation residuals computed at different starting prediction epochs.

Fig. 11.

The mean prediction error in 1984
-

2003.6 of the x, y pole coordinates data
computed from combination of the LS extrapolation and the NN prediction of the LS
extrapolation residuals as well as of the IERS
Sub
-
Bureau for Rapid Service and
Prediction.

The mean prediction error