DocumentCode :
3197221
Title :
Combining fossil and sunspot data: committee predictions
Author :
Wan, Eric A.
Author_Institution :
Dept. of Electr. Eng., Oregon Graduate Inst., Portland, OR, USA
Volume :
4
fYear :
1997
fDate :
9-12 Jun 1997
Firstpage :
2176
Abstract :
It is hypothesized that 680 million years ago solar magnetic storms producing ultraviolet and X-radiation affected the Earths ozone layer, which in turn influenced the variations in the silt deposition from glacial run-off. Preserved as fossils discovered in South Australia, the striation widths constitute clues to ancient solar activity. Utilizing this noisy data, the author has improved his ability to predict the modern sunspot series. In this paper, the author details how the prediction results were achieved through training on the fossil data and committee predictions with the sunspots. Through this exercise, the author has develop general methods for combining predictors and also time series that may be related but separated in time
Keywords :
Sun; X-ray astronomy; astronomy; astronomy computing; atmospheric composition; geology; geophysics computing; neural nets; oceanography; ozone; seafloor phenomena; sediments; solar activity; solar-terrestrial relationships; sunspots; terrestrial atmosphere; ultraviolet astronomy; O3; Precambrian; Proterozoic; South Australia; Sun; UV radiation; X-ray emission; atmosphere; chemical composition; committee prediction; computing method; forecasting; fossil data; geology; glacial run-off; layered sediment; marine sediment; neural net; ocean; ozone layer; ozonosphere; palaeoatmosphere; palaeocean; palaeontology; paleoatmosphere; paleocean; paleontology; prediction; predictor; silt deposition; solar activity; solar magnetic storm; solar radiation; solar terrestrial relationship; stratigraphy; stratosphere; striation width; stromatolite; sunspot; sunspot series; ultraviolet flux; varve; Australia; Benchmark testing; Earth; Feedforward neural networks; Modems; Neural networks; Shape; Storms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
Type :
conf
DOI :
10.1109/ICNN.1997.614245
Filename :
614245
Link To Document :
بازگشت