1 / 31

Forecasting Space Weather and Effects using Knowledge-Based Neurocomputing

Forecasting Space Weather and Effects using Knowledge-Based Neurocomputing. H.Lundstedt, P.Wintoft, T.Hasanov, F. Boberg, H. Gleisner and I. Kronfeldt. Forecasting Space Weather and Effect using Knowledge-Based Neurocomputing - How did it all start in Lund?

kadeem-mccormick
Download Presentation

Forecasting Space Weather and Effects using Knowledge-Based Neurocomputing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Forecasting Space Weather and Effects using Knowledge-Based Neurocomputing H.Lundstedt, P.Wintoft, T.Hasanov, F. Boberg, H. Gleisner and I. Kronfeldt

  2. Forecasting Space Weather and Effect using Knowledge-Based Neurocomputing - How did it all start in Lund? - How has it been covered by media in Sweden? - What is Knowledge-Based Neurocomputing (KBN)? - ESA/Lund Forecast Service based on KBN

  3. Work on Solar-Terrestrial Relations 1980-1981 Geomagnetic activity (Dst) after solar south- or northward directed B. Cosmic ray variation at time of solar wind IR and VAI (storminess)

  4. Lund Solar-Terrestrial Model, 1989

  5. Implementation of Lund Solar-Terrestrial Model, 1989 Inductive Expert System

  6. Neural Network Prediction of Dst, Lund 1990 Space weather was mentioned for the first time in Swedish media 1991

  7. Space weather and TV, 1997

  8. Modeling and Forecasting with Knowledge-Based Neurocomputing The basis of using neural networks as mathematical models is ”mapping”. Given a dynamic system, a neural network can model it on the basis of a set of examples encoding the input/output behavior of the system. It can learn the mathematical function underlying the system operation (i.e. generalize not just fit a curve), if the network is designed (architechure, weights) and trained properly (learning algorithm). Both architechure and weights can be determined from differential equations which describe the causal relations between the physical variables (solution of diff eq is approximized by a RBF). The network (KBN) is then trained with observations. The architechure (number of input and hidden nodes) can also be determined from dynamic system analysis (reconstruction of the attractor from time series gives dimension). Neural networks can discover laws from regularities in data (Newton’s law e.g.). If one construct a hierachy of neural networks where networks at each level can learn knowledge at some level of abstraction, even more advanced laws can be dicovered.

  9. Over twenty years later

  10. User Guide: What is Space Weather?

  11. User Guide: Specific User Information

  12. The Sun Stoplight Applet

  13. The L1 Stoplight Applet

  14. The Earth Stoplight Applet

  15. Latest Info: About CMEs

  16. Latest Info: About satellite anomalies

  17. Latest info: About forecasted Kp,Dst,AE,GIC

  18. Plots of far and nearside solar activity

  19. Plot of the proton flux

  20. Plot of forecasted AE index

  21. Plot of forecasted Kp index

  22. Test a Dst model for selected events or for your own values

  23. Summary - Today’s forecast service is user oriented and in real-time - It will be implemented for specific users (power industry, satellite operators, public (RWC)) - The software package is developed in Java and therefore easily updated for new data and new better models - The stoplight events are logged to keep track of the quality of the forecasts

More Related