PREDICTING INTERPLANETARY SHOCKS USING NEURAL NETWORKS

1
PREDICTING INTERPLANETARY SHOCKS USING NEURAL
NETWORKS

• A.Ibrahim PALA
• METU Aerospace Engineering Department
• Senior Student
• 21.12.2005

2
OUTLINE

• WHAT IS AN INTERPLANETARY SHOCK?
• WHAT IS A NEURAL NETWORK?
• HOW THE NEURAL NETWORKS ARE USED TO PREDICT THE
  INTERPLANETARY SHOCKS?
• CONCLUSION

3
INTERPLANETARY SHOCKS

• Charged particles are
• constantly streaming
• outward from the Sun.
• When events such as
• Coronal Mass Ejections
• (CMEs) occur on the Sun,
• an Interplanetary (IP) shock
• may be generated.

4
INTERPLANETARY SHOCKS

• The abrupt boundary formed at the front of a
  plasma cloud moving much faster than the rest of
  the solar wind, as it pushes its way through
  interplanetary space.

5
NEURAL NETWORKS

• NEURONS
• SYNAPSE
• (INPUT-gtWEIGHTS)
• COLLECTOR
• ACTIVATION FUNCTION-gtOUTPUT

6
NEURAL NETWORKS

• CONSTRUCTING A NEURAL NETWORK BY BRINGING LOTS OF
  NEURONS TOGETHER AND INTERCONNECTING AND
  TRAINING THEM
• SYSTEM PARALLELISM AND STRUCTURAL DISTRIBUTION OF
  OVERALL FUNCTION
• -gtcompensating the errors due to a
  nonfunctional neuron
• GENERALIZATION AND LEARNING ABILITY
• -gtgiving meaningful outputs for also
  the non-trained inputs

7
PREDICTING THE ARRIVAL OFIP SHOCKS BY NEURAL
NETWORKS

• IP Shocks causes the incoming particle flux
  observed at or near Earth to increase by orders
  of magnitude.
• Sharp increases in particle intensity are called
  Energetic Storm Particle (ESP) events

8
PREDICTING THE ARRIVAL OFIP SHOCKS BY NEURAL
NETWORKS

• INPUTS Observations from two ACE instruments
• The Electron, Proton, and Alpha Monitor (EPAM)
  particle intensity at five different energy
  levels. This data is used to detect the onset of
  an event, several days in advance, and to predict
  the ESP event / IP shock arrival.

9
PREDICTING THE ARRIVAL OFIP SHOCKS BY NEURAL
NETWORKS

• INPUTS
• The Solar Wind Electron, Proton, and Alpha
  Monitor (SWEPAM) solar wind plasma temperature,
  density, and speed. This data is used to detect
  the actual IP shock arrival.

10
PREDICTING THE ARRIVAL OFIP SHOCKS BY NEURAL
NETWORKS(Real-time Interplanetary Shock
Prediction (RISP) System )

• TRAINING THE ARTIFICIAL NEURAL NETWORK TO PREDICT
  THE TIME REMAINING UNTIL THE SHOCK ARRIVES
• TRAINED BY 37 OF THE 56 SELECTED SHOCKS
• PERFORMANCE ASSESSED BY FORECASTING ARRIVAL TIME
  COUNTDOWNS FOR 19 SHOCKS NOT USED DURING TRAINING

11
PREDICTING THE ARRIVAL OFIP SHOCKS BY NEURAL
NETWORKS
Particle intensities for test sequence 9.
Predicted time until shock arrival.
12
REFERENCES

• www.physics.usyd.edu.au/cairns/teaching/lecture11
  /node5.htmlinterplanetaryshockshltr
• http//www-spof.gsfc.nasa.gov/Education/wgloss.htm
  l
• http//sd-www.jhuapl.edu/ACE/EPAM/RISP/
• Vandegriff , J., Wagstaff, K., Ho , G., Plauger,
  J. Forecasting space weather Predicting
  interplanetary shocks using neural networks.
  Adv.Space Res. 36, 2323-2327, 2005.
• www.srl.caltech.edu/ACE/
• Efe, M.Ö., Kaynak, O., Yapay sinir aglari ve
  uygulamalari, Bogazici University,2005