Real-time Neural Network predictions of geomagnetic activity indices

Details Real-time Neural Network predictions of geomagnetic activity indices Real-time Neural Network predictions of geomagnetic activity indices

Dec 2009

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2009agufmsm51a1325b&link_type=abstract

American Geophysical Union, Fall Meeting 2009, abstract #SM51A-1325

Physics

[2776] Magnetospheric Physics / Polar Cap Phenomena, [2784] Magnetospheric Physics / Solar Wind/Magnetosphere Interactions, [7924] Space Weather / Forecasting, [7959] Space Weather / Models

Scientific paper

The Boyle potential or the Boyle Index (BI), Φ (kV)=10-4 (V/(km/s))2 + 11.7 (B/nT) sin3(θ/2), is an empirically-derived formula that can characterize the Earth's polar cap potential, which is readily derivable in real time using the solar wind data from ACE (Advanced Composition Explorer). The BI has a simplistic form that utilizes a non-magnetic "viscous" and a magnetic "merging" component to characterize the magnetospheric behavior in response to the solar wind. We have investigated its correlation with two of conventional geomagnetic activity indices in Kp and the AE index. We have shown that the logarithms of both 3-hr and 1-hr averages of the BI correlate well with the subsequent Kp: Kp = 8.93 log10(BI) - 12.55 along with 1-hr BI correlating with the subsequent log10(AE): log10(AE) = 1.78 log10(BI) - 3.6. We have developed a new set of algorithms based on Artificial Neural Networks (ANNs) suitable for short term space weather forecasts with an enhanced lead-time and better accuracy in predicting Kp and AE over some leading models; the algorithms omit the time history of its targets to utilize only the solar wind data. Inputs to our ANN models benefit from the BI and its proven record as a forecasting parameter since its initiation in October, 2003. We have also performed time-sensitivity tests using cross-correlation analysis to demonstrate that our models are as efficient as those that incorporates the time history of the target indices in their inputs. Our algorithms can predict the upcoming full 3-hr Kp, purely from the solar wind data and achieve a linear correlation coefficient of 0.840, which means that it predicts the upcoming Kp value on average to within 1.3 step, which is approximately the resolution of the real-time Kp estimate. Our success in predicting Kp during a recent unexpected event (22 July ’09) is shown in the figure. Also, when predicting an equivalent "one hour Kp'', the correlation coefficient is 0.86, meaning on average a prediction within 0.99 step. Our model is also successful in predicting AE in its original 1-hr cadence format to achieve a linear correlation of 0.83. Our real-time AE prediction model is currently being developed. However, live results of the BI plot and Kp prediction can be obtained from http://space.rice.edu/ISTP/wind.htmlspacalrt system will receive email alerts whenever the value of the predicted Kp reaches 6 or higher, or when the 10-minute BI exceeds 200 kV.

Affiliated with

Also associated with

No associations

Rating

Real-time Neural Network predictions of geomagnetic activity indices does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Real-time Neural Network predictions of geomagnetic activity indices, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Real-time Neural Network predictions of geomagnetic activity indices will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1881015