Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 2000
ABSTRACT The ionosphere shows a large degree of variability on time scales from hours to the sola... more ABSTRACT The ionosphere shows a large degree of variability on time scales from hours to the solar cycle length. This variation is associated with magnetospheric storms, the Earth's rotation, the season, and the level of solar activity. To make accurate predictions of key ionospheric parameters all these variations must be considered. Neural networks, which are data driven non-linear models, are very useful for such tasks. In this work we examine if the F2 layer plasma frequency, foF2, at a single ionospheric station can be predicted 1 to 24 hours in advance by using information of past foF2 observations, magnetospheric activity, and time as inputs to neural networks. Particular attention has been paid to periods when great geomagnetic storms were in progress with the aim to develop a successful ionospheric storm forecasting tool.
Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 2000
Multilayer feed-forward neural network models are developed to make three-hour predictions of the... more Multilayer feed-forward neural network models are developed to make three-hour predictions of the planetary magnetospheric ÃÔ index. The input parameters for the networks are the Þ -component of the interplanetary magnetic field, the solar wind density Ò, and the solar wind velocity Î , given as three-hour averages. The networks are trained with the error back-propagation algorithm on data sequences extracted from the 21 ×Ø solar cycle. The result is a hybrid model consisting of two expert networks providing ÃÔ predictions with an RMS error of 0.96 and a correlation of 0.76 in reference to the measured ÃÔ values. This result can be compared with the linear correlation between δص and ÃÔ´Ø · ¿ hoursµ which is 0.47. The hybrid model is tested on geomagnetic storm events extracted from the 22 Ò solar cycle. The hybrid model is implemented and real time predictions of the planetary magnetospheric ÃÔ index are available at http://www.astro.lu.se/ fredrikb.
A new approach of exploring and forecasting solar activity was recently introduced. The Lund Sola... more A new approach of exploring and forecasting solar activity was recently introduced. The Lund Solar Activity Model (LSAM) uses as input solar activity indicators: For exploration of the long-term space climate C14 proxy. For short-term (space weather) flare forecasts solar magnetic field and helioseismic data. The Lund Group also operates the Region Warning Center (RWC) Sweden of ISES. Real-time forecasts of the space weather and effects are offered. New real-time forecasts of the local geomagnetic activity have been developed, as part of the ESA GIC pilot project. A third workshop on Artificial Intelligence Applications in Solar-Terrestrial Physics is planned to be held in Lund, September 21-23, 2005.
Predictions of the daily solar wind velocity (V) at 1 AU from the flux tube expansion factor fs a... more Predictions of the daily solar wind velocity (V) at 1 AU from the flux tube expansion factor fs are examined with radial basis function neural networks. The flux tube expansion factor is calculated from the potential field model, using Wilcox Solar Observatory magnetograms, with the source surface placed at 2.5 solar radii. The time series extend over 20 years from
The Satellite Anomaly Analysis and Prediction System (SAAPS) is a software containing a database ... more The Satellite Anomaly Analysis and Prediction System (SAAPS) is a software containing a database of space weather data and satellite anomaly data, tools for plotting and analysis, and models for the prediction of anomalies. The system uses real-time data and can run stand-alone ...
Abstract: In order to determine the influence of mankind on climate change it is important to und... more Abstract: In order to determine the influence of mankind on climate change it is important to understand the natural causes of climate variability. A natural effect that has been hard to understand physically is an apparent link between climate and solar activity. From historical and geological ...
Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 2000
ABSTRACT The ionosphere shows a large degree of variability on time scales from hours to the sola... more ABSTRACT The ionosphere shows a large degree of variability on time scales from hours to the solar cycle length. This variation is associated with magnetospheric storms, the Earth's rotation, the season, and the level of solar activity. To make accurate predictions of key ionospheric parameters all these variations must be considered. Neural networks, which are data driven non-linear models, are very useful for such tasks. In this work we examine if the F2 layer plasma frequency, foF2, at a single ionospheric station can be predicted 1 to 24 hours in advance by using information of past foF2 observations, magnetospheric activity, and time as inputs to neural networks. Particular attention has been paid to periods when great geomagnetic storms were in progress with the aim to develop a successful ionospheric storm forecasting tool.
Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 2000
Multilayer feed-forward neural network models are developed to make three-hour predictions of the... more Multilayer feed-forward neural network models are developed to make three-hour predictions of the planetary magnetospheric ÃÔ index. The input parameters for the networks are the Þ -component of the interplanetary magnetic field, the solar wind density Ò, and the solar wind velocity Î , given as three-hour averages. The networks are trained with the error back-propagation algorithm on data sequences extracted from the 21 ×Ø solar cycle. The result is a hybrid model consisting of two expert networks providing ÃÔ predictions with an RMS error of 0.96 and a correlation of 0.76 in reference to the measured ÃÔ values. This result can be compared with the linear correlation between δص and ÃÔ´Ø · ¿ hoursµ which is 0.47. The hybrid model is tested on geomagnetic storm events extracted from the 22 Ò solar cycle. The hybrid model is implemented and real time predictions of the planetary magnetospheric ÃÔ index are available at http://www.astro.lu.se/ fredrikb.
A new approach of exploring and forecasting solar activity was recently introduced. The Lund Sola... more A new approach of exploring and forecasting solar activity was recently introduced. The Lund Solar Activity Model (LSAM) uses as input solar activity indicators: For exploration of the long-term space climate C14 proxy. For short-term (space weather) flare forecasts solar magnetic field and helioseismic data. The Lund Group also operates the Region Warning Center (RWC) Sweden of ISES. Real-time forecasts of the space weather and effects are offered. New real-time forecasts of the local geomagnetic activity have been developed, as part of the ESA GIC pilot project. A third workshop on Artificial Intelligence Applications in Solar-Terrestrial Physics is planned to be held in Lund, September 21-23, 2005.
Predictions of the daily solar wind velocity (V) at 1 AU from the flux tube expansion factor fs a... more Predictions of the daily solar wind velocity (V) at 1 AU from the flux tube expansion factor fs are examined with radial basis function neural networks. The flux tube expansion factor is calculated from the potential field model, using Wilcox Solar Observatory magnetograms, with the source surface placed at 2.5 solar radii. The time series extend over 20 years from
The Satellite Anomaly Analysis and Prediction System (SAAPS) is a software containing a database ... more The Satellite Anomaly Analysis and Prediction System (SAAPS) is a software containing a database of space weather data and satellite anomaly data, tools for plotting and analysis, and models for the prediction of anomalies. The system uses real-time data and can run stand-alone ...
Abstract: In order to determine the influence of mankind on climate change it is important to und... more Abstract: In order to determine the influence of mankind on climate change it is important to understand the natural causes of climate variability. A natural effect that has been hard to understand physically is an apparent link between climate and solar activity. From historical and geological ...
Uploads
Papers by Peter Wintoft