Autom ated Prediction of Solar Flares Using Neural Netw orks and - PowerPoint PPT Presentation

Autom ated Prediction of Solar Flares Using Neural Netw orks and Sunspots Associations Tufan Colak t.colak@bradford.ac.uk & Rami Qahwaji r.s.r.qahwaji@bradford.ac.uk EIMC, University of Bradford BD71DP, U.K. WSC11 -(Sep 25-Oct 6 2006) http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Objective: � We aim to design an automated system that could provide short-term prediction of solar flares by establishing a correlation between sunspots and solar flares using machine learning. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Related Work � Despite the recent advances in solar imaging, machine learning has not been widely applied to solar data, except for verification purposes. � Solar activity (i.e., Wolf Number) was predicted first by (Calvo et al. 1995). � (Borda et al. 2002) described a method for the automatic detection of solar flares using BP MLP. � MLP, SVM and RBF were used for flares detection in (Qu et al. 2003). http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Data? � Data from the publicly available National Geophysical Data Centre (NGDC) sunspot groups and flares catalogues are used in our study. � NGDC keeps record of data from several observatories around the world and holds one of the most comprehensive publicly available databases for solar features and activities. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 The NGDC sunspots catalogue � The NGDC sunspot catalogue holds records of sunspot groups supplying their date, time, location, physical properties, sunspot area and classification data. � Two classification systems exist for sunspots: McIntosh, which depends on the size, shape and spot density of sunspots, and Mt. Wilson., which is based on the distribution of magnetic polarities within spot groups. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 The NGDC Flares catalogue � This catalogue provides information about dates, starting and ending times for flare eruptions, location, NOAA number of the corresponding active region and x-ray classification for the detected flares. � Not all the flares have associated NOAA numbers. Flares without NOAA numbers are not included in our study. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Data http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association and prediction model � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Associating Flares and Sunspots � We’ve investigated all the sunspot groups that were associated with flares from 01 Jan1992 till 31 Dec 2005. � The degree of association was determined based on the NOAA region number and the timing information. � A C++ platform that extracts online flares and sunspots info from NGDC catalogues was created. � Our software has analysed the data related to 29343 flares and 110241 sunspots and has managed to associate 1425 M and X flares with their corresponding sunspot groups. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Associating Flares and Sunspots http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 The Theoretical Model http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Cascade FFBP � In cascade FFBP, the first layer has connecting weights with the input layer. Each subsequent layer has weights connecting it to the input layer and all previous layers. . http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Optimising the Learning Algorithms � A learning algorithm provides best generalisation if it is optimised. � A NN is optimised if the optimum topology, learning algorithm and learning times are found. � After finding that CCNN provides best performance, the number of hidden nodes was found empirically. � We have started with 1 hidden node and continuously were increasing the number of hidden nodes until 35 hidden nodes were reached. � Every time a new number of hidden nodes were used, the error rate and the recognition rate were recorded. After carrying out all the empirical experiments it was found that optimum performance was reached with 9 hidden nodes. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 � Both NGDC catalogues were used and our software has analysed the data related to 29343 flares and 110241 sunspots and has managed to associate 1425 M and X flares with their corresponding sunspot groups. � The total number of samples used for our training set is 2882, where 1425 samples represent sunspots that produced flares. � The remaining samples represent sunspots that existed in non-flaring days and are not related to any sunspot groups within the previous flaring sunspot samples. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 The Training and Testing Sets � The NN training and testing was carried out based on the stati stical Jack-knife technique (Fukunaga 1990). � For all the experiments, 80% of the samples are randomly selected and used for training while the remaining 20% are used for testing. These experiments are repeated for number of times and the average is taken. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Initial Experiments � For each sample, the training vector consists of 5 elements ( 3 for inputs; 2 for outputs). http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Initial Experiments � Several experiments based on the Jack-knife technique were carried out and we found that the prediction rate for flares in the best case scenario was 72.9%. � This indicated that a correlation existed between the input and output sets. But this value is not high enough to provide reliable prediction of solar activities. � To improve the learning performance we tried to associate the classified sunspots with the sunspot cycle. http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 � This seemed logical because the rise and fall of solar activity coincides with the sunspot cycle (Pap et al. 1990). � When the solar cycle is at a maximum, plenty of large active regions exist and many solar flares are detected. These decreases in number as the Sun approaches the minimum part of its cycle (Pap et al. 1990). http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Solar Cycle and Flares Science @ NASA,"Solar Minimum Explodes", 9.15.2005 http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Solar Cycle Modelling-Hathaway’s Model Average Monthly Sunspot Number 140 120 100 Number of Sunspots 80 60 40 Generated Real 20 0 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 Years a represents the amplitude and is related to the rise of the cycle minimum, b is related to the time in months from minimum to maximum; c gives the asymmetry of the cycle; and t o denotes the starting time http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 � For each sample, the training vector consists of 6 elements ( 4 for inputs; 2 for outputs). http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 � Hence, for Fkc sunspot at solar maximum that produced an M flare, the training vector looks like this: http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 http: / / spaceweather.inf.brad.ac.uk/

WSC11 -(Sep 25-Oct 6) SIPWORKIII 08/09/06 Organisation of this talk � Objectives & related work � Solar data (features and activities) � Data Association � Machine learning algorithms � Practical results � Conclusions and future work http: / / spaceweather.inf.brad.ac.uk/