A SVM integrated Case Based Learning Data GA for Solar Flare Prediction

Unusual intense solar flare can have serious impact on the human society. In particular, it may cause serious problems such as damaging electric power plants. It is desirable but difficult to predict intense solar flare because of imbalanced classification problems. To overcome this, we developed Case Based Genetic Algorithm (GA) integrated with Local Optimizer (CBGALO). Here, a Support Vector Machine (SVM) is used as Local Optimizer. However, the prediction precision for learning significantly depends on input data. Therefore, CBGALO was elaborated to extend by a Case Based GA that is able to automatically restart. This forms a good combination searching GA for both learning features and input data (CBRsGcmbGA). Even the currently popular deep learning cannot search the input data for learning automatically or at least evolutionarily. The effect of our approach is proven in predicting X class solar flare as follows: 1) extended CBGALO reached more than 85% of precision in most (12 out of 14) cases and 91.2% at maximum, 2) previous CBGALO reached 84% at most 3) other approaches in the same environment reached less than 75%.

[1]  M. Den,et al.  Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms , 2016, 1611.01791.

[2]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[3]  Xiao-hua Liu,et al.  Combining Genetic Algorithm and Case-based Reasoning for Structure Design , 1996 .

[4]  Yoshizumi Miyoshi,et al.  Probabilistic space weather forecast of the relativistic electron flux enhancement at geosynchronous orbit , 2008 .

[5]  Haimin Wang,et al.  Statistical Assessment of Photospheric Magnetic Features in Imminent Solar Flare Predictions , 2009 .

[6]  K. Shibata,et al.  Solar Flares: Magnetohydrodynamic Processes , 2011 .

[7]  R. Schwenn.  Space Weather: The Solar Perspective , 2006 .

[8]  K. D. Leka,et al.  PHOTOSPHERIC MAGNETIC FIELD PROPERTIES OF FLARING VERSUS FLARE-QUIET ACTIVE REGIONS. III. MAGNETIC CHARGE TOPOLOGY MODELS , 2006 .

[9]  M. S. Wheatland.  A statistical solar flare forecast method , 2005 .

[10]  Carlos A. Coello Coello,et al.  Genetic Algorithms and Case-Based Reasoning as a Discovery and Learning Machine in the Optimization of Combinational Logic Circuits , 2002, MICAI.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[13]  Daren Yu,et al.  Short-Term Solar Flare Prediction Using a Sequential Supervised Learning Method , 2009 .

[14]  G. Barnes,et al.  Photospheric Magnetic Field Properties of Flaring versus Flare-quiet Active Regions. II. Discriminant Analysis , 2003 .

[15]  Monica G. Bobra,et al.  SOLAR FLARE PREDICTION USING SDO/HMI VECTOR MAGNETIC FIELD DATA WITH A MACHINE-LEARNING ALGORITHM , 2014, 1411.1405.

[16]  Ernesto Damiani,et al.  Extending the SVM integration with case based restarting GA to predict solar flare , 2017, 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[17]  T. Okamoto,et al.  STUDY ON THE TRIGGERING PROCESS OF SOLAR FLARES BASED ON HINODE/SOT OBSERVATIONS , 2013, 1309.5465.

[18]  Takayuki Muranushi,et al.  UFCORIN: A fully automated predictor of solar flares in GOES X‐ray flux , 2015, 1507.08011.

[19]  Eyke Hüllermeier,et al.  Case-Based Approximate Reasoning , 2007, Theory and Decision Library.

[20]  Rushi Longadge,et al.  Class Imbalance Problem in Data Mining Review , 2013, ArXiv.

[21]  Rami Qahwaji,et al.  Solar Flare Prediction Using Advanced Feature Extraction, Machine Learning, and Feature Selection , 2011, Solar Physics.

[22]  J. P. Mason,et al.  TESTING AUTOMATED SOLAR FLARE FORECASTING WITH 13 YEARS OF MICHELSON DOPPLER IMAGER MAGNETOGRAMS , 2010 .

[23]  Rongzhi Li,et al.  Support Vector Machine combined with K-Nearest Neighbors for Solar Flare Forecasting , 2007 .

[24]  KimSangyong,et al.  Combining case-based reasoning with genetic algorithm optimization for preliminary cost estimation in construction industry , 2014 .

[25]  B. Heber,et al.  Space Weather. The Physics Behind a Slogan , 2004 .

[26]  K. D. Leka,et al.  Photospheric Magnetic Field Properties of Flaring versus Flare-quiet Active Regions. I. Data, General Approach, and Sample Results , 2003 .

[27]  Yoshitaka Sakurai,et al.  Case based human oriented delivery route optimization , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[28]  D. S. Bloomfield,et al.  TOWARD RELIABLE BENCHMARKING OF SOLAR FLARE FORECASTING METHODS , 2012, 1202.5995.

[29]  Haimin Wang,et al.  Automated flare forecasting using a statistical learning technique , 2010 .

[30]  Rami Qahwaji,et al.  Automated Solar Activity Prediction: A hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares , 2009 .

[31]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[32]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[33]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..