Space weather has become an international issue due to the catastrophic impactit can have on modern societies. Solar flares are one of the major solar activities thatdrive space weather and yet their occurrence is not fully understood. Research isrequired to yield a better understanding of flare occurrence and enable the developmentof an accurate flare prediction system, which can warn industries most at risk to takepreventative measures to mitigate or avoid the effects of space weather. This thesisintroduces novel technologies developed by combining advances in statistical physics, image processing, machine learning, and feature selection algorithms, with advances insolar physics in order to extract valuable knowledge from historical solar data, related toactive regions and flares. The aim of this thesis is to achieve the followings: i) Thedesign of a new measurement, inspired by the physical Ising model, to estimate themagnetic complexity in active regions using solar images and an investigation of thismeasurement in relation to flare occurrence. The proposed name of the measurement isthe Ising Magnetic Complexity (IMC). ii) Determination of the flare predictioncapability of active region properties generated by the new active region detectionsystem SMART (Solar Monitor Active Region Tracking) to enable the design of a newflare prediction system. iii) Determination of the active region properties that are mostrelated to flare occurrence in order to enhance understanding of the underlying physicsbehind flare occurrence. The achieved results can be summarised as follows: i) The newactive region measurement (IMC) appears to be related to flare occurrence and it has apotential use in predicting flare occurrence and location. ii) Combining machinelearning with SMART's active region properties has the potential to provide moreaccurate flare predictions than the current flare prediction systems i.e. ASAP(Automated Solar Activity Prediction). iii) Reduced set of 6 active region propertiesseems to be the most significant properties related to flare occurrence and they canachieve similar degree of flare prediction accuracy as the full 21 SMART active regionproperties. The developed technologies and the findings achieved in this thesis willwork as a corner stone to enhance the accuracy of flare prediction; develop efficientflare prediction systems; and enhance our understanding of flare occurrence. Thealgorithms, implementation, results, and future work are explained in this thesis.

Space weather has become an international issue due to the catastrophic impact it can have on modern societies. Solar flares are one of the major solar activities that drive space weather. Thus, research is required to yield a better understanding of flare occurrence and enable an accurate flare forecasting. This work introduces novel technologies developed by combining advances in statistical physics, image processing, machine learning, and feature selection algorithms, with advances in solar physics in order to extract valuable knowledge from historical solar data, related to active regions and flares. The aim of this work is to achieve the followings: 1) The design of a new measurement, inspired by the physical Ising model, to estimate the magnetic complexity in active regions and an investigation of this measurement in relation to flares. 2) Determination of the flare prediction capability of active region properties generated by the new active region detection system SMART to enable the design of a new flare prediction system. 3) Determination of the active region properties that are most related to flare occurrence in order to enhance understanding flare occurrence.

Solar flares release stored magnetic energy in the form of radiation and can have significant detrimental effects on earth including damage to technological infrastructure. Recent work has considered methods to predict future flare activity on the basis of quantitative measures of the solar magnetic field. Accurate advanced warning of solar flare occurrence is an area of increasing concern and much research is ongoing in this area. Our previous work [11] utilized standard pattern recognition and classification techniques to determine (classify) whether a region is expected to flare within a predictive time window, using a Relevance Vector Machine (RVM) classification method. We extracted 38 features which describing the complexity of the photospheric magnetic field, the result classification metrics will provide the baseline against which we compare our new work. We find true positive rate (TPR) of 0.8, true negative rate (TNR) of 0.7, and true skill score (TSS) of 0.49. This dissertation proposes three basic topics; the first topic is an extension to our previous work [11], where we consider a feature selection method to determine an appropriate feature subset with cross validation classification based on a histogram analysis of selected features. Classification using the top five features resulting from this analysis yield better classification accuracies across a large unbalanced dataset. In particular, the feature subsets provide better discrimination of the many regions that flare where we find a TPR of 0.85, a TNR of 0.65 sightly lower than our previous work, and a TSS of 0.5 which has an improvement comparing with our previous work. In the second topic, we study the prediction of solar flare size and time-to-flare using support vector regression (SVR). When we consider flaring regions only, we find an average error in estimating flare size of approximately half a GOES class. When we additionally consider non-flaring regions, we find an increased average error of approximately 3/4 a GOES class. We also consider thresholding the regressed flare size for the experiment containing both flaring and non-flaring regions and find a TPR of 0.69 and a TNR of 0.86 for flare prediction, consistent with our previous studies of flare prediction using the same magnetic complexity features. The results for both of these size regression experiments are consistent across a wide range of predictive time windows, indicating that the magnetic complexity features may be persistent in appearance long before flare activity. This conjecture is supported by our larger error rates of some 40 hours in the time-to-flare regression problem. The magnetic complexity features considered here appear to have discriminative potential for flare size, but their persistence in time makes them less discriminative for the time-to-flare problem. We also study the prediction of solar flare size and time-to-flare using two temporal features, namely the [delta]- and [delta-delta-]features, the same average size and time-to-flare regression error are found when these temporal features are used in size and time-to-flare prediction. In the third topic, we study the temporal evolution of active region magnetic fields using Hidden Markov Models (HMMs) which is one of the efficient temporal analyses found in literature. We extracted 38 features which describing the complexity of the photospheric magnetic field. These features are converted into a sequence of symbols using k-nearest neighbor search method. We study many parameters before prediction; like the length of the training window W[subscript train] which denotes to the number of history images use to train the flare and non-flare HMMs, and number of hidden states Q. In training phase, the model parameters of the HMM of each category are optimized so as to best describe the training symbol sequences. In testing phase, we use the best flare and non-flare models to predict/classify active regions as a flaring or non-flaring region using a sliding window method. The best prediction result is found where the length of the history training images are 15 images (i.e., W[subscript train]= 15) and the length of the sliding testing window is less than or equal to W[subscript train], the best result give a TPR of 0.79 consistent with previous flare prediction work, TNR of 0.87 and TSS of 0.66, where both are higher than our previous flare prediction work. We find that the best number of hidden states which can describe the temporal evolution of the solar ARs is equal to five states, at the same time, a close resultant metrics are found using different number of states.

Solar flare prediction is a valuable and sought after commodity for the safety of astronauts and satellites. Our work takes an image processing approach to solving this problem using Improved Solar Observing Optical Network (ISOON) images to produce a robust flare prediction algorithm. Our algorithm operates on images of the chromosphere which is associated with the H[alpha] wavelength. We detect solar structures of importance to flare prediction namely filaments and active regions, then extract their features. Using these features, we use a classification method known as anomaly detection which is not affected by an imbalanced dataset. Our results are highly successful when filament features are paired with features of active regions. We speculate the combination of active regions and filament features produce a catalyst to successfully predict solar flares. We also have data indicating that feature selection within anomaly detection may produce higher accuracies.

Extreme Events in Geospace: Origins, Predictability, and Consequences helps deepen the understanding, description, and forecasting of the complex and inter-related phenomena of extreme space weather events. Composed of chapters written by representatives from many different institutions and fields of space research, the book offers discussions ranging from definitions and historical knowledge to operational issues and methods of analysis. Given that extremes in ionizing radiation, ionospheric irregularities, and geomagnetically induced currents may have the potential to disrupt our technologies or pose danger to human health, it is increasingly important to synthesize the information available on not only those consequences but also the origins and predictability of such events. Extreme Events in Geospace: Origins, Predictability, and Consequences is a valuable source for providing the latest research for geophysicists and space weather scientists, as well as industries impacted by space weather events, including GNSS satellites and radio communication, power grids, aviation, and human spaceflight. The list of first/second authors includes M. Hapgood, N. Gopalswamy, K.D. Leka, G. Barnes, Yu. Yermolaev, P. Riley, S. Sharma, G. Lakhina, B. Tsurutani, C. Ngwira, A. Pulkkinen, J. Love, P. Bedrosian, N. Buzulukova, M. Sitnov, W. Denig, M. Panasyuk, R. Hajra, D. Ferguson, S. Lai, L. Narici, K. Tobiska, G. Gapirov, A. Mannucci, T. Fuller-Rowell, X. Yue, G. Crowley, R. Redmon, V. Airapetian, D. Boteler, M. MacAlester, S. Worman, D. Neudegg, and M. Ishii. Helps to define extremes in space weather and describes existing methods of analysis Discusses current scientific understanding of these events and outlines future challenges Considers the ways in which space weather may affect daily life Demonstrates deep connections between astrophysics, heliophysics, and space weather applications, including a discussion of extreme space weather events from the past Examines national and space policy issues concerning space weather in Australia, Canada, Japan, the United Kingdom, and the United States