The automated prediction of solar flares from SDO images using deep learning

In the last few years, there has been growing interest in near-real-time solar data processing, especially for space weather applications. This is due to space weather impacts on both space-borne and ground-based systems, and industries, which subsequently impacts our lives. In the current study, the deep learning approach is used to establish an automated hybrid computer system for a short-term forecast; it is achieved by using the complexity level of the sunspot group on SDO/HMI Intensitygram images. Furthermore, this suggested system can generate the forecast for solar flare occurrences within the following 24 h. The input data for the proposed system are SDO/HMI full-disk Intensitygram images and SDO/HMI full-disk magnetogram images. System outputs are the “Flare or Non-Flare” of daily flare occurrences (C, M, and X classes). This system integrates an image processing system to automatically detect sunspot groups on SDO/HMI Intensitygram images using active-region data extracted from SDO/HMI magnetogram images (presented by Colak and Qahwaji, 2008) and deep learning to generate these forecasts. Our deep learning-based system is designed to analyze sunspot groups on the solar disk to predict whether this sunspot group is capable of releasing a significant flare or not. Our system introduced in this work is called ASAP_Deep. The deep learning model used in our system is based on the integration of the Convolutional Neural Network (CNN) and Softmax classifier to extract special features from the sunspot group images detected from SDO/HMI (Intensitygram and magnetogram) images. Furthermore, a CNN training scheme based on the integration of a back-propagation algorithm and a mini-batch AdaGrad optimization method is suggested for weight updates and to modify learning rates, respectively. The images of the sunspot regions are cropped automatically by the imaging system and processed using deep learning rules to provide near real-time predictions. The major results of this study are as follows. Firstly, the ASAP_Deep system builds on the ASAP system introduced in Colak and Qahwaji (2009) but improves the system with an updated deep learning-based prediction capability. Secondly, we successfully apply CNN to the sunspot group image without any pre-processing or feature extraction. Thirdly, our system results are considerably better, especially for the false alarm ratio (FAR); this reduces the losses resulting from the protection measures applied by companies. Also, the proposed system achieves a relatively high scores for True Skill Statistics (TSS) and Heidke Skill Score (HSS).     

Small spacecraft formation using potential functions

A group of small spacecraft able to change its orbital formation through using the potential function is discussed. Spacecraft shapes, sizes, and maneuvering capabilities in general are not identical. All objects are assumed to maneuver under discrete thruster effects. A hyperbolic form of attractive potential function is then used to reduce the control intervention by using the natural orbital motion for approaching goal configuration. A superquadric repulsive potential with 3D rigid object representation is then used to have more accurate mutual sensing between objects. As spacecraft start away from their goals, the original parabolic attractive potential becomes inefficient as the continuous control force increases with distance linearly. The hyperbolic attractive potential offers good representation of the control force independent of the distance to goal, ensuring global stability as well.     

Satellite-Aided Search and Rescue (SAR) System

To carry out search and rescue of people in distress on the distressed aircrafts/vessels on land, at sea, or in a remote mountainous region, there are a number of different search and rescue systems and methods that are being used by the different national search and rescue organizations worldwide. Herein, the main terrestrial search and rescue (SAR) systems that are in use are discussed in brief and a satellite-aided search and rescue (SAR) system - COSPAS - SARSAT is discussed in detail highlighting its benefits over other SAR systems.     

Optimization of space orbits design for Earth orbiting missions

In Earth orbiting space missions, the orbit selection dictates the mission parameters like the ground resolution, the area coverage, and the frequency of coverage parameters. To achieve desired mission parameters, usually Earth regions of interest are identified and the spacecraft is maneuvered continuously to visit only these regions. This method is expensive, it requires a propulsion system onboard the spacecraft, working throughout the mission lifetime. It also requires a longer time to cover all the regions of interest, due to the very weak thrust forces compared to that of the Earth's gravitational field. This paper presents a methodology to design natural orbits, in which the regions of interest are visited without the use of propulsion systems, depending only on the gravitational forces. The problem is formulated as an optimization problem. A genetic algorithm along with a second order gradient method is implemented for optimization. The design process takes into consideration the gravitational second zonal harmonic, and hence allows for the design of repeated Sun-synchronous orbits. The field of view of the payload is also taken into consideration in the optimization process. Numerical results are presented that demonstrates the efficiency of the proposed method.     

Nonlinear Optimal Feedback Regulation of Satellite Angular Monenta

Some important regulation properties of satellite angular momentum dynamics are investigated using a combination of reaction jets and flywheels. The optimal feedback controller is designed in such a way that system regulation, under large perturbations, to a proper bounded subset in Rn, is achieved by using reaction jets. Thereafter, flywheels are activated to bring the system to the rest (desired) state. The domain and the size over which reaction jets are active, as well as the corresponding fuel cost, are discussed. Further, the effect of linear as well as nonlinear optimal feedback regulators on system behavior is indicated. Finally, the range (in the state space Rn) over which the flywheels are capable of regulating the system is also studied.     

Stability and Control of a Trap Mode in Synchronous Orbit

The possibility of the existence of a trap mode in synchronous orbit is investigated. It is shown that when such a mode exists, certain parameters of the satellite orbit may soon attain undesired equilibrium values, thus complicating the normal stationkeeping operation of the spacecraft. A state-dependent control force which eliminates any such trap mode in the satellite orbit is then investigated.     

On an Intrusion-Detection Approach Via Adaptive Prediction

We introduce the notion of using adaptive (digital) prediction in an intrusion-detection application, where stimuli due to intruders are transient signals. The basic idea is to use an adaptive digital predictor for removing correlated noise. As such, this approach assists in reducing false (nuisance) alarms in the absence of intruder stimuli. It also yields an improvement in signal-to-noise ratio when intruder stimuli are present, thereby assisting in their detection. The performance of this approach is assessed in terms of a fixed-point arithmetic simulation. Some aspects of a corresponding hardware implementation that involves a commercial microprocessor are also included.     

Experimental study in adaptive tracking control

The authors describe an experimental study of adaptive pointing and tracking control for flexible spacecraft conducted on a complex ground experiment facility. The algorithm used is based on a multivariable direct model reference adaptive control law. Several experimental validation studies performed using this algorithm for vibration damping and robust regulation are extended by addressing the pointing and tracking problem. As is consistent with an adaptive control framework, the plant is assumed to be poorly known to the extent that only system level knowledge of its dynamics is available. Explicit bounds on the steady-state pointing error are derived as functions of the adaptive controller design parameters. It is shown that good tracking performance can be achieved in an experimental setting by adjusting adaptive controller design weightings according to the guidelines indicated by the analytical expressions for the error     

Study the behavior of the ionospheric frequencies at Karachi during three consecutive solar minima of cycle 21, 22 & 23 and their comparison with IRI-2016

The behavior of critical frequencies of ionospheric E and F2 layers (foE & foF2) along with minimum ionospheric frequency (fmin) is studied for solar minima of cycle 21 (1986), 22 (1996) and 23 (2008) over Karachi (24.95$°$N, 67.13$°$E), Pakistan. The station is located at the crest of equatorial ionization anomaly region. Beside seasonal differences, pronounced change in the values of frequencies is noted from one solar minimum to another solar minimum. A strong and direct correlation of foF2 with Smoothed Sunspot Number (SSN) and F10.7?cm solar flux is observed. In the minimum of cycle 23, reduction in foF2 is noted due to reduction of solar EUV as compared to other minima. Also disappearance of semi-annual variations in foF2 is noted in cycle 23 minimum. Unexpectedly higher values of foE and fmin are observed in minimum of cycle 23 as compared to other minima. It is difficult to explain this unusual behavior of fmin and foE along with disappearance of semi-annual variation in foF2. It is possible that during very low solar activity, thermospheric conditions are changed which in turn altered the ionosphere. Further investigation of atmosphere-ionosphere coupling is required to understand this complex behavior. On comparison of observed values with IRI-2016, higher deviations are observed in foE before noon hours while in case of foF2, large deviations are noted during daytime. The absence of foF2 semi-annual variation in cycle 23 is not reproduced by IRI-2016. It is suggested that IRI-2016 need some modification for extremely low solar activity condition.