In the present paper we apply a recently developed pattern recognition algorithm SPs to the problem of automated detection of artificial disturbances in one-second magnetic observatory data. The SPs algorithm relies on the theory of discrete mathematical analysis, which has been developed by some of the authors for more than 10 years. It continues the authors' research in the morphological analysis of time series using fuzzy logic techniques. We show that, after a learning phase, this algorithm is able to recognize artificial spikes uniformly with low probabilities of target miss and false alarm. In particular, a 94% spike recognition rate and a 6% false alarm rate were achieved as a result of the algorithm application to raw one-second data acquired at the Easter Island magnetic observatory. This capability is critical and opens the possibility to use the SPs algorithm in an operational environment.
The continuous growth of geophysical observations requires adequate methods for their processing and analysis. This becomes one of the most important and widely discussed issues in the data science community. The system analysis methods and data mining techniques are able to sustain the solution of this problem. This paper presents an innovative holistic hardware/software system (HSS) developed for efficient management and intellectual analysis of geomagnetic data, registered by Russian geomagnetic observatories and international satellites. Geomagnetic observatories that comprise the International Real-time Magnetic Observatory Network (INTERMAGNET) produce preliminary (raw) and definitive (corrected) geomagnetic data of the highest quality. The designed system automates and accelerates routine production of definitive data from the preliminary magnetograms, obtained by Russian observatories, due to implemented algorithms that involve artificial intelligence elements. The HSS is the first system that provides sophisticated automatic detection and multi-criteria classification of extreme geomagnetic conditions, which may be hazardous for technological infrastructure and economic activity in Russia. It enables the online access to digital geomagnetic data, its processing results and modelling calculations along with their visualization on conventional and spherical screens. The concept of the presented system agrees with the accepted 'four Vs' paradigm of Big Data. The HSS can increase significantly the 'velocity' and 'veracity' features of the INTERMAGNET system. It also provides fusion of large sets of ground-based and satellite geomagnetic data, thus facilitating the 'volume' and 'variety' of handled data.
Preliminary magnetograms contain different types of temporal anthropogenic disturbances: spikes, baseline jumps, drifts, etc. These disturbances should be identified and filtered out during the prepro cessing of the preliminary records for the definitive data. As of now, at the geomagnetic observatories, such filtering is carried out manually. Most of the disturbances in the records sampled every second are spikes, which are much more abundant than those on the magnetograms sampled every minute. Another important feature of the 1 s magnetograms is the presence of a plenty of specific disturbances caused by short period geomagnetic pulsations, which must be retained in the definitive records. Thus, creating an instrument for formalized and unified recognition of spikes on the preliminary 1 s magnetograms would largely solve the problem of labor consuming manual preprocessing of the magnetic records. In the context of this idea, in the present paper, we focus on recognition of the spikes on the 1 s magnetograms as a key point of the problem. We describe here the new algorithm of pattern recognition, SPs, which is capable of automatically identifying the spikes on the 1 s magnetograms with a low probability of missed events and false alarms. The algorithm was verified on the real magnetic data recorded at the French observatory located on Easter Island in the Pacific.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.