Asperities’ location is a very important factor in spatiotemporal analysis of an area’s seismicity, as they can accumulate a large amount of tectonic stress and, by their rupture, a great magnitude earthquake. Seismic attributes of earthquakes, such as the b-value and seismic density, have been shown to be useful indicators of asperities’ location. In this work, machine learning techniques are used to identify the location of areas with high probability of asperity existence using as feature vector information extracted solely by earthquake catalogs (b-value and seismic density), avoiding thus any geo-location information. Extensive experimentation on algorithms’ performance is conducted with a plethora of machine learning classification algorithms, focusing on the effect of data oversampling and undersampling, as well as the effect of cost sensitive classification without any resampling of the data. The results obtained are promising with performance being comparable to geo-location information including vectors.

The introduction of stochastic earthquake recurrence times in feature vector is attempted for the identification of asperities in the area of Hokkaido, Japan, using machine learning algorithms. Seismicity attributes, feature selection algorithms, and class balancing techniques were used. The stochastic attributes of earthquake density in space, b-value, and the earthquake recurrence intervals were set as asperity identifiers. The study area was divided into 422 subareas, and in each one of them the aforementioned attributes were estimated for each subarea. For increasing the method efficiency a feature selection algorithm was utilized to indicate which of the selected attributes have the potential to contribute to the identification of asperities. A feature vector is presented, combining the attributes mentioned above, and well-known machine learning algorithms were used to identify the asperities locations. The performance of the method was tested with the 10-fold cross-validation technique and was found sufficient in means of F 1 score.

In the Gutenberg-Richter relation that describes the frequency-magnitude distribution of earthquakes, the b value represents the distribution's slope. Since b values can be used for mapping the dynamic response of earthquake source, methodologies for calculating robust b values are of great importance. Although nowadays software which is meant for statistical analysis of earthquake data can determine b values with high accuracy, in occasions where catalogs that contain small number of earthquake events, the produced results are not satisfactory. In this paper we present a new self-optimized algorithm for a more efficient calculation of the b value. The algorithm's results are compared with two widely known software for statistical analysis of earthquake data, showing a better performance in evaluating b values for earthquake catalogs containing small number of events.

In this study it is proposed that spatially detecting low b values in certain segment faults in conjunction to the spatial earthquake density of the corresponding areas, can be used in order to locate faults asperities. This hypothesis is tested in the area of Corinth Gulf where we have processed data from the earthquake catalog of the Aristotle University of Thessaloniki, during a significant period of 45 years, from 1970 until 2015. From the calculations of b values and earthquake density in certain regions asperity patterns have been observed: asperity located by small b values and low densities coincide with proposition of possible asperity found in literature. Based on these facts we reproduce the hypothesis of an Asperity in the south area of Corinth Gulf between the Helike and Xilokastro faults.