• The Journal of Engineering Geology
• /
• v.5 no.3
• /
• pp.309-329
• /
• 1995

Seismicity and stress state in the Korean peninsula are studied using the catalogue of historical earthquakes and that from the seismological observations before the 1960s, with the aid of instrumental catalogue up to 1995. It seems that the completeness of the historical catalogue has a significant enhancement during the first two hundred years of the Yi dynasty, i.e., from the 1400s to the 1600s. From then on the catalogue may be regarded as near to complete for strong earthquakes in an overall sense. From the distribution of strong earthquakes, three seismic zones may be identified. From the south to the north, those are the southern seismic zone (남부지진대), the Seoul-Pyongyang seismic zone (서울-평양지진대), and the northern seismic zone (북부지진대). The mechanisms of some earthquakes obtained using first motion read- ings are reevaluated with a grid testing method. The results indicate that the compressional axis is nearly horizontal along the EW direction.

• The Journal of Engineering Geology
• /
• v.32 no.3
• /
• pp.377-388
• /
• 2022

Recently, several studies have utilized machine learning to efficiently and accurately analyze seismic data that are exponentially increasing. In this study, we expand earthquake information such as occurrence time, hypocentral location, and magnitude to produce a dataset for applying to machine learning, reducing the dimension of the expended data into dominant features through principal component analysis. The dimensional extended data comprises statistics of the earthquake information from the Global Centroid Moment Tensor catalog containing 36,699 seismic events. We perform data preprocessing using standard and max-min scaling and extract dominant features with principal components analysis from the scaled dataset. The scaling methods significantly reduced the deviation of feature values caused by different units. Among them, the standard scaling method transforms the median of each feature with a smaller deviation than other scaling methods. The six principal components extracted from the non-scaled dataset explain 99% of the original data. The sixteen principal components from the datasets, which are applied with standardization or max-min scaling, reconstruct 98% of the original datasets. These results indicate that more principal components are needed to preserve original data information with even distributed feature values. We propose a data processing method for efficient and accurate machine learning model to analyze the relationship between seismic data and seismic behavior.