RISS 검색 - 국내학술지논문 상세보기

다국어 초록 (Multilingual Abstract)

Stress interaction among many faults in earthquake prone region is strongly affected by the spatial distribution of faults. To build a robust Machine Learning (ML) algorithm for finding hidden relationships between fault distribution and its controlling factors, the performance of ML in dependence of various parameters, such as the complexity and data size of the fault distribution, needs to be investigated. We have, therefore, developed an ML algorithm by combining Principal Component Analysis (PCA) with a Random Forest (RF) to unveil the controlling factors on seismic fault distribution. We synthesized fault images for training of RF classifier ND (> 10,000) fault images, which scattered the faults in a square with R km R km. R, ranging from 200 km to 600 km, is a controlling factor of fault distribution. PCA extracts the dominant features of the seismic fault images to supply the refined training data to the RF. This leads to a dimensional reduction of the data. We tested the influence of the number of principal components (NP) on PCA performance in retaining the information. Larger and more variable R values (i.e., a more complicated fault distribution) with larger amounts of training data required more principal components for a full preservation of the original data. We quantified the optimized NP/ND ratio for an efficient RF classifier, which was about ~0.1 for the evaluating efficacy of the PCA. This showed that the RF classifiers is effective in predicting R values depending on the fault zone with R km × R km and not on specific fault locations. We propose that a small NP, equivalent to ~10% of the training data, suffices for training accurately RF classifier for fault distributions, which can reduce the complexity of fault distribution to understand stress interaction among many faults.

번역하기

참고문헌 (Reference)

1 Smith, L.I., "bA tutorial on Principal Components Analysis" University of Otago 26-, 2002

2 Raileanu, L. E., "Theoretical comparison between the Gini index and information gain criteria" 41 : 77-93, 2004

3 Stein, R. S., "The role of stress transfer in earthquake occurrence" 402 : 605-609, 1999

4 So, B. D., "The emergence of seismic cycles from stress feedback between intra-plate faulting and far-field tectonic loading" 447 : 112-118, 2016

5 So, B. D., "The effect of plate-scale rheology and plate interactions on intraplate seismicity" 478 : 121-131, 2017

6 Wang, H., "Strain partitioning and stress perturbation around stepovers and bends of strike-slip faults:numerical results" 721 : 211-226, 2017

7 Karimzadeh, S., "Spatiotemporal deformation patterns of the Lake Urmia Causeway as characterized by multisensor InSAR analysis" 8 : 1-10, 2018

8 Li, Q., "Spatiotemporal complexity of continental intraplate seismicity: insights from geodynamic modeling and implications for seismic hazard estimation" 99 : 52-60, 2009

9 Aktar, M., "Spatial variation of aftershock activity across the rupture zone of the 17August 1999 Izmit earthquake, Turkey" 391 : 325-334, 2004

10 Lafuente, P., "Spatial and temporal variation of palaeoseismic activity at an intraplate, historically quiescent structure: the Concud fault (Iberian Chain, Spain)" 632 : 167-187, 2014