Determination of reservoir induced earthquake using support vector machine and gaussian process regression

The prediction of magnitude （M） of reservoir induced earthquake is an important task in earthquake engineering. In this article, we employ a Support Vector Machine （SVM） and Gaussian Process Regression （GPR） for prediction of reservoir induced earthquake M based on reservoir parameters. Comprehensive parameter （E） and maximum reservoir depth] （H） are considered as inputs to the SVM and GPR. We give an equation for determination oil reservoir induced earthquake M. The developed SVM and GPR have been compared with] the Artificial Neural Network （ANN） method. The results show that the developed SVM and] GPR are efficient tools for prediction of reservoir induced earthquake M. /

Study on Precise Location and Structure of Earthquakes in the Shanxi Reservoir,Zhejiang Province

The Shanxi reservoir earthquakes are significant seismic events in southern Zhejiang Province in recent years, an area with fewer and weaker earthquakes. The seismicity showed an intermittent characteristic and group distribution. The epicenters located by the seismic network did not show a predominant direction and the seismogenic structure is not clear. In the study, the nonlinear imaginary wave travel time equation was linearized and solved, and the source position, initial imaginary velocity and travel time residuals were obtained. Then by doubling the standard deviation as time residuals, the maximum error generated from longitude, latitude, depth and imaginary velocity was calculated. The genetic population was structured using the maximum error and the end result of earthquake location was obtained by genetic algorithm. The result of relocation of the Shanxi reservoir earthquakes with this method shows that earthquakes are largely concentrated on a near-vertical, northwest oriented fault plane, and the included angles between the normal of the plane and the due north, due east and vertical directions are 46~, 44~, and 87~, respectively. The result is in agreement with that of comprehensive fault plane solutions of small earthquakes. The average depth of the earthquakes was 4.7km, the maximum depth 9.5kin, and the minimum depth 1.7km. The epicenters showed a northwestward narrow banded distribution, and the focal depth increased along the northwest direction. There was a discontinuous seismic gap of about 3.5km long at the northwest end of the strip. The characteristics of source parameters obtained by using the Borun model were not significantly different from that of tectonic earthquakes. Seismic stress drop was about 0.33MPa, and the average stress drop was 0.88MPa. According to the stress drop＇ spatial distribution, the seismic discontinuities segment at the northwest end of the strip is in a low stress drop zone.

Research and Practice on the Crustal Deformation Mobile Monitoring Network Layout in the Hydropower Station Reservoir Area

According to the construction project of the crustal deformation mobile monitoring network in the cascade hydropower stations built in the lower reaches of Jinsha River,this paper analyzes the design ideas and layout principles of crustal deformation mobile monitoring used in the monitoring of reservoir induced earthquakes. This paper introduces three types of monitoring networks used in the Xiluodu reservoir and Xiangjiaba reservoir, as well as the work already undertaken,in order to provide a kind of reference for the related engineering construction and comprehensive monitoring of reservoir induced earthquakes.