首页|Findings from NORSAR Provides New Data about Networks (Arraynet: a Combined Seismic Phase Classification and Back-azimuth Regression Neural Network for Array Processing Pipelines)
Findings from NORSAR Provides New Data about Networks (Arraynet: a Combined Seismic Phase Classification and Back-azimuth Regression Neural Network for Array Processing Pipelines)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Network Daily News - Investigatorspublish new report on Networks. According to news reporting originating from Kjeller, Norway, by NewsRxcorrespondents, research stated, “Array processing is an integral part of automatic seismic event detectionpipelines for measuring apparent velocity and backazimuth of seismic arrivals. Both quantities are usuallymeasured under the plane-wave assumption, and are essential to classify the phase type and to determinethe direction toward the event epicenter.”Our news editors obtained a quote from the research from NORSAR, “However, structural inhomogeneitiescan lead to deviations from the plane-wave model, which must be taken into account for phaseclassification and back-azimuth estimation. We suggest a combined classification and regression neural network,which we call ArrayNet, to determine the phase type and back -azimuth directly from the arrival-timedifferences between all combinations of stations of a given seismic array without assuming a plane-wavemodel. ArrayNet is trained using regional P-and S -wave arrivals of over 30,000 seismic events from reviewedregional bulletins in northern Europe from the past three decades. ArrayNet models are generatedand trained for each of the ARCES, FINES, and SPITS seismic arrays. We observe excellent per-formancefor the seismic phase classification (up to 99% accuracy), and the derived back -azimuth residuals aresignificantly improved in comparison with traditional array processing results using the plane-wave assumption.The SPITS array in Svalbard exhibits particular issues when it comes to array processing in the formof high apparent seismic velocities and a multitude of frost quake signals inside the array, and we showhow our new approach better handles these obstacles. Furthermore, we demonstrate the performance ofArrayNet on 20 months of continuous phase detections from the ARCES array and investigate the resultsfor a selection of regional seismic events of interest.”
NETL
NSTL
