首页|Researcher from University of Naples Federico II Reports Details of New Studies and Findings in the Area of Machine Learning (A Robust and Rapid Grid-Based Mach ine Learning Approach for Inside and Off-Network Earthquakes Classification in . ..)
Researcher from University of Naples Federico II Reports Details of New Studies and Findings in the Area of Machine Learning (A Robust and Rapid Grid-Based Mach ine Learning Approach for Inside and Off-Network Earthquakes Classification in . ..)
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
New research on artificial intelligenc e is the subject of a new report. According to news reporting from Naples, Italy , by NewsRx journalists, research stated, "Earthquake location and magnitude est imation are critical for seismic monitoring and emergency response. However, acc urately determining the location and the magnitude of off-network earthquakes re mains challenging." Our news correspondents obtained a quote from the research from University of Na ples Federico II: "Seismic stations receive signals from various sources, and it is crucial to quickly discern whether events originated within the area of inte rest. Location determination relies on obtaining ample P-and S-wave readings to ensure accurate and dependable results. Seismic networks vary due to station ch anges or outages, and their variable geometry represents a constraint for tradit ional machine learning models, which rely on fixed data structures. This study p resents a novel approach for real-time classification of local and off-network e arthquakes using the first three associated P picks within an early warning scen ario, and also identifying the event's direction. To handle variable network geo metry, we employ a grid structure over the seismic area. The effectiveness of ou r method was initially validated with data from the Italian National Seismic Net work, selecting Central Italy and Messina Strait subnetworks, and from a subnetw ork of the Southern California Seismic Network; it achieves an inside-outside ac curacy of 95%, 93%, and 96%, and a locati on region accuracy of 93%, 82%, and 97%, respectively. Its robustness was further demonstrated using picks from an earthq uake early warning (EEW) system, the PRobabilistic and Evolutionary early warnin g SysTem (PRESTo) software, to simulate real and noncataloged input data."
University of Naples Federico IINaplesItalyEuropeCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
