Rayleigh wave frequency dispersion curve inversion method based on deep learning and application

• Main Authors: ZHANG ZHIHOU, ZHAO GUANGMAO, LUO BING, ZHAO MINGHAO, ZHANG TIANYI, LIU WEIXIN, XIE XIAOGUO, XU GUANGCHUN, YE ZHIHU
• Format: Patent
• Language: Chinese; English
• Published: 22.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETECTING MASSES OR OBJECTS; GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; MEASURING; PHYSICS; TESTING

The invention provides a Rayleigh wave frequency dispersion curve inversion method based on deep learning and application. The Rayleigh wave frequency dispersion curve inversion method comprises the steps of performing seismic data acquisition on Rayleigh waves, superposing the acquired seismic data to form a frequency dispersion curve energy diagram, extracting a frequency dispersion curve from an energy spectrum, and inverting the frequency dispersion curve to obtain shear wave velocities of all underground layers. According to the geophysical inversion based on the technical scheme of the invention, the data set has sufficient performance and diversity, the network structure has higher universality and generalization, the inversion precision is more accurate in the shallow layer including the stratum boundary, and the stratum condition deeper than that of the traditional inversion method can be inverted. The Rayleigh surface wave exploration technology for performing inversion on the frequency dispersion c