A note on the equivalence of three major propagator algorithms for computational stability and efficiency

It is shown in this note that the three methods, the orthonormalization method, the minor matrix method and the recursive reflection-transmission matrix method are closely related and solve the numerical instability in the original Thomson-Haskell propagator matrix method equally well. Another stable and efficient method based on the orthonormalization and the Langer block-diagonal decomposition is presented to calculate the response of a horizotttal stratified model to a plane, spectral wave. It is a numerically robust Thomson-Haskell matrix method for high frequencies, large layer thicknesses and horizontal slownesses. The technique is applied to calculate reflection-transmission coefficients, body wave receiver functions and Rayleigh wave dispersion.

Receiver functions of CCDSN and crustal structure of Chinese mainland

The teleseismic receiver functions of 48 stations belonging to the CCDSN are used to invert the crustal structure beneath each station with the neighborhood algorithm. Thin layers with low velocity have been found beneath eight stations with ＂abnormal＂ observed receiver functions. Unreasonable results of few stations have been adjusted lightly with the trial-and-error method. The final result indicates that the crust in the western China is relatively thicker than the eastern China. The crust thickness beneath the Tibetan plateau is very large, which reaches 84 km at the station LSA. Double-crust structure exists below the stations LSA and CAD in Tibet, which might imply the collision between the Indian and Eurasian plates. A pronounced low velocity zone in the lower crust beneath the station TNC of Yunnan province might relate to the high temperature or emergence of partially molten material caused by Quaternary volcano, magma and geothermal activities in this area. The Moho is a transitional zone made up of thin layers instead of simple sharp discontinuity beneath several stations. The Conrad discontinuity is clearly identified beneath 20 stations mainly in the southeastern China, whereas it is blurry beneath 14 stations and uncertain beneath remaining stations.

Peeling linear inversion of upper mantle velocity structure with receiver functions

A peeling linear inversion method is presented to study the upper mantle （from Moho to 800 km depth） velocity structures with receiver functions. The influences of the crustal and upper mantle velocity ratio error on the inversion results are analyzed, and three valid measures are taken for its reduction. This method is tested with the IASP91 and the PREM models, and the upper mantle structures beneath the stations GTA, LZH, and AXX in northwestern China are then inverted. The results indicate that this inversion method is feasible to quantify upper mantle discontinuities, besides the discontinuities between 3hM （hM denotes the depth of Moho） and 5hM due to the interference of multiples from Moho. Smoothing is used to overcome possible false discontinuities from the multiples and ensure the stability of the inversion results, but the detailed information on the depth range between 3hM and 5hM is sacrificed.