For density inversion of gravity anomaly data, once the inversion method is determined, the main factors affecting the inversion result are the inversion parameters and subdivision scheme. A set of reasonable inversion parameters and subdivision scheme can, not only improve the inversion process efficiency, but also ensure inversion result accuracy. The gravity inversion method based on correlation searching and the golden section algorithm is an effective potential field inversion method. It can be used to invert 2D and 3D physical properties with potential data observed on flat or rough surfaces. In this paper, we introduce in detail the density inversion principles based on correlation searching and the golden section algorithm. Considering that the gold section algorithm is not globally optimized. we present a heuristic method to ensure the inversion result is globally optimized. With a series of model tests, we systematically compare and analyze the inversion result efficiency and accuracy with different parameters. Based on the model test results, we conclude the selection principles for each inversion parameter with which the inversion accuracy can be obviously improved.
Quantitative thickness estimation of thin-layer is a great challenge in seismic exploration, especially for thin-layer below tuning thickness. In this article, we analyzed the seismic response cha- racteristics of rhythm and gradual type of thin-layer wedge models and presented a new method for thin-layer thickness estimation which uses relative peak frequency increment. This method can de- scribe the peak frequency to thickness relationship of rhythm and gradual thin-layers in unified equa- tion while the traditional methods using amplitude information cannot. What＇s more, it won＇t be in- fluenced by the absolute value of thin-layer reflection coefficient and peak frequency of wavelet. The unified equations were presented which can be used for rhythm and gradual thin-layer thickness cal- culation. Model tests showed that the method we introduced has a high precision and it doesn＇t need to determine the value of top or bottom reflection coefficient, so it has a more wide application in practice. The application of real data demonstrated that the relative peak frequency increment attribute can character the plane distribution feature and thickness characteristic of channel sand bodies very well.
