Crude oil film absolute thickness inversion method based on self-extended convolutional neural network

Abstract

The invention provides a crude oil film absolute thickness inversion method based on a self-extended convolutional neural network. The method comprises the following steps: screening actually measuredspectral data to obtain real spectral characteristic data; inputting the real spectral characteristic data into an adversarial generative network to generate self-expansion sample data; and performing feature extraction on the self-extended sample data by using a convolutional neural network, and performing inversion on the absolute thickness of the crude oil film. According to the method, actually measured spectral data are screened, wave bands with poor separability are removed, and accurate and quantitative inversion of the thickness of a crude oil film is facilitated; the adversarial generative network is used for expanding the data, so that a large amount of high-imitation data can be generated based on the model only by a small amount of measured data, the generalization of the model is enriched, and the robustness of the model is enhanced; and by utilizing the convolution process of the convolutional neural network, spectral information can be fully learned, and the loss of information amount is avoided, so that the inversion precision of the absolute thickness of the crude oil film is improved.

Description

technical field [0001] The invention relates to the field of ocean detection, in particular to a method for retrieving the absolute thickness of crude oil film based on a self-expanding convolutional neural network. Background technique [0002] Oil spill is a maritime emergency caused by oil leakage during offshore oil exploration, development, and transportation. It has been listed by the American Academy of Sciences as one of the 32 scientific issues to be solved before 2030. In recent years, marine oil spill disasters have occurred frequently, seriously affecting the sustainable development of the marine ecological environment and marine resources. The amount of oil spilled on the sea surface is an important indicator for evaluating the threat level of oil spill accidents at sea and determining the level of oil spill accidents. It is also an important basis for accountability for pollution compensation. [0003] Accurate acquisition of oil spill area, oil film thickness...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides a crude oil film absolute thickness inversion method based on a self-expanding convolutional neural network to solve the problem that the method for measuring the absolute thickness of the oil film in the prior art is limited to insufficient experimental data, resulting in low measurement accuracy.

Images