基于多层前馈神经网络加权提高全球平均测高精度方法

基于多层前馈神经网络加权提高全球平均测高精度方法，包括：明确星座构型对GNSS-R测高能力的影响，构建多层前馈神经网络加权预测模型并进行验证，最后利用该模型进行星载GNSS-R测高能力预测。本发明解决了不同仿真条件下星载GNSS-R测高能力评估复杂的问题，显著提高了测高精度的计算效率。 A method for improving global average altimetry precision based on multi-layer feed-forward neural network weighting comprises the steps that the influence...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageChinese
Published 17.06.2025
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:基于多层前馈神经网络加权提高全球平均测高精度方法，包括：明确星座构型对GNSS-R测高能力的影响，构建多层前馈神经网络加权预测模型并进行验证，最后利用该模型进行星载GNSS-R测高能力预测。本发明解决了不同仿真条件下星载GNSS-R测高能力评估复杂的问题，显著提高了测高精度的计算效率。 A method for improving global average altimetry precision based on multi-layer feed-forward neural network weighting comprises the steps that the influence of constellation configuration on GNSS-R altimetry capacity is determined, a multi-layer feed-forward neural network weighting prediction model is constructed and verified, and finally satellite-borne GNSS-R altimetry capacity prediction is conducted through the model. According to the method, the problem that satellite-borne GNSS-R height measurement capability evaluation is complex under different simulation conditions is solved, and the calculation efficiency of height measurement precision is remarkably improved.
Bibliography:Application Number: CN202211599173