基于单层神经网络模型的风化壳型稀土矿床母岩中低含量稀土副矿物质量分数的反演方法
By constructing an inversion method based on a single-layer neural network model and combining whole-rock and mineral data, the problem of accurate quantification of low-content rare earth accessory minerals in weathering crust-type rare earth deposits was solved, achieving high-precision mineral identification and interpretation.
CN120526890BActive Publication Date: 2026-07-17GUANGZHOU INSTITUTE OF GEOCHEMISTRY CHINESE ACADEMY OF SCIENCES
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU INSTITUTE OF GEOCHEMISTRY CHINESE ACADEMY OF SCIENCES
- Filing Date
- 2025-05-16
- Publication Date
- 2026-07-17
Smart Images
Figure CN120526890B_ABST
Abstract
本发明公开了一种基于单层神经网络模型的风化壳型稀土矿床母岩中低含量稀土副矿物质量分数的反演方法，该方法包含：获取稀土元素在全岩中的含量数据；对岩石样品中矿物的稀土配分特征分析；构建单层神经网络结构对矿物质量分数进行反演求解，设定各矿物质量分数为待优化权重，以各矿物稀土元素含量矩阵为输入，以母岩全岩稀土元素含量为输出；设置神经网络主损失函数及副损失函数；迭代训练，通过误差反向传播优化各矿物的质量分数参数；训练收敛后，模型优化参数即为每种矿物的质量百分含量。本发明的方法不依赖传统图像识别方法，能准确识别含量低、粒径小、共生复杂的稀土副矿物，提升定量识别能力与地质解释性。
Need to check novelty before this filing date? Find Prior Art