北部湾海底沉积物稀土元素与影响因子关系的BP神经网络定量分析

摘要

The distribution characteristics of rare earth elements (REE) in bottom sediments are influenced by many factors. Hence, conducting a quantitative analysis is difficult. A qualitative analysis of the relationships between ΣREE content and provenance, hydrodynamics, grain size and mineral distribution in the Beibu Gulf shows that terrestrial rocks control the ΣREE composition. Both weaker hydrodynamics and finer grain size lead to a higher ΣREE content. Relative curves revealing the relationships between individual impact factors and ΣREE content were obtained from the combination of qualitative and quantitative analyses of the BP neural network, which trained the position of samples, gravel content, sand content, silt content, clay content and clay mineral content. The results are consistent with those of the quantitative analysis. The self-learning algorithm is automatically determined and calculated quantitatively. The impact of each factor on REEs and how each factor controls the ΣREE distribution is identified. Thus, environmental changes and the geological evolution of the region can be inferred based on curve variation and the actual situation. This method also provides useful theoretical guidance for the analysis of REE enrichment and dispersion.%海底沉积物中稀土元素的分布特征受很多影响因子的影响,很难定量分析.北部湾沉积物稀土元素(ΣREE)与物源、水动力、沉积物粒度和粘土矿物百分比等关系定性分析显示,本区的ΣREE的物源主要由陆源岩石控制,弱水动力和细粒度都对应较高含量的ΣREE.结合北部湾海底沉积物的位置、砾石含量、砂含量、粉砂含量、粘土含量和粘土矿物含量训练出来的BP神经在控制变量的情况下定量分析它们与ΣREE的关系,获得单个影响因子与ΣREE的关系曲线.这些关系曲线揭示了北部湾沉积物中稀土元素与各影响因子的联系,所获得的结果与定性分析的结果基本一致,该方法能够通过自主学习,自动判断并定量计算,有助于识别每一个因子对稀土元素含量影响的大小,是如何控制ΣREE的分布,从而根据曲线的变化规律结合实际情况去推断区域的环境变化及地质演变,对稀土元素的富集和分散提供有益的理论指导.