论文部分内容阅读
沉积物的形成受到多种地质因素的综合控制。通过粒度分析可判别沉积物的成因类型,推断其形成的沉积环境,解释环境演变;而沉积物的粒度组分除了受到原岩的控制外,还受到机械沉积作用的影响难以准确预测。运用人工神经网络对稳定湖相沉积物和风沉积物的粒度参数进行研究,将沉积物的4个粒度参数作为网络模型的输入变量,在对168个浙闽沿海迎风岸风成老红砂样品和282个苏贝淖湖滨湖泊沉积物样品所对应的粒度参数进行数据样本训练之后,获得了基于BP神经网络的稳定湖相和风沉积物预测模型。然后利用448个大树摆鱼湖相沉积物粒度参数样本和100个兰州榆中黄土风沉积物粒度参数样本作为测试样本对该模型进行了测试和验证,结果显示模型的可靠性较好,能够对沉积物的形成环境做出正确的判断。
The formation of sediments is controlled by a variety of geological factors. By means of particle size analysis, the type of sedimentary genesis can be distinguished and the sedimentary environment formed can be inferred and the environmental evolution can be explained. However, the grain size components of sediments are difficult to predict accurately due to the influence of mechanical sedimentation. Using artificial neural network to study the grain size parameters of stable lacustrine sediments and wind sediments, taking the four grain size parameters of sediments as the input variables of the network model, After data samples were trained on the particle size parameters corresponding to 282 sediment samples from Lakeside lakes of Lake Beibei, stable lacustrine and wind sediment prediction models based on BP neural network were obtained. Then, the model was tested and verified by using 448 samples of pelagic lacustrine sediment particle size and 100 samples of loess aeolian wind sediment in Lanzhou as test samples. The results show that the reliability of the model is good, Correct the formation of the sediment environment.