重金属污染的卡尔曼预测及可视化系统研究

Research on Kalman Prediction and Visualization System for Heavy Metal Pollution

摘要: 传统的重金属污染预测是基于数学统计进行回归分析预测，由于现代人类生产活动、非自然地质演变等要素所带来的噪声影响，传统的数学统计方法预测效果欠佳，为了解决这一问题，针对基于卡尔曼滤波算法的重金属污染预测模型进行了研究，并采用皮尔逊相关系数检验和Wilcoxon符号秩检验来验证该预测模型的准确性，实验结果表明通过卡尔曼滤波算法建立的重金属污染预测模型具有良好的稳定性和准确性。此外，重点就重金属污染防治可视化进行了研究探讨，并基于Django架构设计的城市规划平台成功将区域重金属污染状况在地图上进行数据渲染和动态监测，对重金属污染起到一定的预防作用。

Abstract: Traditional heavy metal pollution prediction is based on mathematical statistics for regression analysis prediction, due to the noise influence brought by modern human production activities, unnatural geological evolution and other elements, the traditional mathematical statistics method prediction effect is poor, in order to solve this problem, for the heavy metal pollution prediction model based on Kalman filter algorithm was studied, and the Pearson correlation coefficient test and Wilcoxon The experimental results show that the heavy metal pollution prediction model established by Kalman filtering algorithm has good stability and accuracy. In addition, the research is focused on the visualization of heavy metal pollution prevention and control, and the urban planning platform designed based on Django architecture successfully renders the regional heavy metal pollution status on the map for data rendering and dynamic monitoring, which plays a certain role in the prevention of heavy metal pollution.