Visual analysis method and system for ocean multidimensional data

Abstract

The invention belongs to the technical field of visual analysis, discloses a visual analysis method and system for ocean multidimensional data, and aims to reduce large-scale ocean data by using a dimension reduction method on the basis of reserving a data relation. The correlation among the ocean multi-dimensional data and the correlation among the dimensions is analyzed on the basis of visual display; and a multi-view visual analysis method suitable for ocean multi-dimensional data is further improved. According to the parallel coordinate visual analysis method provided by the invention, thebuoy observation point data is visually displayed, and a user is supported to directly select a data file needing to be analyzed; a sliding block function is added to select a time point which a useris interested in or a certain dimension data value interval, so that data which the user wants to observe can be displayed more visually; interested data is selected from the lower data bar, and thedistribution condition of the interested data can be highlighted in the visual parallel coordinates, so that the visual effect is more visual.

Description

technical field [0001] The invention belongs to the technical field of visual analysis, and in particular relates to a visual analysis method and system for marine multidimensional data. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] At present, my country has formed a comprehensive ocean monitoring network, resulting in explosive growth of ocean data. The sources of monitoring data include aerial remote sensing, marine stations, buoy observation systems, etc.; multiple sources lead to the use of different data mining techniques when obtaining marine data, which in turn leads to differences in data formats, parameters and areas of use of marine data. There are huge differences; at the same time, marine data contains some sensitive information such as meteorology, hydrology, disaster warning, etc., and security measures need to be taken; on the other hand, the application value of marine data must be...

AI Technical Summary

Problems solved by technology

Ocean big data has the characteristics of massive, multi-source, multi-dimensional, dynamic, spatial, and heterogeneous. Traditional visual analysis technologies have certain limitations in mining the hidden information behind ocean data:

[0020] (2) Traditional visual analysis technology cannot accurately judge the correlation of marine data and data of various dimensions

[0021] (3) The visual analysis of marine data based on scatter plots is not suitable for the situation where all dimensions need to be displayed at the same time; and with the increase of data dimensions, the scale of the scatter plot matrix increases, which is difficult for the layout of the visual interface and the understanding of users Brings a burden, and based on the expansion of two-dimensional scatter diagrams, it does not have the ability to discover more dimensional attribute correlations, and there are still limitations

[0022] (4) The visual analysis of marine data based on parallel coordinates will lead to dense lines and overlapping coverage caused by large-scale data items, and it is difficult to effectively display the specific information of each dimension of the original data, which has certain limitations

When performing similarity measurement, it is necessary to calculate the difference between two pairs of data, resulting in a huge amount of calculation

Images