Unequal space time sequence abnormal trend analysis method for disaster prediction

Abstract

The invention discloses an unequal space time sequence abnormal trend analysis method for disaster prediction and belongs to the technical field of disaster prediction. Firstly, dynamic observation data with set indexes of a to-be-studied disaster are acquired, and the optimal space of an unequal space time sequence is determined; then, noise components of the dynamic observation data are removed;finally, abnormal trend detection is performed on the obtained dynamic observation data. The concept of the optimal space of the unequal space time sequence and a calculation method are provided, calculation is convenient, and the unequal space time sequence is converted into an equal space time sequence by use of the optimal space. The method can recognize the abnormal trend in the unequal spacetime sequence quickly and assist related experts in disaster prediction.

Description

technical field [0001] The invention belongs to the technical field of disaster prediction, in particular to a method for analyzing abnormal trend of time series with unequal intervals for disaster prediction. Background technique [0002] Natural disasters are major threats faced by the whole world. Their common characteristics are strong suddenness and great destructive power. They are difficult to predict and avoid accurately, often causing heavy casualties and economic losses, and bringing huge and far-reaching social impacts. Disaster prediction is an important part and future development direction of disaster prevention and mitigation and disaster emergency response. Relevant research and practical experience have shown that effective disaster prediction can largely avoid heavy losses caused by natural disasters: for example, in February 1975, the earthquake with a magnitude of 7.0 occurred in Haicheng and Yingkou, Liaoning Province, China. The earthquake was accurate...

AI Technical Summary

Problems solved by technology

The dynamic observation sequence has a strong unequal spacing, so it is difficult for traditional time series analysis methods to deal with it directly, and the noise components in it cover up the real change trend to a certain extent

Therefore, the above two characteristics of dynamic observation data in the field of disaster prediction make it extremely difficult to extract abnormal trends from dynamic observation data and then perform disaster prediction.

Images