Precipitation prediction method based on deep network

Abstract

The invention discloses a precipitation prediction method based on a deep network. The precipitation prediction method comprises specific steps as follows: collecting hydrological environment data, preprocessing the data and normalizing the data in a 01 interval; detecting the sufficiency of environmental factors by using KMO test and Bartlett sphericity test, and screening the environmental factors with a factor analysis method after test; using a divided training sample as an input value of the deep network, subjecting the network to hierarchical unsupervised learning and then performing reverse fine adjustment on the whole network by use of a top BP network to guarantee the precision; using a test sample as the input of a trained model and inversely-normalizing the output obtained from the model to obtain the predicted result of precipitation. The precipitation of an area in the future can be predicted more accurately, the factors with lower correlation are screened out with the factor analysis method, the calculation efficiency is improved, and the scientificity and reasonability of the precipitation prediction process are greatly enhanced.

Description

technical field [0001] The invention relates to a precipitation prediction method based on a deep network. Background technique [0002] With the rapid expansion of population, the pollution level of rivers is also rising. How to make full use of the precious water resources on the earth is a serious problem facing human beings. As a very important link in the hydrological system cycle, precipitation is in The entire water cycle plays a key role, and the drastic changes in precipitation in a relatively short period of time can easily lead to drought and flood disasters in the regional environment, thus causing serious harm to the economic development of the entire region. For this reason, how to better Precise prediction of future precipitation in a relatively short period of time is one of the key issues that need to be solved urgently in the field of water information. [0003] Precipitation prediction has made great progress in recent decades. A type of model that is oft...

AI Technical Summary

Problems solved by technology

[0004] The physical statistical model has strict requirements on the quality of the data, and the location of the region has a great influence on the prediction effect. It is not flexible enough in actual use, and is easily affected by unstable factors, and it is similar to the linear description method, which cannot be very accurate. Stable to predict precipitation, there is a large randomness

Images