LSTM neural network cyclic hydrological forecasting method based on mutual information

Abstract

The invention belongs to the technical field of data processing, and discloses an LSTM neural network cycle hydrological forecasting method based on mutual information, which comprises the following steps: screening and classifying original data through mutual information analysis, and taking rainfall, reservoir water level and flow hydrological characteristics as input characteristics of a long-term and short-term memory cycle forecasting model; the long-term change of flood is reflected by simulating rainfall process training and determining the structure of the LSTMC model; and verifying the output of the model by using the actual flood data. According to the method, the data set is analyzed by adopting a mutual information-based method, the flow at the current moment and each hydrological characteristic of the previous longer time period are fully captured, and the input characteristics of the model are dynamically selected. According to the method, the deep learning algorithm is utilized, the cyclic prediction model based on the LSTM neural network is adopted, when the method is used for flood flow time series prediction, the problem that the hydrological change process is greatly influenced by factors in the earlier stage is solved, and effective features can be automatically captured well.

Description

technical field [0001] The invention belongs to the technical field of data processing, in particular to a mutual information-based LSTM neural network cycle hydrological forecasting method. Background technique [0002] Currently, the closest available technique: Floods, as a type of natural disaster, are an integral part of hydrological research. Flood is a water flow phenomenon in which the water volume of rivers and lakes increases rapidly or the water level rises rapidly caused by natural factors such as heavy rain, rapid melting of ice and snow, and storm surge. When a flood hazard occurs, many hazards result, the consequences of which include danger to human life, disruption of transport and communication networks, damage to buildings and infrastructure, and loss of crops. Therefore, flood control and disaster reduction is particularly important. Correct and reliable flood forecasting is one of the most important means to improve the response time to flood disasters...

AI Technical Summary

Problems solved by technology

The shortcoming of prior art 2, on the one hand, all the input and output of the artificial neural network method are independent of each other, when used for time series analysis and prediction, any information about the order of the input sequence will be lost, and the hydrological change process is affected by the previous various Aspects of factors have a relatively large influence

On the other hand, the artificial neural network method has the disadvantages of slow convergence, easy to fall into local optimum, overfitting, etc.

[0006] To sum up, the problems existing in the existing technology are: the traditional model is difficult to simulate the complex physical relationship in the hydrological process and the input and output of the current artificial neural network are independent of each other, and the hydrological change process is greatly affected by various factors in the early stage, and The accuracy of flood forecasting for a longer period of time decreases rapidly

[0007] The difficulty of solving the above technical problems: Traditional models are difficult to simulate complex physical relationships in the hydrological process and the input and output of the current artificial neural network are independent of each other, while the hydrological change process is greatly affected by various factors in the early stage, and the flood forecast is accurate for a long time problems such as rapid decrease in speed

Images