Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

WOA-LSTM-MC-based hydrological time series prediction optimization method

A hydrological time series, forecast optimization technology, applied in forecasting, neural learning methods, data processing applications, etc., can solve the problems of small sample set model accuracy, time-consuming training, large errors, etc., to ensure global search capabilities and local The effect of exploring ability and speeding up the convergence speed

Active Publication Date: 2021-04-30
HOHAI UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The effect of hydrological time series prediction is remarkable, but there are still some problems. For example, the accuracy of the model for small sample sets will be affected to a certain extent. There are problems that the larger the amount of data, the larger the error, and the more time-consuming the training. The prediction model itself is also difficult. There are some problems, so it is crucial to choose an algorithmic model with a certain robustness

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • WOA-LSTM-MC-based hydrological time series prediction optimization method
  • WOA-LSTM-MC-based hydrological time series prediction optimization method
  • WOA-LSTM-MC-based hydrological time series prediction optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067]Example 1: This example is predicted on the Hankou Hydrology Station of the Yangtze River Basin, such asFigure 5 withFigure 6 As shown, including the following steps:

[0068]Step S1, the data set of this embodiment selects the hourly traffic data of Hankou Hydrology, January 1, 2019, from January 1, 2020, of which 8:00 to 2020, January 2019 5 At 7:00 on the 15th, 12,000 data were taken as a training set, and from 8:00 on June 12, 2020, 4351 data were 4351 data as a test set.

[0069]Step S11, the present embodiment sets the traffic data of the Hankou Hydrology as a forecasting factor, and sets a 1-24-hour foreseeable period, and different predictive models are established for different foreseevelopments. By correlation analysis, the first T is selected1Hourly prediction T2Hours, T1Get through correlation analysis, T2For the foresee period.

[0070]Step S21, the present embodiment takes the flow data of Hankou Station in the Yangtze River Basin as an example, and the adaptivity value i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a WOA-LSTM-MC-based hydrological time series prediction optimization method. The method comprises the steps of performing parameter optimization on part of parameters of a prediction model by using an optimized whale optimization algorithm; selecting flow data of the hydrological station to be predicted as experimental data; dividing the data set into a training set and a test set, and performing training and prediction; using a Markov chain MC for correction, so that a final hydrological prediction result, namely a more accurate prediction value, is obtained; and establishing a hybrid WOA-LSTM-MC (White Object Model Management Controller) model. According to the method, the optimal parameters required by the prediction model can be found more quickly and accurately, the global search capability and the local exploration capability of the algorithm can be ensured, and the convergence rate is high; and the prediction result is accurate.

Description

Technical field[0001]The present invention belongs to hydrological prediction techniques, and more particularly to a hydrological time sequence prediction optimization method based on WOA-LSTM-MC.Background technique[0002]With the development of today's computer and software technology, its application is increasing, the massive data of time series is more visible. On the one hand, some of these data can be used for us to study, so massive time series Data mining techniques are born, and we can perform the status of future data through the law and development trends, so it is critical to the analysis and prediction of time series.[0003]Hydrological data is the discrete record, evaporation amount, rainfall, and water level, etc. of the hydrological process, and the standard time series. Hydrological data has the characteristics of large data volume, fast update, and complicated types, which are also related to many of the season, geommon, and hydrological laws. How to effectively ana...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/00G06N3/04G06N3/08G06Q10/04
CPCG06N3/006G06N3/049G06N3/08G06Q10/04
Inventor 窦钰博万定生余宇峰杨志勇
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products