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

River flood prediction method based on deep learning model interpretable research strategy

A technology of deep learning and prediction methods, applied in the field of artificial intelligence, can solve the problem of low prediction accuracy of deep learning models, and achieve the effect of improving the prediction accuracy of models

Inactive Publication Date: 2022-03-15
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a river flood prediction method based on a deep learning model that can explain the research strategy, thereby solving the problem that the existing deep learning model for river flood prediction has low prediction accuracy technical issues

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
  • River flood prediction method based on deep learning model interpretable research strategy
  • River flood prediction method based on deep learning model interpretable research strategy
  • River flood prediction method based on deep learning model interpretable research strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0034] An embodiment of the present invention provides a river flood prediction method based on a deep learning model that can explain research strategies, such as figure 1 shown, including:

[0035] S1, divide the original time series data into the original training set and the original test set, and train the complex deep learning model Net-T including the LSTM network based on the original t...

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 riverway flood prediction method based on a deep learning model interpretable research strategy, and the method comprises the steps: building a more visual and reliable interpretable research strategy of a deep learning model Net-T, i.e., employing an interpretable assembly to construct a model Net-S, and achieving the prediction of the riverway flood on the premise of guaranteeing the minimum prediction capability difference of the two types of models. Carrying out substitution research on the deep learning model Net-T, and carrying out distillation training on the model Net-S so as to extract knowledge contained in the trained model Net-T to the model Net-S; selecting the trained model Net-S with the optimal prediction result according to the statistical indexes of the prediction results of the plurality of trained models Net-S, and determining the optimal input step length and the optimal prediction step length of the trained model Net-S; based on the optimal input step length and the optimal prediction step length, the trained model Net-T is adopted to predict the water level or flow of the river section.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and more specifically relates to a river flood prediction method based on a deep learning model that can explain research strategies. Background technique [0002] River flood forecasting is an important non-engineering measure to control flood disasters. Using the river flood forecasting method can not only directly provide the magnitude and occurrence time of flood disasters, but also provide accurate flood information for reservoir flood control scheduling, and then through the flood control function of the reservoir Reduce downstream flood disasters. Therefore, studying how to improve the reliability and accuracy of river flood prediction and constructing a river flood prediction model with high prediction accuracy has gradually become one of the important ways to control flood disasters in the river basin in the future. [0003] In recent years, deep learning models have bee...

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
IPC IPC(8): G06Q10/04G06N3/04G06N3/08G06K9/62G06N5/02G06Q50/26
CPCG06Q10/04G06N3/08G06N5/022G06Q50/26G06N3/044G06F18/214Y02A10/40
Inventor 康玲周丽伟李争和
Owner HUAZHONG UNIV OF SCI & TECH
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