Unlock instant, AI-driven research and patent intelligence for your innovation.

Rapid prediction method for rainstorm waterlogging event

A forecasting method and rainstorm technology, applied in forecasting, instruments, biological neural network models, etc., can solve problems such as shortening the forecast time of waterlogging risk, and achieve the effects of fast calculation speed, high forecasting accuracy, and large demand.

Active Publication Date: 2021-09-03
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the actual waterlogging monitoring data and numerical simulation results, the prediction results of this method have very small errors, which can effectively replace the numerical simulation prediction results, greatly shorten the time for waterlogging risk prediction, and effectively solve the timeliness of urban waterlogging prediction and early warning question

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
  • Rapid prediction method for rainstorm waterlogging event
  • Rapid prediction method for rainstorm waterlogging event
  • Rapid prediction method for rainstorm waterlogging event

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] like figure 1 As shown, step 100 is executed to obtain multiple types of rainfall processes. The rainfall process includes the short-duration heavy rainfall process, the characteristic rainfall process of different temporal and spatial distributions, and the design rainfall process designed according to the rainstorm intensity formula, among which: the short-duration heavy rainfall process is the short-duration heavy rain process within 3 hours of the actual rainfall duration ; The characteristic rainfall process of different temporal and spatial distributions is the rainfall process that conforms to the characteristics of different types of spatial and temporal distribution and the cumulative rainfall of a single station in 3 hours is from 30 mm to 500 mm; 30mm to 500mm Chicago rain pattern rainfall process.

[0056] Execute step 110 to construct a refined urban flood simulation model, which consists of a one-dimensional river network model, a two-dimensional surface...

Embodiment 2

[0078] This paper combines the traditional numerical simulation model with neural network technology, and proposes a new method for predicting urban waterlogging risk. Taking the Hewan area of ​​Shenzhen as an example, this method is used to simulate and predict the process of rainstorm waterlogging. The results show that the prediction results of this method have very small errors compared with the measured water accumulation monitoring data and numerical simulation results, which can effectively replace the prediction results of numerical simulation, greatly shorten the time for waterlogging risk prediction, and effectively solve the problem of urban waterlogging prediction and early warning timeliness issues.

[0079] The Hewan River Basin in Shenzhen is one of the five major river basins in Shenzhen. It is a typical area of ​​rapid development in Shenzhen. The underlying surface has a high degree of hardening, the confluence time is short, and the construction of drainage f...

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 provides a rapid prediction method for a rainstorm waterlogging event, and the method comprises the steps: obtaining various types of rainfall processes, and also comprises the following steps: constructing an urban flood simulation refined model; checking the urban flood simulation refined model by using the various types of rainfall processes to obtain a rainstorm-waterlogging sample; using 90% of the rainstorm-waterlogging samples to construct a neural network model of each ponding point, and training the neural network models; utilizing the trained neural network model to predict the ponding process which does not participate in model training; and judging the similarity degree of prediction results by calculating the decision coefficient R2 of the prediction data and the simulation data. According to the rapid prediction method for the rainstorm waterlogging event, a traditional numerical simulation model and an artificial neural network are combined, a large number of rainstorm-waterlogging samples under different rainfall conditions are generated through the numerical simulation model, and a BP neural network ponding prediction model is trained through the samples.

Description

technical field [0001] The invention relates to the technical field of water conservancy engineering, in particular to a rapid prediction method for rainstorm and waterlogging events. Background technique [0002] With the change of global climate and environment, the frequency of extreme rainfall is getting higher and higher, and urban waterlogging disasters occur frequently. With the rapid development of cities, the population and urban economy have become more and more concentrated, and the losses caused by extreme precipitation and its associated secondary disasters have also been multiplied. Many cities such as Beijing, Guangzhou, Shenzhen, and Wuhan Larger flood disasters have occurred, and heavy rainstorms in cities have become the main disasters that affect my country's urban construction and normal life. Urban flood prevention and control has important scientific value and strategic significance for ensuring national water security and supporting sustainable social ...

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): G06Q10/04G06Q10/06G06Q50/26G06N3/04
CPCG06Q10/04G06Q10/067G06Q50/265G06N3/045Y02A10/40
Inventor 刘媛媛刘业森臧文斌李敏柴福鑫刘舒郑敬伟
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES