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

Local rainfall pattern analysis method based on machine learning

A technology of machine learning and analysis methods, which is applied in the fields of water conservancy projects and flood control forecasting. It can solve the problems of different sample selection, subjectivity, and different understandings, so as to avoid differences and save the workload of human analysis.

Active Publication Date: 2020-03-27
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF13 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the same-frequency method requires more human intervention, and the results are often subjective due to different sample selection and understanding due to different expert experience.
The Chicago rain pattern, the Huff rain pattern, the Yen&Chow rain pattern and other design rain patterns are obtained by foreign scholars based on the generalized design of rainstorm samples in a certain area, and there is a certain gap with the actual rainfall process, and there is currently no recognized rain pattern as a The basis of the design, due to the differences in the mechanism of heavy rain in various places, the selected design rain pattern is not necessarily representative

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
  • Local rainfall pattern analysis method based on machine learning
  • Local rainfall pattern analysis method based on machine learning
  • Local rainfall pattern analysis method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A method for analyzing local rainfall and rain patterns based on machine learning, comprising the following steps:

[0049] 1) Data collection, processing and storage

[0050] Data collection: Collect rainfall observation data from hydrological and meteorological stations in the watershed (area) to be analyzed. Due to the large demand for data volume in cluster analysis, the time span of rainfall data needs to cover 10 years or more.

[0051] Data processing: the rainfall data is processed into a time series of equal time periods. If the original data is non-equal time period data, the data needs to be interpolated. It is preferable to interpolate according to the rainfall accumulation curve, such as figure 2 As shown, firstly, the original sequence is used to obtain the rainfall accumulation curve, and then the difference is obtained to obtain the equal-period rainfall time series {P′ 1 , P′ 2 , P′ 3 ,...,P′ 12}.

[0052] Save the processed rainfall time series d...

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 local rainfall pattern analysis method based on machine learning. The local rainfall pattern analysis method comprises the following steps: 1) collecting, processing and storing data; 2) automatically extracting rainfall events; 3) generating a local rainfall sample set; 4) carrying out GPU acceleration-based rainfall event clustering analysis; and 5) analyzing the generated clustering tree to obtain a representative rain pattern. The local rainfall pattern analysis method collects basin station observation data, automatically extracts rainfall events, and analyzes the most representative rainfall process by adopting a machine learning method to serve as a local rainfall representative rain pattern, thus greatly reducing the workload of manual analysis, avoiding the difference caused by subjective judgment while the analysis result has more regional pertinence, and providing powerful support for mountain torrent critical rainfall analysis and urban inland inundation numerical simulation.

Description

technical field [0001] The invention belongs to the technical field of water conservancy engineering, in particular to the technical field of flood control forecasting, and specifically relates to a machine learning-based analysis method for local rainfall patterns. Background technique [0002] In recent years, extreme rainstorms have occurred frequently in my country, and local rainstorms are sudden and short-lived, which are the main inducing factors of mountain torrents and urban waterlogging. For local rainstorms, in addition to rainfall amount and intensity, rain pattern, as a description of the rainstorm process, shows the distribution of rainstorm intensity on the time scale, and is one of the main disaster-causing characteristics of rainstorm events. The torrential rain process of different rain types has completely different disaster-causing properties. [0003] Due to the steep ups and downs of the rainstorm and flood process in hilly areas, it is difficult to fo...

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): G06Q50/26G06Q10/06
CPCG06Q10/0639G06Q50/265
Inventor 王帆
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES