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

A river water level prediction method based on chaotic fireflies and a gradient lifting tree model

A technology of gradient boosting tree and river water level, applied in the field of information and hydrological condition prediction, can solve the problem of low degree of mining a large amount of water conservancy data, and achieve the effect of classification and regression tasks, good classification and regression tasks

Pending Publication Date: 2019-05-03
NANJING UNIV OF TECH
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, China has developed rapidly in the field of water conservancy informatization, and has achieved some successful applications in water resource allocation and management. Fewer means of discovering valuable information in hydrological data

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
  • A river water level prediction method based on chaotic fireflies and a gradient lifting tree model
  • A river water level prediction method based on chaotic fireflies and a gradient lifting tree model
  • A river water level prediction method based on chaotic fireflies and a gradient lifting tree model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] combine figure 1 , the present invention carries out river water level prediction based on chaotic firefly and gradient lifting tree model, comprises the following steps:

[0047] A. Data collection, the required data is divided into five categories in total, including complete verifiable time stamp data that can indicate that a piece of data already exists at a specific time point, and the cumulative water volume data of the sum of river flow in the current time period, unit The instantaneous flow data of the fluid volume flowing through the effective section of the closed pipe or open channel within a certain period of time, the flow rate data of the displacement of the river per unit time, and the water level data that most intuitively reflect the water regime in the current time period.

[0048] B. The Decision Tree model trained with the Gradient Boosting strategy. The result of the model is a set of regression classification tree combinations (CART Tree Ensemble),...

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 river water level prediction method based on chaotic fireflies and a gradient lifting tree model, and relates to the technical field of information and hydrological conditionprediction. Firstly, data is collected, and required data is divided into five classes; and then data preprocessing is carried out, including abnormal value elimination, missing value processing and data normalization. The improved chaotic firefly algorithm is used for optimizing training parameters of the gradient lifting tree model, and the improved gradient lifting tree model is applied to river water level prediction research of structural data. Finally, constructing a training sample set;randomly adopting a part of five types of data obtained after processing for model training; accordingto the method, a GSO algorithm is used for optimizing and parameter tuning is carried out to obtain a GBDT model under optimal parameters, the generalization ability is better, the water level prediction precision of the model is improved, finally, a test set is combined for carrying out model inspection, errors between an obtained actual value and a calculated value are compared and analyzed, and the good performance of the model is verified.

Description

technical field [0001] The invention discloses a river water level prediction method based on a chaotic firefly and a gradient boosting tree model, and relates to the field of information technology and the technical field of hydrological situation prediction. Background technique [0002] In the early 1970s, the Swedish Hydrometeorological Agency developed a hydrological forecasting model for the flood forecasting of hydropower plants, and carried out flood forecasting by inputting reasonable forecasting parameters, and verified the forecasting results. In recent years, China has developed rapidly in the field of water conservancy informatization, and has achieved some successful applications in water resource allocation and management. There are fewer means of discovering valuable information in hydrological data. [0003] The research significance of this note mainly lies in how to make reasonable and accurate predictions of river water levels by means of information tec...

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): G06Q10/04G06K9/62G06N3/00
Inventor 梁雪春苏佳佩
Owner NANJING UNIV OF 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com