Algae bloom prediction method based on principal component analysis and BP neural network

A technology of BP neural network and principal component analysis, applied in neural learning methods, biological neural network models, prediction, etc., can solve problems such as low prediction accuracy, redundant samples and large randomness

Inactive Publication Date: 2019-07-23
CHINA THREE GORGES UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to directly predict the chlorophyll a content of the water body with a large amount of monitoring index data in the existing algae bloom prediction method, the sample is redundant and random, and the prediction accuracy is not high. Principal component analysis and BP neural network algae bloom prediction method to select the main factors of algae growth, reduce the randomness of model input factors, and improve prediction accuracy

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
  • Algae bloom prediction method based on principal component analysis and BP neural network
  • Algae bloom prediction method based on principal component analysis and BP neural network
  • Algae bloom prediction method based on principal component analysis and BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] The invention provides a method for predicting algal blooms based on a BP neural network. like figure 1 The flow shown, the specific steps are as follows:

[0069] Step 1. Monitoring data preprocessing;

[0070] 1. Data outlier processing;

[0071] The data used are 13 monitoring index values ​​of PH, ammonia nitrogen, conductivity, water temperature, dissolved oxygen, chlorophyll, freshwater blue-green algae, redox potential, air temperature, air pressure, relative humidity, rainfall and light intensity during the monitoring period of a reservoir research water area , the frequency of data capture is once every 10 minutes. Since the monitoring data is susceptible to external interference and the data is random, there will be outliers in the monitoring data that are obviously inconsistent with the actual situation. The present invention adopts the Chauvier criterion to determine the abnormal value in the sample data, that is, in a certain monitoring data, n times of...

Embodiment 2

[0135] A method for predicting algal blooms based on BP neural network, said method comprising the following steps:

[0136] Step 1. Monitoring data preprocessing;

[0137] The data used are pH, ammonia nitrogen, chemical oxygen demand, water temperature, dissolved oxygen, chlorophyll, air pressure, sea level air pressure, maximum air pressure, minimum air pressure, maximum wind speed, maximum wind speed, average wind speed, temperature / air temperature, maximum air temperature, 21 monitoring index values ​​such as minimum temperature, relative humidity, water vapor pressure, minimum relative humidity, rainfall and light intensity. Similar to Embodiment 1, data outlier processing, data smoothing processing, and data type conversion are sequentially performed here.

[0138] Step 2. Influencing factor analysis based on principal component analysis;

[0139] 1. Calculate the correlation matrix of each indicator

[0140] The correlation analysis of the 21 monitoring indicators 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 an algae bloom prediction method based on principal component analysis and a BP neural network, and belongs to the technical field of water environment management. The method comprises the steps of monitoring data randomness preprocessing; carrying out influence factor analysis based on a principal component analysis method; and constructing a prediction model by taking thechlorophyll a content and the chlorophyll a content change rate of the water body as output parameters and analyzing the prediction precision. The method is characterized in that an integral derivation data smoothing method is adopted, so that the influence of data randomness is eliminated; based on a principal component analysis method, prediction model input factors are simplified, chlorophylla content change rate is taken as an output parameter, and the defect that chlorophyll a content fluctuation interferes with a prediction result is eliminated, so that the prediction precision of thealgae bloom is effectively improved.

Description

technical field [0001] The invention relates to a method for predicting algae blooms based on principal component analysis and BP neural network, which belongs to the technical field of water environment management. It is a sensitivity analysis method to analyze the change degree of the output value before and after the input factor standard deviation disturbance is added. Background technique [0002] Algae bloom refers to a water pollution phenomenon in which algal blooms explode and accumulate to a certain concentration in eutrophic water bodies when the environmental conditions such as light intensity, temperature, climate, and hydrology are favorable for the growth and reproduction of algae. The outbreak of algal blooms will seriously damage the ecological balance of the water area, affect the sensory properties of the water body and the quality of urban water supply, and some algae can even secrete and release toxic substances into the water body. Pay attention to. I...

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): G06K9/62G06N3/08G06Q10/04G06Q50/26
CPCG06N3/084G06Q10/04G06Q50/26G06F18/2135G06F18/2433
Inventor 蒋定国全秀峰戴会超刘伟李飞王蒙蒙杨晨昱姚义振
Owner CHINA THREE GORGES UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap