A ca-narx water quality prediction method based on meteorological factors

A meteorological factor, water quality prediction technology, applied in the direction of prediction, neural learning methods, general water supply conservation, etc., can solve the problems of difficult monitoring and control of discharge methods, few researches, etc., to achieve strong versatility and portability, stable performance, The effect of overcoming the requirement of covariance

Active Publication Date: 2022-03-25
YANSHAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Non-point source pollution mainly enters water bodies through agricultural application of chemical fertilizers, soil erosion, surface runoff, and atmospheric dry and wet deposition. The discharge methods are diverse and difficult to monitor and control. There are few researches at home and abroad.

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 ca-narx water quality prediction method based on meteorological factors
  • A ca-narx water quality prediction method based on meteorological factors
  • A ca-narx water quality prediction method based on meteorological factors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The key technology of the present invention is: 1. after data standardization, select the initial cluster center according to the four factor quantiles, perform preliminary clustering according to the Euclidean distance between each sample observation point and the initial cluster center, and then calculate the intra-class Variance, so as to continuously iterate according to the Mahalanobis distance between sample observations and various centers, until the total distance difference between the two iterations before and after is less than a certain value, while traversing a certain range of cluster numbers, according to the sample average silhouette coefficient (silhouette coefficient) value to determine the optimal number of clusters. ② According to the classified data, the forward NARX neural network is used to directly use the four meteorological factors and the water quality data of the previous 1-2 days as input factors, and combine the m-fold cross-validation metho...

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 CA-NARX water quality prediction method based on meteorological factors, which belongs to the technical field of intelligent water quality prediction data application and includes the following steps: ① standardize data, ② create a sample matrix, ③ determine the initial cluster center according to the quantile , ④ perform initial clustering according to the Euclidean distance, ⑤ use the mean value of each class as the new cluster center, ⑥ cluster according to the Mahalanobis distance between each sample and the cluster center, ⑦ screen the number of clusters, ⑧ select the most Good number of clusters, ⑨m-fold cross-validation to select training samples, ⑩forward NARX neural network classification prediction. The invention mainly solves the problems of high water quality prediction cost and low prediction accuracy of small and medium-sized reservoirs, and at the same time solves the problem of inapplicability of traditional clustering algorithms to data heterogeneity and different variances, and improves the accuracy of NARX neural network training. Improve to a certain extent.

Description

technical field [0001] The invention relates to the technical field of intelligent water quality prediction data application, in particular to a CA-NARX water quality prediction method based on meteorological factors, which is applied to water quality prediction and management of water sources. Background technique [0002] The water quality of water source areas is closely related to people's lives. Using scientific methods to predict water quality indicators is an effective method for water resources management and protection. The content of total phosphorus and total nitrogen is an important evaluation index for the eutrophication state of water body, and it is also an important factor affecting the water body environment. Accurate and rapid prediction of total phosphorus and total nitrogen content in water can provide theoretical support for water environment assessment and early warning, and also provide decision-making basis for relevant departments, which is helpful f...

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 Patents(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06N3/08
CPCG06Q10/04G06Q10/06393G06Q50/06G06N3/08Y02A20/152
Inventor 王晶耿燕章胤金玉玺
Owner YANSHAN 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