A Collaborative Compound Neural Network Model for Soil Heavy Metal Content Prediction

Wenqi Cao,Cong Zhang

doi:10.1109/access.2020.3009248

Wenqi Cao, Cong Zhang

Open Access

https://doi.org/10.1109/access.2020.3009248

Copy DOI

Abstract

The prediction of soil heavy metal content is an important part of the management of soil heavy metal pollution, but it is often ignored. At present, there are few studies on the prediction of soil heavy metal content, and it is an urgent problem to choose an efficient method for soil heavy metal content prediction. In this paper, a collaborative compound neural network model (CCNN) was put forward to predict the soil heavy metal content, this model uses wavelet neural network (WNN) as the basic prediction model, and at the same time proposes a parallel bird swarm algorithm (PBSA) to solve the parameter optimization problem of WNN, based on the bird swarm algorithm (BSA), the PBSA not only increases the gathering behavior of individual, but also adopts sine transformation based on fitness difference ratio to carry out the following behavior of beggars to improve the global optimization ability, besides that, the acceptance criterion is used to compare the fitness of individuals after updating to avoid falling into a local optimum. Soil heavy metal content data from Yinchuan city of Ningxia and six new urban areas in Wuhan, China are used to make prediction experiments respectively, through compare with support vector machine (SVM), radial basis function neural network (RBFNN), WNN and bird swarm algorithm optimizes wavelet neural network (BSA-WNN), the experimental results demonstrate that the predicted value of the CCNN is closer to the actual value and has better prediction performance.

Highlights

The heavy metals in the soil are usually not broken down by soil microorganisms, its long-term accumulation will pollute the environment and enter the human body along with the food chain, which directly endangering human health [1]
As researchers have more and more research on artificial neural network, it has been widely used in data prediction, there are many types of neural networks available for it, for example, back propagation neural network (BPNN) [6], fuzzy neural network (FNN) [7], radial basis function neural network (RBFNN) [8] and general regression neural network (GRNN) [9], etc., compared with traditional prediction methods, artificial neural networks have been proven to have higher prediction accuracy on nonlinear problems [10], [11]
On the basis of BSA, the gathering behavior, the sine transformation position update method based on fitness difference ratio and acceptance criterion are introduced, and a new parallel bird swarm algorithm (PBSA) is put forward, which improves the internal information utilization rate of the population while enhances the algorithm’s global search capability, apply PBSA to optimize the parameters of wavelet neural network (WNN) to ensure its prediction efficiency

Summary

Introduction

The heavy metals in the soil are usually not broken down by soil microorganisms, its long-term accumulation will pollute the environment and enter the human body along with the food chain, which directly endangering human health [1]. For the past several years, with the continuous development of industry, the heavy metal pollutants discharged to soil are increasing, how to reduce the content of heavy metal pollutants in soil has become one of the problems that need to be urgently solved [2]. Data, so predicting soil heavy metal content has become an effective way to solve this problem [3]. As researchers have more and more research on artificial neural network, it has been widely used in data prediction, there are many types of neural networks available for it, for example, back propagation neural network (BPNN) [6], fuzzy neural network (FNN) [7], radial basis function neural network (RBFNN) [8] and general regression neural network (GRNN) [9], etc., compared with traditional prediction methods, artificial neural networks have been proven to have higher prediction accuracy on nonlinear problems [10], [11].

Objectives

Methods

Conclusion