Prediction Model of Soil Heavy Metal Content Based on Particle Swarm Algorithm Optimized Neural Network

Abstract

In 2014, the relevant research data from the Ministry of Environmental Protection and the Ministry of Land and Resources showed that the total exceedance rate of soil heavy metal pollution in China had reached 16.1%, and in the construction of ecological civilization in the 13th Five-Year Plan, China has made the prevention and control of soil heavy metal pollution as the focus of prevention and control. Therefore, in this paper, four neural optimization network models, that is, radial basis neural network (RBFNN), generalized regression neural network (GRNN), wavelet neural network (WNN), and fuzzy neural network (FNN), are simulated and created to measure and correlate the soil heavy metal content in a city in northwest China and a city in central China from the actual situation in China. The simulations were conducted. Finally, by analyzing the comparison of predicted and true values of these four models on the test data of two sets of experimental data, the distribution of predicted differences to true values, and the calculation results of three error indicators, we found that WNN has the best prediction performance when using RBFNN, GRNN, WNN, and FNN for soil heavy metal content prediction.

Prediction of Total Petroleum Hydrocarbons and Heavy Metals in Acid Tars Using Machine Learning

“…This library can automatically test and tune 19 machine-learning algorithms that come with it. Other algorithms can be tried, but the authors considered the default number of algorithms to be enough and did not use this option [43,[46][47][48][49][50][51][52].…”