Title: Prediction of the environmental quality of a central province based on GRA-BO-LSSVM

Authors: Fang He; Shuliang Cheng; Tianyu Zhao; Jing Zhu

Addresses: School of Urban Construction, Wuhan University of Science and Technology, Wuhan, China ' School of Urban Construction, Wuhan University of Science and Technology, Wuhan, China ' School of Urban Construction, Wuhan University of Science and Technology, Wuhan, China ' Wuhan Ecological Environmental Monitoring Centre, Department of Ecology and Environment of Hubei Province, Wuhan, China

Abstract: An ecological environment quality prediction model based on the combination of grey relational analysis and Bayesian optimised least squares support vector machine is presented in this study. The key indicators affecting environmental quality were identified through grey relational analysis to reduce the input variables in the model. The Bayesian evidence framework was used to optimise least squares support vector machine algorithm for establishing an environmental quality prediction model. The results indicated that the accuracy of the GRA-BO-LSSVM prediction model for water, air, and sound environmental quality was 99.61%, 99.81%, and 99.91%, respectively. This model demonstrated strong applicability to environmental quality. It was used to forecast environmental quality from 2023 to 2027. The quality of water, air, and sound environments has been further improved, leading to a consistent enhancement of overall environmental quality.

Keywords: environmental quality; grey relational analysis; Bayesian evidence framework; least square support vector machine.

DOI: 10.1504/IJWMC.2025.146640

International Journal of Wireless and Mobile Computing, 2025 Vol.28 No.4, pp.337 - 352

Received: 05 Jun 2024
Accepted: 06 Sep 2024
Published online: 10 Jun 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article