Study on the Predictive Algorithm of Plant Restoration under Heavy Metals

Abstract

Heavy metal pollution of soil is becoming a more serious issue globally. Heavy metal contamination of the soil environment is inevitable as a result of the rapid and extensive growth of industry and agriculture, resulting in unfavorable environmental circumstances for both the flora and fauna. Traditional approaches for collecting field sampling with laboratory testing of soil heavy metals are restricted not only by their time and cost but also by their inability to gather sufficient information about the spatial distribution characteristics of heavy metals in soil over a vast area. The continuous development of the urban industrial processes leads to the degree of heavy metal pollution in urban gardens. For soil monitoring and cleanup, having quick and accurate access to heavy metal concentration data is very crucial and critical. In order to improve the restoration ability of garden heavy metal pollution, a new algorithm to predict plant restoration ability under the garden heavy metal pollution environment is put forward in this study. Firstly, we analyzed the composition of garden heavy metal pollution and the harm of garden heavy metal pollution. Secondly, we identified the restoration technology of garden heavy metal pollution to plants, determine the level of garden heavy metal pollution with the help of the land accumulation index method, and reflect the average pollution water level of garden heavy metal elements with the help of Numero comprehensive pollution heatstroke. On this basis, the plant repairability prediction model was constructed with the help of wavelet function, to predict the plant repairability under garden heavy metal pollution environment and to complete the prediction of plant repairability under garden heavy metal pollution environment. The experimental results show that the proposed method was better than the traditional approaches in terms of prediction accuracy and is also less time-consuming.