外文摘要：PurposeWith the continuous advancement of modern agriculture and urbanization, soil quality assessment has been considered an important guarantee for sustainable agricultural development. Despite the availability of numerous methods for assessing soil quality, little emphasis has been paid to comprehensive studies on soil quality in greenhouse agriculture. This study aims to construct a comprehensive evaluation model of greenhouse agricultural soil quality, including soil nutrition and heavy metal pollution, to better assess greenhouse soil quality.Materials and methodsIn this study, the concentrations of eight heavy metals, five soil nutrients, and nine soil-available microelements in 300 greenhouses were measured. Genetic algorithm-backpropagation (GA-BP) neural networks and backpropagation (BP) neural networks were used to construct a comprehensive soil quality evaluation model, and the soil quality of the greenhouse in the study area was evaluated based on soil nutrients and heavy metal pollution.ResultsThe results showed that the prediction accuracy of both models exceeded 85%. However, constructed utilizing the genetic algorithm-backpropagation (GA-BP), the evaluation model can be more effective in assessing soil quality, with an accuracy of 96.1%. In this study, the soil quality was categorized into eight levels: IA, IB, IC, IIA, IIB, IIC, IIIA, and IIIB. 80.6% of the samples were IIA and IIB, suggesting that the soil quality of greenhouse planting sheds in this research area was poor, with severe heavy metal pollution, although soil nutrients were relatively sufficient.ConclusionsThis study holds significance for assessing soil quality in greenhouse agriculture and improving agricultural scientific management.
外文关键词：Soil nutrients;Backpropagation neural network;Heavy metals;Genetic algorithm-backpropagation neural network
作者：Lan, Yubin;Sun, Yuemei;Zhang, Jingzhi;Bai, Jingbo;Xu, Yanxiang;Chen, Yunlin;Han, Xin
作者单位：Shandong Univ Technol;Shandong Siyuan Agr Dev Co Ltd Zibotd;Shandong Prov Engn Technol Res Ctr Agr Aviat Intel
期刊名称：JOURNAL OF SOILS AND SEDIMENTS
期刊影响因子：0.0
出版年份：2024
出版刊次：24(3)
原文传递申请：江苏省科技资源（工程技术文献）统筹服务平台