Comprehensive assessment of soil quality in greenhouse agriculture based on genetic algorithm and neural network

Purpose With 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 compr...

Full description

Saved in:
Bibliographic Details
Published in:Journal of soils and sediments Vol. 24; no. 3; pp. 1302 - 1315
Main Authors: Sun, Yuemei, Zhang, Jingzhi, Bai, Jingbo, Xu, Yanxiang, Chen, Yunlin, Lan, Yubin, Han, Xin
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2024
Springer Nature B.V
Subjects:
Accuracy
Agricultural development
Agricultural land
agricultural soils
Agriculture
Algorithms
Availability
Back propagation
Back propagation networks
Earth and Environmental Science
Environment
Environmental Physics
Farm buildings
Genetic algorithms
greenhouse soils
Greenhouses
Heavy metals
Metal concentrations
Metals
Model accuracy
Neural networks
Nutrients
Nutrition
pollution
prediction
Quality assessment
Quality control
Sec 5 • Soil and Landscape Ecology • Research Article
Soil
Soil nutrients
Soil pollution
Soil quality
Soil Science & Conservation
Soils
Sustainable agriculture
Sustainable development
Trace elements
Urbanization
Soil nutrients
Backpropagation neural network
Heavy metals
Genetic algorithm–backpropagation neural network
ISSN:1439-0108, 1614-7480
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose With 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 methods In 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. Results The 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. Conclusions This study holds significance for assessing soil quality in greenhouse agriculture and improving agricultural scientific management.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1439-0108
1614-7480
DOI:10.1007/s11368-023-03706-5