A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network

The phenotype (P) of a crop is determined by the genotype (G), environment (E), and genotype-by-environment (G × E) interaction, expressed as P = G + E + G × E. Thus, studying G × E interactions is essential for phenotypic research. Traditional methods of crop phenotypes and adaptability based on G...

Full description

Saved in:
Bibliographic Details
Main Authors: Longpeng Bai, Kaiyi Wang, Qiusi Zhang, Qi Zhang, Xiaofeng Wang, Shouhui Pan, Liyang Zhang, Xuliang He, Ran Li, Dongfeng Zhang, Yanyun Han
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/4/358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082249029976064
author Longpeng Bai
Kaiyi Wang
Qiusi Zhang
Qi Zhang
Xiaofeng Wang
Shouhui Pan
Liyang Zhang
Xuliang He
Ran Li
Dongfeng Zhang
Yanyun Han
author_facet Longpeng Bai
Kaiyi Wang
Qiusi Zhang
Qi Zhang
Xiaofeng Wang
Shouhui Pan
Liyang Zhang
Xuliang He
Ran Li
Dongfeng Zhang
Yanyun Han
author_sort Longpeng Bai
collection DOAJ
description The phenotype (P) of a crop is determined by the genotype (G), environment (E), and genotype-by-environment (G × E) interaction, expressed as P = G + E + G × E. Thus, studying G × E interactions is essential for phenotypic research. Traditional methods of crop phenotypes and adaptability based on G × E interaction analysis, based on large ecological regions, fail to account for year-to-year environmental changes and the blurring of region boundaries, leading to inaccurate insights into the relationship between genotypes and environmental factors. To address these issues, this study divided the research area into small ecological regions through the clustering of meteorological data, providing a more accurate framework for studying G × E interactions in maize. To ascertain the optimal method for ecological region delineation, the yield variance (SYV), the Davies–Bouldin Index (DBI), and the Silhouette Index (SI) were used to evaluate and compare the performance of the K-Means, Autoencoder K-Means (Ae-KM), and Deep K-Means Clustering Neural Network (DKMCNN) methodologies. The DKMCNN surpassed other methodologies and was selected for delineation. Based on this delineation result, the interactions between genotypes and the environment on maize were investigated and clarified using genome-wide association analysis (GWAS) and analysis of variance (ANOVA). Ultimately, through the analysis of maize field trial data from 2020 to 2021, we identified up to 108 single-nucleotide polymorphisms (SNPs) in 2020 and 153 SNPs in 2021 that exerted significant effects on maize yield and exhibited strong correlations with environmental factors, including temperature, cumulative precipitation, and cumulative sunshine duration.
format Article
id doaj-art-ef60e0a21ad845c4ba181dfa8bfd4946
institution DOAJ
issn 2077-0472
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-ef60e0a21ad845c4ba181dfa8bfd49462025-08-20T02:44:33ZengMDPI AGAgriculture2077-04722025-02-0115435810.3390/agriculture15040358A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural NetworkLongpeng Bai0Kaiyi Wang1Qiusi Zhang2Qi Zhang3Xiaofeng Wang4Shouhui Pan5Liyang Zhang6Xuliang He7Ran Li8Dongfeng Zhang9Yanyun Han10Key Laboratory of Fisheries Information, Ministry of Agriculture and Rural Affairs, Shanghai Ocean University, Hucheng Ring Road 999, Shanghai 201306, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaSDIC Seed Technology Co., Ltd., Beijing 100034, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaThe phenotype (P) of a crop is determined by the genotype (G), environment (E), and genotype-by-environment (G × E) interaction, expressed as P = G + E + G × E. Thus, studying G × E interactions is essential for phenotypic research. Traditional methods of crop phenotypes and adaptability based on G × E interaction analysis, based on large ecological regions, fail to account for year-to-year environmental changes and the blurring of region boundaries, leading to inaccurate insights into the relationship between genotypes and environmental factors. To address these issues, this study divided the research area into small ecological regions through the clustering of meteorological data, providing a more accurate framework for studying G × E interactions in maize. To ascertain the optimal method for ecological region delineation, the yield variance (SYV), the Davies–Bouldin Index (DBI), and the Silhouette Index (SI) were used to evaluate and compare the performance of the K-Means, Autoencoder K-Means (Ae-KM), and Deep K-Means Clustering Neural Network (DKMCNN) methodologies. The DKMCNN surpassed other methodologies and was selected for delineation. Based on this delineation result, the interactions between genotypes and the environment on maize were investigated and clarified using genome-wide association analysis (GWAS) and analysis of variance (ANOVA). Ultimately, through the analysis of maize field trial data from 2020 to 2021, we identified up to 108 single-nucleotide polymorphisms (SNPs) in 2020 and 153 SNPs in 2021 that exerted significant effects on maize yield and exhibited strong correlations with environmental factors, including temperature, cumulative precipitation, and cumulative sunshine duration.https://www.mdpi.com/2077-0472/15/4/358small ecological region delineationdeep k-means clustering neural networkgenotype by environment interaction
spellingShingle Longpeng Bai
Kaiyi Wang
Qiusi Zhang
Qi Zhang
Xiaofeng Wang
Shouhui Pan
Liyang Zhang
Xuliang He
Ran Li
Dongfeng Zhang
Yanyun Han
A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
Agriculture
small ecological region delineation
deep k-means clustering neural network
genotype by environment interaction
title A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
title_full A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
title_fullStr A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
title_full_unstemmed A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
title_short A Study of Maize Genotype–Environment Interaction Based on Deep K-Means Clustering Neural Network
title_sort study of maize genotype environment interaction based on deep k means clustering neural network
topic small ecological region delineation
deep k-means clustering neural network
genotype by environment interaction
url https://www.mdpi.com/2077-0472/15/4/358
work_keys_str_mv AT longpengbai astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT kaiyiwang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT qiusizhang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT qizhang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT xiaofengwang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT shouhuipan astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT liyangzhang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT xulianghe astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT ranli astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT dongfengzhang astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT yanyunhan astudyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT longpengbai studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT kaiyiwang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT qiusizhang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT qizhang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT xiaofengwang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT shouhuipan studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT liyangzhang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT xulianghe studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT ranli studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT dongfengzhang studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork
AT yanyunhan studyofmaizegenotypeenvironmentinteractionbasedondeepkmeansclusteringneuralnetwork