Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index
The frequent occurrence of drought, halting from unpredictable climate-induced weather patterns, presents significant challenges in breeding drought-tolerant maize to identify adaptable genotypes. The study explores the optimization of machine learning (ML) to predict both the grain yield and stress...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Sustainable Food Systems |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fsufs.2024.1334421/full |
| _version_ | 1797324135698792448 |
|---|---|
| author | Muhammad Azrai Muhammad Aqil N. N. Andayani Roy Efendi Suarni Suwardi Muhammad Jihad Bunyamin Zainuddin Salim Bahtiar Ahmad Muliadi Muhammad Yasin Muhammad Fitrah Irawan Hannan Rahman Amiruddin Syam |
| author_facet | Muhammad Azrai Muhammad Aqil N. N. Andayani Roy Efendi Suarni Suwardi Muhammad Jihad Bunyamin Zainuddin Salim Bahtiar Ahmad Muliadi Muhammad Yasin Muhammad Fitrah Irawan Hannan Rahman Amiruddin Syam |
| author_sort | Muhammad Azrai |
| collection | DOAJ |
| description | The frequent occurrence of drought, halting from unpredictable climate-induced weather patterns, presents significant challenges in breeding drought-tolerant maize to identify adaptable genotypes. The study explores the optimization of machine learning (ML) to predict both the grain yield and stress tolerance index (STI) of maize under normal and drought-induced stress. In total, 35 genotypes, comprising 31 hybrid candidates and four commercial varieties, were meticulously evaluated across three normal and drought-treated sites. Three popular ML were optimized using a genetic algorithm (GA) and ensemble ML to enhance data capture. Additionally, a Multi-trait Genotype-Ideotype Distance (MGIDI) was also involved to identify superior maize hybrids well-suited for drought conditions. The results highlight that the ensemble meta-models optimized by grid search exhibit robust performance with high accuracy across the testing datasets (R2 = 0.92 for grain yield and 0.82 for STI). The RF optimized by GA algorithm demonstrates slightly lower performance (R2 = 0.91 for grain yield and 0.79 for STI), surpassing the predictive performance of individual SVM-GA and KNN-GA models. Selection of the best-performing hybrids indicated that out of the six hybrids with the highest STI values, both the ensemble and MGIDI can accurately predict four hybrids, namely H06, H10, H13, and H35. Thus, combining ML with MGIDI enables researchers to discern traits for each genotype and holds promise for advancing the field of drought-tolerant maize breeding and expediting the development of resilient varieties. |
| first_indexed | 2024-03-08T05:45:50Z |
| format | Article |
| id | doaj.art-9239ddc8601d42aeaa55dddfea9b8daf |
| institution | Directory Open Access Journal |
| issn | 2571-581X |
| language | English |
| last_indexed | 2024-03-08T05:45:50Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Sustainable Food Systems |
| spelling | doaj.art-9239ddc8601d42aeaa55dddfea9b8daf2024-02-05T10:30:23ZengFrontiers Media S.A.Frontiers in Sustainable Food Systems2571-581X2024-02-01810.3389/fsufs.2024.13344211334421Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance indexMuhammad Azrai0Muhammad Aqil1N. N. Andayani2Roy Efendi3 Suarni4 Suwardi5Muhammad Jihad6Bunyamin Zainuddin7 Salim8 Bahtiar9Ahmad Muliadi10Muhammad Yasin11Muhammad Fitrah Irawan Hannan12 Rahman13Amiruddin Syam14Department of Agronomy, Faculty of Agriculture, Hasanuddin University, Makassar, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Behavioral and Circular Economics, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency Republic of Indonesia—BRIN, Bogor, IndonesiaResearch Center for Macroeconomics and Finance, National Research and Innovation Agency Republic of Indonesia—BRIN, Jakarta, IndonesiaThe frequent occurrence of drought, halting from unpredictable climate-induced weather patterns, presents significant challenges in breeding drought-tolerant maize to identify adaptable genotypes. The study explores the optimization of machine learning (ML) to predict both the grain yield and stress tolerance index (STI) of maize under normal and drought-induced stress. In total, 35 genotypes, comprising 31 hybrid candidates and four commercial varieties, were meticulously evaluated across three normal and drought-treated sites. Three popular ML were optimized using a genetic algorithm (GA) and ensemble ML to enhance data capture. Additionally, a Multi-trait Genotype-Ideotype Distance (MGIDI) was also involved to identify superior maize hybrids well-suited for drought conditions. The results highlight that the ensemble meta-models optimized by grid search exhibit robust performance with high accuracy across the testing datasets (R2 = 0.92 for grain yield and 0.82 for STI). The RF optimized by GA algorithm demonstrates slightly lower performance (R2 = 0.91 for grain yield and 0.79 for STI), surpassing the predictive performance of individual SVM-GA and KNN-GA models. Selection of the best-performing hybrids indicated that out of the six hybrids with the highest STI values, both the ensemble and MGIDI can accurately predict four hybrids, namely H06, H10, H13, and H35. Thus, combining ML with MGIDI enables researchers to discern traits for each genotype and holds promise for advancing the field of drought-tolerant maize breeding and expediting the development of resilient varieties.https://www.frontiersin.org/articles/10.3389/fsufs.2024.1334421/fulldroughtmaizemachine learningGAensemble |
| spellingShingle | Muhammad Azrai Muhammad Aqil N. N. Andayani Roy Efendi Suarni Suwardi Muhammad Jihad Bunyamin Zainuddin Salim Bahtiar Ahmad Muliadi Muhammad Yasin Muhammad Fitrah Irawan Hannan Rahman Amiruddin Syam Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index Frontiers in Sustainable Food Systems drought maize machine learning GA ensemble |
| title | Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| title_full | Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| title_fullStr | Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| title_full_unstemmed | Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| title_short | Optimizing ensembles machine learning, genetic algorithms, and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| title_sort | optimizing ensembles machine learning genetic algorithms and multivariate modeling for enhanced prediction of maize yield and stress tolerance index |
| topic | drought maize machine learning GA ensemble |
| url | https://www.frontiersin.org/articles/10.3389/fsufs.2024.1334421/full |
| work_keys_str_mv | AT muhammadazrai optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT muhammadaqil optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT nnandayani optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT royefendi optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT suarni optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT suwardi optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT muhammadjihad optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT bunyaminzainuddin optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT salim optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT bahtiar optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT ahmadmuliadi optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT muhammadyasin optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT muhammadfitrahirawanhannan optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT rahman optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex AT amiruddinsyam optimizingensemblesmachinelearninggeneticalgorithmsandmultivariatemodelingforenhancedpredictionofmaizeyieldandstresstoleranceindex |