Deep learning based stacking ensembles for tropical sorghum classification
Subtle morphological differences among sorghum varieties make varietal identification difficult in breeding and seed production, increasing the risk of contamination, reduced grain quality, and challenges in maintaining seed purity for farmers. This research integrates deep learning with a stacking...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Journal of Agriculture and Food Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666154325003023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850226071632347136 |
|---|---|
| author | Muhammad Aqil Muhammad Azrai Roy Efendi Nining Nurini Andayani Suwardi Bunyamin Zainuddin Suarni Herawati Andi Irma Damayanti Muhammad Jihad Syafruddin Ramlah Arief Paesal Yustisia Rahman |
| author_facet | Muhammad Aqil Muhammad Azrai Roy Efendi Nining Nurini Andayani Suwardi Bunyamin Zainuddin Suarni Herawati Andi Irma Damayanti Muhammad Jihad Syafruddin Ramlah Arief Paesal Yustisia Rahman |
| author_sort | Muhammad Aqil |
| collection | DOAJ |
| description | Subtle morphological differences among sorghum varieties make varietal identification difficult in breeding and seed production, increasing the risk of contamination, reduced grain quality, and challenges in maintaining seed purity for farmers. This research integrates deep learning with a stacking ensemble approach to develop a rapid and accurate method for sorghum seed classification, supporting breeding programs, seed production, and on-farm varietal identification. The research was conducted at two experimental sites: Bajeng in Gowa and ICERI in Maros Regency, South Sulawesi. Five popular sorghum varieties (Numbu, Kawali, Super 1, Suri 3 Agritan, and Super 4) were classified using CNN models (VGG16, SqueezeNet, DenseNet-121 and ResNet-50), while a stacking ensemble was constructed with support vector machine, and k-nearest neighbors, using logistic regression as the meta-model. Grid and Bayesian search optimizations were applied for parameter tuning, and model performance was assessed using an 80/20 train-validation split and tenfold cross-validation. The results show that the SqueezeNet-LR stacking model via Bayesian hyper parameters search achieved the highest accuracy of 0.978, highlighting its effectiveness, particularly with high-dimensional features. In comparison, the VGG16-KNN model exhibited the lowest accuracy at 0.924, while ResNet-50 and DenseNet-121 showed slightly lower but comparable performance. Multi-dimensional scaling (MDS) analysis of misclassifications indicated that errors were concentrated among the Kawali, Numbu, and Suri 3 Agritan varieties. Overall, the SqueezeNet-LR stacking model outperformed the others, demonstrating its superiority in seed classification. Furthermore, the practical application of these findings could extend to mobile platforms through integration with Android Studio, Flutter, and TensorFlow Lite, for in-field varietal identification and future research. Overall, this framework is essential for breeding programs and in-field varietal identification, especially to prevent varietal contamination during seed production. |
| format | Article |
| id | doaj-art-c5b5a52d9b9640cfbc97250deaccc385 |
| institution | OA Journals |
| issn | 2666-1543 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Agriculture and Food Research |
| spelling | doaj-art-c5b5a52d9b9640cfbc97250deaccc3852025-08-20T02:05:10ZengElsevierJournal of Agriculture and Food Research2666-15432025-06-012110193110.1016/j.jafr.2025.101931Deep learning based stacking ensembles for tropical sorghum classificationMuhammad Aqil0Muhammad Azrai1Roy Efendi2Nining Nurini Andayani3 Suwardi4Bunyamin Zainuddin5 Suarni6 Herawati7Andi Irma Damayanti8Muhammad Jihad9 Syafruddin10Ramlah Arief11 Paesal12 Yustisia13 Rahman14Research Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaDepartment of Agronomy, Faculty of Agriculture, Hasanuddin University, Jl. Perintis Kemerdekaan Km. 10 Kampus Unhas, Makassar, 90245, Indonesia; Corresponding author. Department of Agronomy, Faculty of Agriculture, Hasanuddin University, Indonesia.Research Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaResearch Center for Food Crops, National Research and Innovation Agency (BRIN), Republic of Indonesia. Jl. Raya Bogor Km. 46 Cibinong, Bogor, 16911, IndonesiaSubtle morphological differences among sorghum varieties make varietal identification difficult in breeding and seed production, increasing the risk of contamination, reduced grain quality, and challenges in maintaining seed purity for farmers. This research integrates deep learning with a stacking ensemble approach to develop a rapid and accurate method for sorghum seed classification, supporting breeding programs, seed production, and on-farm varietal identification. The research was conducted at two experimental sites: Bajeng in Gowa and ICERI in Maros Regency, South Sulawesi. Five popular sorghum varieties (Numbu, Kawali, Super 1, Suri 3 Agritan, and Super 4) were classified using CNN models (VGG16, SqueezeNet, DenseNet-121 and ResNet-50), while a stacking ensemble was constructed with support vector machine, and k-nearest neighbors, using logistic regression as the meta-model. Grid and Bayesian search optimizations were applied for parameter tuning, and model performance was assessed using an 80/20 train-validation split and tenfold cross-validation. The results show that the SqueezeNet-LR stacking model via Bayesian hyper parameters search achieved the highest accuracy of 0.978, highlighting its effectiveness, particularly with high-dimensional features. In comparison, the VGG16-KNN model exhibited the lowest accuracy at 0.924, while ResNet-50 and DenseNet-121 showed slightly lower but comparable performance. Multi-dimensional scaling (MDS) analysis of misclassifications indicated that errors were concentrated among the Kawali, Numbu, and Suri 3 Agritan varieties. Overall, the SqueezeNet-LR stacking model outperformed the others, demonstrating its superiority in seed classification. Furthermore, the practical application of these findings could extend to mobile platforms through integration with Android Studio, Flutter, and TensorFlow Lite, for in-field varietal identification and future research. Overall, this framework is essential for breeding programs and in-field varietal identification, especially to prevent varietal contamination during seed production.http://www.sciencedirect.com/science/article/pii/S2666154325003023Machine learningVGG-NetDenseNet-121Squeeze-netResNet-50Sorghum |
| spellingShingle | Muhammad Aqil Muhammad Azrai Roy Efendi Nining Nurini Andayani Suwardi Bunyamin Zainuddin Suarni Herawati Andi Irma Damayanti Muhammad Jihad Syafruddin Ramlah Arief Paesal Yustisia Rahman Deep learning based stacking ensembles for tropical sorghum classification Journal of Agriculture and Food Research Machine learning VGG-Net DenseNet-121 Squeeze-net ResNet-50 Sorghum |
| title | Deep learning based stacking ensembles for tropical sorghum classification |
| title_full | Deep learning based stacking ensembles for tropical sorghum classification |
| title_fullStr | Deep learning based stacking ensembles for tropical sorghum classification |
| title_full_unstemmed | Deep learning based stacking ensembles for tropical sorghum classification |
| title_short | Deep learning based stacking ensembles for tropical sorghum classification |
| title_sort | deep learning based stacking ensembles for tropical sorghum classification |
| topic | Machine learning VGG-Net DenseNet-121 Squeeze-net ResNet-50 Sorghum |
| url | http://www.sciencedirect.com/science/article/pii/S2666154325003023 |
| work_keys_str_mv | AT muhammadaqil deeplearningbasedstackingensemblesfortropicalsorghumclassification AT muhammadazrai deeplearningbasedstackingensemblesfortropicalsorghumclassification AT royefendi deeplearningbasedstackingensemblesfortropicalsorghumclassification AT niningnuriniandayani deeplearningbasedstackingensemblesfortropicalsorghumclassification AT suwardi deeplearningbasedstackingensemblesfortropicalsorghumclassification AT bunyaminzainuddin deeplearningbasedstackingensemblesfortropicalsorghumclassification AT suarni deeplearningbasedstackingensemblesfortropicalsorghumclassification AT herawati deeplearningbasedstackingensemblesfortropicalsorghumclassification AT andiirmadamayanti deeplearningbasedstackingensemblesfortropicalsorghumclassification AT muhammadjihad deeplearningbasedstackingensemblesfortropicalsorghumclassification AT syafruddin deeplearningbasedstackingensemblesfortropicalsorghumclassification AT ramlaharief deeplearningbasedstackingensemblesfortropicalsorghumclassification AT paesal deeplearningbasedstackingensemblesfortropicalsorghumclassification AT yustisia deeplearningbasedstackingensemblesfortropicalsorghumclassification AT rahman deeplearningbasedstackingensemblesfortropicalsorghumclassification |