Sustainable AI for plant disease classification using ResNet18 in few-shot learning
Addressing the critical challenge of reduced crop production caused by plant diseases is essential to safeguard agricultural yield and quality. Conventional methods like visual inspection and laboratory testing are both time-consuming and costly. Although Modern AI-based deep learning techniques are...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005625000220 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849422208532742144 |
|---|---|
| author | Fareeha Naveed Adven Masih Jabar Mahmood Moeez Ahmed Aitizaz Ali Aysha Saddiqa Mohamed Shabbir Hamza Abdulnabi Ebenezer Agbozo |
| author_facet | Fareeha Naveed Adven Masih Jabar Mahmood Moeez Ahmed Aitizaz Ali Aysha Saddiqa Mohamed Shabbir Hamza Abdulnabi Ebenezer Agbozo |
| author_sort | Fareeha Naveed |
| collection | DOAJ |
| description | Addressing the critical challenge of reduced crop production caused by plant diseases is essential to safeguard agricultural yield and quality. Conventional methods like visual inspection and laboratory testing are both time-consuming and costly. Although Modern AI-based deep learning techniques are promising, their potential in fields such as plant disease identification often remains unexplored due to the requirement of large and expert-labeled data. To mitigate these challenges, it is imperative to explore sustainable approaches that require minimal data while maintaining high accuracy in classification tasks. This research proposes a novel few-shot learning (FSL) framework employing a minimum sample size of 1 image and a maximum of 10 images per class for the accurate classification of plant diseases. The architecture incorporates a pre-training phase based on transfer learning as a feature extractor, followed by meta-learning using Prototypical Networks (ProtoNets) for class prototype computation and distance-based classification. The study evaluates the effectiveness of the proposed approach on the PlantVillage as well as rice disease datasets, performing comparative analyses among different transfer learning models such as ResNet18, ResNet50, and Vision Transformers in combination with Prototypical Networks under various N-way classification tasks (3-way, 5-way, and 10-way) and support sample (K-shot) settings (K =1, K =5, K =10). The experimental findings indicate that the proposed combination of pretraining through ResNet18 with Prototypical Networks achieved an impressive accuracy of 93% and 75% on PlantVillage. The proposed model’s performance was further evaluated on rice disease data where it achieves the average accuracy of 75%. Specifically, the proposed model demonstrated the ability to classify 10 distinct plant diseases with high accuracy when provided with a suitable sample size per class. The proposed framework offers a substantial advancement in sustainable AI for plant disease recognition by enhancing the model generalization, enabling accurate classification across numerous classes with minimal sample size, and addressing data scarcity in AI-driven agricultural solutions. |
| format | Article |
| id | doaj-art-3e544aab45cd40ec9679a3d7ff94caeb |
| institution | Kabale University |
| issn | 2590-0056 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj-art-3e544aab45cd40ec9679a3d7ff94caeb2025-08-20T03:31:11ZengElsevierArray2590-00562025-07-012610039510.1016/j.array.2025.100395Sustainable AI for plant disease classification using ResNet18 in few-shot learningFareeha Naveed0Adven Masih1Jabar Mahmood2Moeez Ahmed3Aitizaz Ali4Aysha Saddiqa5Mohamed Shabbir Hamza Abdulnabi6Ebenezer Agbozo7Faculty of Computing and Information Technology, University of Sialkot, Daska Road, Sialkot 51040, Punjab, PakistanFaculty of Computing and Information Technology, University of Sialkot, Daska Road, Sialkot 51040, Punjab, Pakistan; Corresponding authors.State Key Laboratory of Blockchain and Data Security, School of Cyber Science and Technology, and College of Computer Science and Technology, Zhejiang University, Hangzhou 310007, Zhejiang, ChinaFaculty of Computing and Information Technology, University of Sialkot, Daska Road, Sialkot 51040, Punjab, PakistanSchool of Technology (SOT), Asia Pacific University of Technology and Innovation, 57000, Kuala Lumpur, MalaysiaFaculty of Computing and Information Technology, University of Sialkot, Daska Road, Sialkot 51040, Punjab, PakistanSchool of Technology (SOT), Asia Pacific University of Technology and Innovation, 57000, Kuala Lumpur, Malaysia; Corresponding authors.Department of Big Data Analytics and Video Analysis Methods, Ural Federal University, 620002, RussiaAddressing the critical challenge of reduced crop production caused by plant diseases is essential to safeguard agricultural yield and quality. Conventional methods like visual inspection and laboratory testing are both time-consuming and costly. Although Modern AI-based deep learning techniques are promising, their potential in fields such as plant disease identification often remains unexplored due to the requirement of large and expert-labeled data. To mitigate these challenges, it is imperative to explore sustainable approaches that require minimal data while maintaining high accuracy in classification tasks. This research proposes a novel few-shot learning (FSL) framework employing a minimum sample size of 1 image and a maximum of 10 images per class for the accurate classification of plant diseases. The architecture incorporates a pre-training phase based on transfer learning as a feature extractor, followed by meta-learning using Prototypical Networks (ProtoNets) for class prototype computation and distance-based classification. The study evaluates the effectiveness of the proposed approach on the PlantVillage as well as rice disease datasets, performing comparative analyses among different transfer learning models such as ResNet18, ResNet50, and Vision Transformers in combination with Prototypical Networks under various N-way classification tasks (3-way, 5-way, and 10-way) and support sample (K-shot) settings (K =1, K =5, K =10). The experimental findings indicate that the proposed combination of pretraining through ResNet18 with Prototypical Networks achieved an impressive accuracy of 93% and 75% on PlantVillage. The proposed model’s performance was further evaluated on rice disease data where it achieves the average accuracy of 75%. Specifically, the proposed model demonstrated the ability to classify 10 distinct plant diseases with high accuracy when provided with a suitable sample size per class. The proposed framework offers a substantial advancement in sustainable AI for plant disease recognition by enhancing the model generalization, enabling accurate classification across numerous classes with minimal sample size, and addressing data scarcity in AI-driven agricultural solutions.http://www.sciencedirect.com/science/article/pii/S2590005625000220AI-driven disease classificationFew-shot learningPrototypical networksResNet18Sustainable AITransfer learning |
| spellingShingle | Fareeha Naveed Adven Masih Jabar Mahmood Moeez Ahmed Aitizaz Ali Aysha Saddiqa Mohamed Shabbir Hamza Abdulnabi Ebenezer Agbozo Sustainable AI for plant disease classification using ResNet18 in few-shot learning Array AI-driven disease classification Few-shot learning Prototypical networks ResNet18 Sustainable AI Transfer learning |
| title | Sustainable AI for plant disease classification using ResNet18 in few-shot learning |
| title_full | Sustainable AI for plant disease classification using ResNet18 in few-shot learning |
| title_fullStr | Sustainable AI for plant disease classification using ResNet18 in few-shot learning |
| title_full_unstemmed | Sustainable AI for plant disease classification using ResNet18 in few-shot learning |
| title_short | Sustainable AI for plant disease classification using ResNet18 in few-shot learning |
| title_sort | sustainable ai for plant disease classification using resnet18 in few shot learning |
| topic | AI-driven disease classification Few-shot learning Prototypical networks ResNet18 Sustainable AI Transfer learning |
| url | http://www.sciencedirect.com/science/article/pii/S2590005625000220 |
| work_keys_str_mv | AT fareehanaveed sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT advenmasih sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT jabarmahmood sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT moeezahmed sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT aitizazali sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT ayshasaddiqa sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT mohamedshabbirhamzaabdulnabi sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning AT ebenezeragbozo sustainableaiforplantdiseaseclassificationusingresnet18infewshotlearning |