Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging
Rice, as a staple crop globally, requires proactive and accurate disease detection to ensure sustainable production. This study introduces a novel hybrid Deep Learning approach integrating thermal imaging and model hybridization for early and precise detection of rice leaf diseases. A dataset of 5,9...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525000486 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087345821646848 |
|---|---|
| author | Jagamohan Padhi Kunal Mishra Ashoka Kumar Ratha Santi Kumari Behera Prabira Kumar Sethy Aziz Nanthaamornphong |
| author_facet | Jagamohan Padhi Kunal Mishra Ashoka Kumar Ratha Santi Kumari Behera Prabira Kumar Sethy Aziz Nanthaamornphong |
| author_sort | Jagamohan Padhi |
| collection | DOAJ |
| description | Rice, as a staple crop globally, requires proactive and accurate disease detection to ensure sustainable production. This study introduces a novel hybrid Deep Learning approach integrating thermal imaging and model hybridization for early and precise detection of rice leaf diseases. A dataset of 5,932 self-generated rice leaf images was augmented with simulated thermal images to capture subtle temperature variations indicative of early stress responses prior to visible symptoms. This novel use of thermal imaging enhances disease diagnosis efficiency and practicality. Eighteen Convolutional Neural Network (CNN) models were evaluated using transfer learning, with statistical analysis via Duncan's multiple range test (DMRT) identifying Darknet53 as the best-performing model, achieving an accuracy of 95.79 %, sensitivity of 95.79 %, specificity of 95.93 %, and an F1 score of 0.96. To further improve performance, Darknet53 was hybridized by replacing its dense layer with a Support Vector Machine (SVM), resulting in significant enhancements. The hybrid model achieved 99.43 % accuracy, 99.43 % sensitivity, 99.81 % specificity, and an F1 score of 0.99. These results highlight the model's potential for real-time deployment in agricultural applications, providing an efficient and reliable solution for small-scale farmers. This research underscores the value of integrating thermal imaging with Deep Learning for advancing crop disease management and offers a framework for addressing other crop pathologies. |
| format | Article |
| id | doaj-art-485eea76e6f24acdb480c5b5d17227b4 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-485eea76e6f24acdb480c5b5d17227b42025-02-06T05:13:03ZengElsevierSmart Agricultural Technology2772-37552025-03-0110100814Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imagingJagamohan Padhi0Kunal Mishra1Ashoka Kumar Ratha2Santi Kumari Behera3Prabira Kumar Sethy4Aziz Nanthaamornphong5Department of Electronics, Sambalpur University, Sambalpur, Odisha, 768 019, IndiaDepartment of Computer Science and Engineering, SUIIT, Sambalpur University, Odisha, 768019, IndiaDepartment of Electronics, Sambalpur University, Sambalpur, Odisha, 768 019, IndiaDepartment of Computer Science and Engineering, VSSUT Burla, Odisha 768019, IndiaCorresponding authors.; Department of Electronics, Sambalpur University, Sambalpur, Odisha, 768 019, IndiaCorresponding authors.; College of Computing, Prince of Songkla University, Phuket campus, 83120, ThailandRice, as a staple crop globally, requires proactive and accurate disease detection to ensure sustainable production. This study introduces a novel hybrid Deep Learning approach integrating thermal imaging and model hybridization for early and precise detection of rice leaf diseases. A dataset of 5,932 self-generated rice leaf images was augmented with simulated thermal images to capture subtle temperature variations indicative of early stress responses prior to visible symptoms. This novel use of thermal imaging enhances disease diagnosis efficiency and practicality. Eighteen Convolutional Neural Network (CNN) models were evaluated using transfer learning, with statistical analysis via Duncan's multiple range test (DMRT) identifying Darknet53 as the best-performing model, achieving an accuracy of 95.79 %, sensitivity of 95.79 %, specificity of 95.93 %, and an F1 score of 0.96. To further improve performance, Darknet53 was hybridized by replacing its dense layer with a Support Vector Machine (SVM), resulting in significant enhancements. The hybrid model achieved 99.43 % accuracy, 99.43 % sensitivity, 99.81 % specificity, and an F1 score of 0.99. These results highlight the model's potential for real-time deployment in agricultural applications, providing an efficient and reliable solution for small-scale farmers. This research underscores the value of integrating thermal imaging with Deep Learning for advancing crop disease management and offers a framework for addressing other crop pathologies.http://www.sciencedirect.com/science/article/pii/S2772375525000486Rice leaf diseaseDeep learningCNNCrop yieldAgricultureFood security |
| spellingShingle | Jagamohan Padhi Kunal Mishra Ashoka Kumar Ratha Santi Kumari Behera Prabira Kumar Sethy Aziz Nanthaamornphong Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging Smart Agricultural Technology Rice leaf disease Deep learning CNN Crop yield Agriculture Food security |
| title | Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging |
| title_full | Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging |
| title_fullStr | Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging |
| title_full_unstemmed | Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging |
| title_short | Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging |
| title_sort | enhancing paddy leaf disease diagnosis a hybrid cnn model using simulated thermal imaging |
| topic | Rice leaf disease Deep learning CNN Crop yield Agriculture Food security |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525000486 |
| work_keys_str_mv | AT jagamohanpadhi enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging AT kunalmishra enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging AT ashokakumarratha enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging AT santikumaribehera enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging AT prabirakumarsethy enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging AT aziznanthaamornphong enhancingpaddyleafdiseasediagnosisahybridcnnmodelusingsimulatedthermalimaging |