Abstract
Early detection of agricultural diseases is important for reducing crop damage, particularly in rural or remote regions. This research work provides an explainable Convolutional Neural Network (CNN) technique for agricultural disease alert system that uses Sentinel-2 multispectral data, NDVI and Red Edge NDVI (NDRE) fusion to produce continuous notifications. It increases spectral learning features like stressed plant signals into the raw red, near-infrared and red edge bands. It also increases the capacity to recognize healthy and unhealthy crops. Grad-CAM's module help farmers and agronomists to evaluate model results by recognizing the primary spectral data related to each prediction increases transparency and trust. A client-side storage system allows monitoring the fields and disease analysis queries offline, that can be updated with the server when a connection is available. The evaluations using merged sentinel-2 data show that combining NDVI and NDRE increases the accuracy of detection and produces feature activation maps makes its efficient for early stress detection. This technology was created for adaptive communication with agricultural systems and it provides accurate crop health signals using satellite images.
References
- H. Wang, C. Ruan, J. Zhao, Y. Wang, Y. Li, Y. Dong, and L. Huang, “Utilizing Interpretable Machine Learning Algorithms and Multiple Features from Multi-Temporal Sentinel-2 Imagery for Predicting Wheat Fusarium Head Blight,” Artificial Intelligence in Agriculture, 2025.
- R. Tufail, P. Tassinari, and D. Torreggiani, “Deep Learning Applications for Crop Mapping Using Multi-Temporal Sentinel-2 Data and Red-Edge Vegetation Indices: Integrating Convolutional and Recurrent Neural Networks,” Remote Sensing, vol. 17, no. 18, 2025, 3207.
- J. Guo, R. Kang, T. Xu, C. Deng, L. Zhang, S. Yang, and H. Kaufmann, “Detection of Pine Wilt Disease Using a VIS–NIR Slope-Based Index from Sentinel-2 Data,” Forests, vol. 16, no. 7, 2025, 1170.
- J. Judith, R. Tamilselvi, M. P. Beham, S. Lakshmi, A. Panthakkan, S. A. Mansoori, and H. A. Ahmad, “Remote Sensing Based Crop Health Classification Using NDVI and Fully Connected Neural Networks,” arXiv preprint arXiv:2504.10522, 2025.
- B. Bade, U. Schulthess, G. Blasch, S. R. Sherpa, H. L. Shrestha, D. Bajimaya, and S. Nepali, “Temporal Sentinel-2 Imagery for Wheat Mapping and Monitoring: Analyzing Phenological Stages with Machine Learning to Improve Mapping Precision for Small Farms,” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2025, 143–149.
- A. I. Atanasov, A. Z. Atanasov, and B. I. Evstatiev, “Application of NDVI for Early Detection of Yellow Rust (Puccinia Striiformis),” AgriEngineering, vol. 7, no. 5, 2025, 160.
- A. Descals, K. Torres, A. Verger, and J. Peñuelas, “Evaluating Sentinel-2 for Monitoring Drought-Induced Crop Failure in Winter Cereals,” Remote Sensing, vol. 17, no. 2, 2025, 340.
- B. N. Azubuike, A. Chlingaryan, M. Correa-Luna, C. E. Clark, and S. C. Garcia, “Data Augmentation and Interpolation Improves Machine Learning-Based Pasture Biomass Estimation from Sentinel-2 Imagery,” Remote Sensing, vol. 17, no. 23,2025, 3787.
- S. S. Sharma, J. Mukherjee, and F. Dell’Acqua, “Leveraging Sentinel-2 data and Machine Learning for Drought Detection in India: Ground Truth Construction and A Case Study,” Remote Sensing, vol. 17, no. 18, 2025, 3159.
- Z. M. Mobarakeh, S. Pourmanafi, and M. Ahmadi, “Employing Sentinel-2 Time-Series and Noisy Data Quality Control to Enhance Crop Classification in Arid Environments: A Comparison of Machine Learning and Deep Learning Methods,” International Journal of Applied Earth Observation and Geoinformation, vol. 142, 2025, 104678.
- S. Mukherjee, S. K. Shah, T. P. Singh, and V. Kumbhar, “Classification and Phenological Stage Monitoring of Grape Crops Using Sentinel-1 And Sentinel-2 Time Series and Deep Learning Techniques,” 2025.
- T. C. Parreiras, C. D. O. Santos, É. L. Bolfe, E. E. Sano, V. B. S. Leandro, G. Bayma, and D. Morton, “Dense Time Series of Harmonized Landsat Sentinel-2 and Ensemble Machine Learning to Map Coffee Production Stages,” Remote Sensing, vol. 17, no. 18, 2025, 3168.
- R. Nandhini and A. K. Prakash, “Harnessing Satellite Data for Sustainable Agriculture: An Overview of Remote Sensing in Crop Health Monitoring,” 2024.
- M. M. Rahman, A. Robson, and T. Bekker, “Machine Learning Approaches for Assessing Avocado Alternate Bearing Using Sentinel-2 And Climate Variables: A Case Study in Limpopo, South Africa,” 2025.
- T. Dzurume, R. Darvishzadeh, T. Dube, T. A. Babu, M. Billah, S. N. Alam, and A. Nelson, “Synergistic Use of Sentinel-1 and Sentinel-2 Data for Fall Armyworm Infestation Detection and Mapping in Maize Croplands,” International Journal of Remote Sensing, vol. 46, no. 19, 2025, 7044–7076.
- U. Mittal, P. Sharma, and R. Gupta, “Plant Disease Detection and Classification: A Systematic Review,” Computers and Electronics in Agriculture, vol. 206, 2023, 107645.
- A. T. Khan, M. Rafiq, and S. Ahmed, “Plant Disease Detection Models for Edge Computing Devices: A Lightweight Approach,” Frontiers in Plant Science, vol. 14, 2023, 1147281.
- R. Patel, K. Mehta, and D. Sharma, “Interpretable Convolutional Neural Networks for Maize Disease Detection Using Grad-CAM Visualizations,” Computers in Biology and Medicine, vol. 153, 2023, 106486.