In order to advance the research further, we aim to do the following: (a) implement the system into an application and test it on field photographs; (b) gather more diverse datasets (different crops a

The gap

Consensus across the literature

Supporting evidence — 4 representative gaps

• Zero Hunger - Crop Disease Detection using Computer Vision (2026) · doi

  In order to advance the research further, we aim to do the following: (a) implement the system into an application and test it on field photographs; (b) gather more diverse datasets (different crops and different field settings); (c) try more complicated architectures such as attention models; and (d) use sensor network data. These efforts will make AI applications for plant pathology readily available to farmers.

  Keywords: field different order advance further following implement system application test photographs gather diverse datasets crops
• FERTICAST – Data-Driven Fertilizer Optimization System Embedded with Rainfall Prediction (2026) · doi

  Ferticast can be further improved by integrating IoT sensors to collect real-time soil data such as moisture and nutrient levels, which would increase prediction accuracy. Developing a mobile application can enhance accessibility for farmers. The model can also be strengthened using larger and region-specific datasets and advanced techniques like deep learning. Additionally, incorporating satellite data and real- time alerts can make the system more accurate and practical for precision agriculture.

  Keywords: real time ferticast further improved integrating sensors collect soil moisture nutrient levels increase prediction accuracy
• An image based case based reasoning system to identify maize crop attacks and recommend treatments (2026) · doi

  5.1 Conclusion This study proposed a CBR model to recommend treatments against three (3) maize dis- eases. Accurate detection and appropriate treatment recommendations for such diseases are crucial for successful cultivation and mitigating food insecurity. The proposed model uses image analysis to detect maize leaf attacks and recommends treatment actions based on past successful cases. Comparative analysis shows that the proposed CBR sys- tem performs competitively against classical classification algorithms like SVM, Ran- dom Forest, KNN, and Logistic Regression. Each model performed well, with SVM and Logistic Regression excelling other models with outstanding performance in accurately classifying Blight, Common Rust, and Healthy maize. Each model has struggled to accu- rately diagnose Gray leaf spot, frequently mistaking it for Blight. Suggesting a need for enhanced differentiation techniques, especially for Blight and Gray leaf spot. Compared to the existing literature, the proposed model shows promising results. At present we are Margwe et al. Discover Artificial Intelligence (2026) 6:408 Page 28 of 35 working on improving the developed easy to use mobile application that could be used on field by the farmers. 5.2 Future work Future work will focus on extending and strengthening the proposed CBR-based maize disease diagnosis system in several important directions. First, the system will be expanded to support a broader range of maize disease types, moving beyond the three major diseases considered in this study. This expansion will improve the practicality and coverage of the system under complex real-world planting conditions. In addition, future versions will investigate the incorporation of multimodal data sources, such as environ- mental sensor data, textual descriptions from farmers, and historical field records, to provide a more comprehensive and reliable diagnostic basis. Second, particular emphasis will be placed on lightweight and offline-capable deploy- ment, including the development of optimized mobile and web-based applications suitable for field environments with weak or unstable network connectivity. Model com- pression and computational efficiency will be considered to ensure timely diagnosis and accessibility for farmers at low cost. In addition, a dynamic update and maintenance mechanism for the case base will be designed, including automated strategies for evaluating, screening, revising, and retain- ing new cases. This will allow the system to continuously learn from user feedback and expert corrections, preventing knowledge aging and enabling long-term adaptability. Fig. 10 The diagnosis Interface Margwe et al. Discover Artificial Intelligence (2026) 6:408 Page 29 of 35 Fig. 11 Prompting the user for revision Finally, future studies will validate the proposed system using real field datasets and explore integration with agricultural internet of things (IoT) platforms and unmanned aerial vehicle (UAV) data collection systems. Such integration would enable large-scale crop health monitoring, early disease warning, and a transition from point-based diag- nosis to systematic maize field management.

  Keywords: proposed model maize field system based future leaf blight farmers disease diagnosis against three treatment
• AI-Driven Crop Disease Prediction System (2026) · doi

  The AI-Driven Crop Disease Prediction System bridges conventional agricultural practices with advanced automation. By combining computer vision, deep learning, and environmental data analysis, the system provides farmers with an efficient, accurate, and accessible solution for early disease identification. It reduces dependency on manual expert inspection, supports localized decision-making, and promotes sustainable crop management through timely intervention and prevention strategies. Future work will focus on the following enhancements: • Blockchain-based record storage to ensure transparency and traceability of disease data. • Federated AI learning models for privacy-preserving and region-specific training. • Integration of conversational chatbots to assist farmers with instant, context-aware recommendations. • Predictive modeling for disease outbreak forecasting using weather and soil parameters. • IoT-based real-time monitoring for automated image and sensor data collection. • Cloud-based synchronization for scalable deployment across multiple agricultural zones. © Author(s). This work is peer-reviewed, openly published, and permanently archived This article is openly accessible and reusable with proper attribution. https://ijsmt.org/ , Email: [email protected] 6 International Journal of Science, Strategic Management and Technology Volume 02 Issue 05 May-2026 | ISSN: 3108-1762 (Online) | Impact Factor: 3.8 An International, Peer-Reviewed, Open Access Scholarly Journal Indexed in recognized academic databases

  Keywords: disease based crop system agricultural learning farmers accessible management peer reviewed openly ijsmt international journal