A predictive intelligence and AI-driven irrigation optimization framework for enhancing crop yield in precision agriculture
Precision agriculture increasingly relies on Artificial Intelligence (AI)-assisted irrigation optimization with predictive intelligence. However, existing approaches generally address wheat disease detection, environmental prediction, irrigation management, and yield assessment as separate or partially integrated tasks, creating a gap in the unified use of multimodal crop information for disease-aware irrigation and crop assessment. To address this gap, the proposed approach combines Deep Learning (DL)-based disease detection using a Residual Network (ResNet) with environmental sensor data processing. Internet of Things (IoT)-based sensor networks collect real-time soil moisture, temperature, humidity, and light-intensity data, while high-resolution wheat leaf images are analyzed to extract visual information. A Long Short-Term Memory (LSTM)-based model processes temporal information for yield-trend prediction and supports irrigation scheduling through rule-based reasoning. The integrated framework dynamically adjusts irrigation decisions according to crop stress, environmental conditions, and disease severity. The proposed approach demonstrated high classification accuracy and precision on the selected wheat dataset, together with fast convergence during training, indicating its potential for practical crop-monitoring and irrigation-management applications. Overall, the hybrid framework provides an intelligent decision-support approach for early disease management, efficient water utilization, and data-driven wheat crop monitoring.
Authors
- Ibrahim Rizqallah Alzahrani (ORCID: https://orcid.org/0000-0001-7606-8384)
- Asim Seedahmed Ali Osman (ORCID: https://orcid.org/0000-0003-3444-6249)
- Daifallah Zaid Alotaibe
- Adil Mahmoud Mohamed Mahmoud
- Mohammed Eltayeb Ahmed Hemady
Institutions
- Nile Valley University (SD)
- University of Hafr Al-Batin (SA)
Publication Details
- Journal
- Journal of Environmental Science and Health Part A
- Published
- 2026-11-20
- DOI
- https://doi.org/10.1080/10934529.2026.2751694
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00