SADSS-Tobacco: A Predictive Deep Learning Decision-Support Framework for Yield Forecasting and Leaf-Stress Detection in Zimbabwe's Tobacco Production

Background: Tobacco is Zimbabwe's most economically significant agricultural export commodity, generating annual revenues exceeding USD 1 billion and sustaining livelihoods for hundreds of thousands of smallholder farmers . Farm management decisions remain predominantly reactive, relying on visual inspection and experiential judgement rather than data-driven predictive intelligence.Objective: This paper presents SADSS-Tobacco (Smart Artificial Intelligence Driven Decision Support System for Tobacco), an integrated multi-modal framework combining deep learning, Internet of Things (IoT) environmental sensing, and explainable artificial intelligence (XAI) for leaf-stress detection, irrigation forecasting, yield prediction, and curing optimisation in Zimbabwean tobacco production.Methods: A ResNet50 convolutional neural network was fine-tuned on 1,152 field-collected, expert-labelled tobacco leaf images (Fleiss' κ = 0.87; Eq. 6) for three-class stress classification. A Random Forest regression model was trained on approximately 50,000 IoT sensor readings for 24-hour irrigation forecasting. An XGBoost regression model was developed from 48 field-year TIMB historical records (2018–2025) for seasonal yield prediction. Explainability was implemented via Grad-CAM (image models) and SHAP (Eq. 4, tabular models). Five-fold cross-validation and a structured ablation study were applied throughout.Results: ResNet50 achieved 92.3% accuracy (95% CI: 89.1–94.8%; F1-macro = 0.91; Brier = 0.091). The irrigation model attained RMSE = 0.12 m³/m³ (R² = 0.81). Yield forecasting achieved RMSE = 142 kg/ha (Eq. 3) and R² = 0.78 on 2025 held-out data (MAPE = 7.2%). Revenue grade prediction accuracy reached 84% (Wilson-score 95% CI: 43–97%). Multi-modal fusion improved F1-macro by 12.3% over the image-only baseline (Cohen's d = 1.04; p < 0.001, Bonferroni-corrected).Conclusions: SADSS-Tobacco demonstrates that integrating multi-source data through explainable deep learning can transform reactive tobacco management into proactive, evidence-based decision-making, offering a replicable architecture for export-oriented cash crops in data-scarce Sub-Saharan African environments.