University of Science and Technology Chittagong

Sustainable agriculture in arid regions faces critical challenges due to water scarcity, high temperatures, and inefficient traditional farming practices. This study presents an AI-enabled smart farming framework for optimizing date palm (Phoenix dactylifera) cultivation through the integration of Machine Learning (ML) and Internet of Things (IoT) technologies. A structured multimodal dataset comprising biometric features palm height, trunk diameter, and leaf number, environmental parameters soil moisture, temperature, and humidity, and categorical attributes variety and health status was analyzed to classify palm health and support data-driven irrigation management. Four ML algorithms Random Forest (RF), Gradient Boosting Machine (GBM), Artificial Neural Network (ANN), and Support Vector Machine (SVM) were developed and optimized using grid search with five-fold cross-validation. Among them, the Random Forest model achieved the highest classification accuracy of 95.3%, demonstrating strong robustness for heterogeneous agricultural data. Feature importance analysis highlighted soil moisture, humidity, trunk diameter, and leaf number as key contributors to palm health prediction. The proposed AI-IoT framework enables real-time monitoring, predictive diagnostics, and automated decision support for sustainable water use and crop management, aligning with Saudi Vision 2030 objectives for technology-driven and resource-efficient agriculture.

The rapid expansion of digital agriculture driven by sensors, drones, IoT devices, and remote sensing technologies has generated unprecedented volumes of farm-level data, intensifying concerns surrounding privacy, ownership, and secure data sharing. Federated Learning (FL) has emerged as a promising paradigm that enables distributed model training without exposing raw data, making it well suited for precision agriculture. This systematic review examines 90 peer-reviewed studies published between 2022 and 2025 across major academic databases to evaluate how FL is being applied to enhance agricultural intelligence while reducing raw-data sharing and, in fewer studies, using explicit privacy mechanisms. This review distinguishes between (i) baseline FL, where privacy is primarily achieved by keeping raw data local and (ii) FL augmented with explicit privacy-preserving mechanisms such as differential privacy, homomorphic encryption and secure multi-party computation. Besides, it highlights that horizontal and cross-silo FL architectures dominate current research, particularly in crop disease detection, yield prediction, smart irrigation, and IoT-based farm monitoring. A key finding is that most agricultural FL studies still rely on baseline FL without formal privacy guarantees, and the adoption of DP/HE/SMPC remains limited highlighting a major research gap. Although FL often matches centralized deep-learning accuracy, real-world adoption is limited by non-IID data, communication costs, and constrained compute/connectivity in rural settings. This review summarizes FL architectures, agricultural applications, and the limited use of explicit privacy mechanisms, highlighting key gaps and research directions (personalized/hierarchical FL, federated reinforcement learning, explainable and energy-efficient models, and quantum-enhanced FL).

Early detection of plant and crop diseases is vital for achieving sustainable agriculture and global food security. Traditional inspection methods are often slow and subjective, whereas Artificial Intelligence (AI) techniques offer fast, scalable, and objective alternatives. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, this systematic review synthesizes 145 studies published between 2023 and 2025 that employ Machine Learning (ML), Deep Learning (DL), Explainable AI (XAI), and Federated Learning (FL) for plant and crop disease classification. The studies are organized by crop species, imaging modality, and model architecture to evaluate performance in terms of accuracy, robustness, interpretability, and privacy preservation. Results reveal that XAI techniques such as Grad-CAM, LIME, and SHAP enhance transparency and trust, while FL enables decentralized and privacy-aware collaboration across distributed agricultural datasets with only minimal reductions in model accuracy compared to centralized training. Despite strong results in controlled conditions, many models struggle to generalize under real-field variability due to data imbalance and environmental factors. Emerging directions include lightweight edge architectures, domain adaptation, and unified explainable-federated frameworks. Overall, this review identifies FL and XAI as complementary drivers of transparent, privacy-preserving, and scalable AI systems for sustainable precision agriculture.

Aquaculture is the fastest-growing sector of animal food production, yet it faces increasing challenges in maintaining fish health and sustainability due to the widespread use of antibiotics and synthetic feed additives. Green tea ( Camellia sinensis ), a natural source of polyphenols and bioactive compounds, has gained attention as a functional feed additive capable of enhancing growth performance, immune function and disease resistance in aquaculture species. This review critically examines genomic and omics-based evidence supporting the efficacy of C. sinensis in fish and shrimp nutrition. Findings from quantitative PCR (qPCR) and transcriptomic studies reveal that green tea supplementation significantly modulates the expression of key immune and antioxidant genes, including IL-1β , TNF-α , SOD and CAT , thereby strengthening innate immune responses and oxidative stress resistance. In addition, green tea influences critical stress and pathogen-response pathways through the upregulation of HSP70 , toll-like receptors (TLRs) and activation of the NF-κB signalling cascade. These molecular responses collectively contribute to enhanced physiological resilience and reduced reliance on antibiotics. Comparative data indicate consistent improvements in growth metrics, gene expression profiles and immune biomarkers across multiple aquaculture species, emphasizing dose specificity and conserved pathways across species. The integration of green tea into aquafeeds presents a sustainable, eco-friendly strategy aligned with modern functional feed innovations. Future research should aim to optimize dosage levels, evaluate species-specific responses and employ integrative multi-omics approaches to further elucidate long-term effects on aquatic health and environmental sustainability.

Persimmon, a tropical shrub yielding fibrous, meaty fruits, is conventionally used in traditional medicine to address angina, stroke, hypertension, infectious disorders, and atherosclerosis. In recent decades, multiple studies have shown that various significant classes of functional bioactive chemicals, including proanthocyanidins, flavonoid oligomers, tannins, phenolic acids, catechin, and carotenoids, are prevalent in the leaves and fruits of Diospyros kaki (D. kaki). These phytochemicals are responsible for several biological actions. A significant number of published studies demonstrate that the bioactive compounds of this plant possess anticancer, antiinflammatory, neuroprotective, cardioprotective, and cosmeceutical properties. Persimmon extract has therapeutic properties and little documented adverse effects, making it a reliable and safe botanical for widespread usage, with some traditional uses being examined in pharmacological studies. Moreover, Persimmon is nutritionally valuable due to its abundance of carbohydrates, protein, and vitamins A, B6, B12, D, E, and K, as well as ascorbic acid. This review examines the potential phytochemicals in D. kaki that may be effective in treating various diseases, alongside in vitro pharmacological studies, in vivo pre-clinical research, toxicological assessments, and future research prospects for this plant, which is rich in multifunctional nutrients.