Banana and plantain ( Musa spp.) production in Sub-Saharan Africa is severely constrained by multiple diseases, with Banana bunchy top virus (BBTV) representing the most devastating viral threat. Inadequate diagnostic infrastructure limits effective management, particularly for asymptomatic infections disseminated through informal planting material exchange. This study presents an integrated diagnostic framework combining Loop-Mediated Isothermal Amplification (LAMP) molecular diagnostics with deep learning-based computer vision for rapid, scalable disease detection under field conditions. A LAMP assay targeting the BBTV DNA-S coat protein gene was developed using conserved sequences from diverse African isolates and validated with a simplified alkaline extraction protocol eliminating conventional DNA purification. The assay achieved 100% specificity and concordant detection with PCR and qPCR, reducing diagnostic time from 4 to 6 hours to 60 minutes. In-house recombinant Bst LF polymerase production demonstrated comparable enzymatic performance to commercial alternatives, with projected per-reaction cost reductions of 70 to 80%. Concurrently, an SSDLite MobileNetV2 object detection model was developed through 19 iterative training cycles on 19,914 field-collected images spanning 22 disease and physiological stress classes. The final model achieved recall rates of 92.5% for BBTV, 91.0% for Banana Xanthomonas Wilt, and 98.1% for healthy leaf classification, deployed via the PlantVillage mobile application for real-time offline diagnostics. A QR code-based metadata system integrates phenotypic AI assessments with molecular confirmation for comprehensive surveillance. This complementary framework addresses broad-scale phenotypic screening and molecular confirmation of pre-symptomatic infections, providing accessible tools to safeguard food security across Sub-Saharan Africa.
Nine years after its invasion, fall armyworm ( Spodoptera frugiperda , FAW) still remains a major constraint to maize production and food security in sub-Saharan Africa. While augmentative biological control has been promoted in national and regional FAW management strategies, evidence of its farm-level economic performance is limited. This study evaluated the agronomic and economic outcomes of using egg parasitoids ( Telenomus remus and Trichogramma chilonis ) in smallholder maize systems in Kenya. We surveyed 403 households across five agro-ecological zones, comparing parasitoid-based control against chemical pesticides and no active control using ex-post cost-benefit analysis and multivariate regression models. Results indicate that in agro-ecological Zones I-III, parasitoid-based FAW management led to significantly higher maize yields, total revenue, and net farm benefits compared with both pesticides use and no control. These economic gains were driven by improved yields and lower pest management costs, as farmers reduced pesticide and spraying labor expenses. In contrast, no significant differences in yield or economic outcomes were detected in Zones IV and V, where low seed rates constrained a yield potential. Overall, the findings demonstrate that parasitoid-based biological control is a profitable, sustainable component of integrated pest management in maize-based smallholder systems. By improving net returns while reducing reliance on synthetic pesticides, this approach offers a viable pathway for strengthening farm profitability and food security for smallholders.
Plants exposed to volatile signals from herbivore-infested neighbors can activate faster and stronger defenses against subsequent herbivore attack, a phenomenon called defense priming. However, the specific volatile components responsible for activating defense priming remain unclear. Here, we examined the role of green leaf volatiles (GLV) by silencing their biosynthesis using virus-induced gene silencing technique. Exposure to full blend of herbivore-induced plant volatiles (HIPV) primed receiver plants for enhanced production of all 5 groups of HIPV (GLV, monoterpenes, sesquiterpenes, aldoximes, and indole). When GLV production was silenced in emitter plants, receiver plants were no longer primed for terpene production. However, exposure to ( Z )-3-hexenol (Z3HOL) alone primed receiver plants for terpene production. These results suggest that GLV are necessary, and Z3HOL alone is sufficient, to prime terpene production in receiver plants. Consistent with enhanced resistance, Manduca sexta larvae feeding on Z3HOL-or HIPV-primed plants consumed less leaf tissue and exhibited reduced growth compared with controls. Importantly, priming did not impose fitness costs, as Z3HOL-exposed plants showed normal growth but produced more seed capsules and seeds than control plants. Together, these findings suggest that Z3HOL alone is sufficient to prime plants for better defense without compromising their ability to grow and reproduce.