Burkholderia glumae in rice: Climate-driven epidemiology, advanced detection techniques and AI-enhanced predictive forecasting models

Bacterial panicle blight (BPB), caused by Burkholderia glumae, is a major and rising threat to global rice production. Its severity is heightened by climate change, with outbreaks driven by high temperatures and humidity during the vulnerable flowering stage. Current management is hampered by delayed detection and a disconnect between diagnostic tools and predictive models. This review synthesises advances across climatology, molecular biology, and computational agriculture to address this gap. We analyse climate-driven disease dynamics, precise molecular diagnostics, and the emergence of AI for real-time image-based detection and weather-based forecasting. The novel contribution of this work is the proposal of an Integrated Multimodal AI Framework (IMAF) that converges these domains. The IMAF links climate modelling, sensor data, and computer vision to enable proactive, climate-resilient disease forecasting and decision support. This synthesis represents a critical paradigm shift from reactive management to intelligent, predictive intervention. We conclude with a roadmap for developing and deploying such integrated systems to enhance global rice resilience.