"FACT: Big data analytics to harmonize disease and pest management with agricultural logistics" Grant uri icon

abstract

  • Management of agricultural challenges such as diseases and insect pests requires making decisions. Agricultural producers making these decisions require information on which to base their choices. Integrated management, combining multiple challenges and management actions into a coordinated approach, requires information that is also integrated. Model-driven decision support systems enhance integrated management when they are built on models that account for interactions between components, and the several logistical problems faced by producers. Integration increases efficiency; efficiency results in beneficial economic impact, reduced environmental impact, and resources available for further research into system improvement. The primary goal of this project, which focuses on cotton production as a model system, is to optimize simultaneous management of multiple problems in realistic setting, by applying high-performing analytics to empirically fit models for management, and using producer feedback for improving implementation of these models. We will conduct in-field research to fit epidemic and phenology models of cotton seedling disease, western flower thrips, and cotton fleahoppers. The project addresses two problems: the difficulty of applying results recovered through scientifically reductionist research to whole systems, and the challenges of benefiting producers by involving them in research. Delivering a beneficial decision support tool will enhance management by providing information in broad and realistic context, and the conduct of research that leverages powerful analytics in direct collaboration with producers will enhance produer ability to use resultant cyberinformatics tools, while also facilitating producers' engagement in future informatics-based research. This project addresses topic A1541, the "Food and Agriculture Cyberinformatics Tools" initiative.

date/time interval

  • 2020 - 2023