Research and development of a predictive system for fall armyworm early warning on maize crop

Abstract

The rapid increase in fall armyworms (FAW, Spodoptera frugiperda) in recent years has posed major challenges to maize growers around the globe. To keep larval density below the economic threshold, we need interdisciplinary agricultural solutions like plant protection epidemiology, the Internet of Things, and scientific data techniques for early detection, monitoring, forecasting, and making informed decisions. Pest control should be planned ahead of time to prevent indiscriminate pesticide spraying, waste, and a negative effect on the environment. In this study, the authors plan to create a comprehensive iFAWcast software system that will automatically predict, alert, and gather research data on fall armyworms on maize crops in Vietnam. The system is comprised of three major components: (i) An automatic forecasting and alerting tool for fall armyworm outbreaks on the web platform; (ii) An agriculture reporting, forecasting, alerting, and user management tool on the web platform; and (iii) A mobile app that provides forecasting and alerting services on fall armyworms to farmers based on their geographical location. The iFAWcast system
includes a central computation that dynamically updates weather forecasts from the Visual Crossing API and the OpenWeatherMap API, as well as a formula for the effective cumulative temperature based on the characteristics of fall armyworms on maize crops in Vietnam. The developed system was tested using data collected straight from the field, yielding extremely accurate and dependable results.