A Bleeding Edge Web Application for Early Detection of Cyanobacterial Blooms

Abstract

Harmful Algal and Cyanobacterial Bloom (HACB) threaten aquatic ecosystems, human health, and the economy. Many factors influence these dynamic events, which are often difficult to detect until the late stages of growth. The inclusion of an Early Warning System (EWS) can be instrumental in identifying hazards and preventing or at least minimizing their impact. Traditional monitoring approaches often fail to provide the real-time, high-resolution data needed for effective early warnings. The integration of Internet of Things (IoT) technologies offers a promising avenue to address these limitations by creating a network of interconnected sensors capable of continuously collecting and transmitting data from various aquatic environments. In this paper, we present DEVS-BLOOM-WebUI, an advanced web application that extends the capabilities of the DEVS-BLOOM framework, providing a user-friendly interface that supports different user roles. The application includes an interface to manage users and permissions, dashboards to inspect data (from sensors, Unmanned Surface Vehicles (USVs), weather stations, etc.), train AI models, explore their predictions, and facilitate decision-making through notification of early warnings. A key feature of DEVS-BLOOM-WebUI is the Scenario Configuration Editor (SCE). This interactive tool allows for users to design and configure the deployment of monitoring infrastructure within a water body, enhancing the system’s adaptability to user-defined simulation scenarios. This paper also investigates the practical implementation of an IoT-based EWS, discussing design considerations, sensor technologies, and communication protocols essential for seamless data integration and effective operation of the EWS.