The increase in frequency and severity of cyanobacterial harmful algal bloom (cyanoHAB) events in our freshwater ecosystems represents a major concern due to their adverse health effects and impacts to the local economies. Traditionally, cyanoHAB detection occurred via monitoring of biomass and toxins and after the fact; new technologies (scaled up remote sensing, improved weather modeling and increased biological data) have improved our early detection and cyanoHAB prediction capabilities. In this talk, we will discuss our current efforts in developing Machine Learning (ML) datasets and algorithms that integrate chemical, physical and biological disparate data points from the Great Lakes region, towards building a holistic model for cyanoHAB prediction and toxin release. We will also describe our efforts in cyanoHAB flow cytometry for high-throughput, semi-automated data generation to generate new datasets able to feed into our ML models. Our work supports the overall cyanoHAB community in developing management and mitigation strategies in support of the sustainability of aquatic ecosystems affected by cyanobacterial algal blooms.