Cyanobacterial Harmful Algal Blooms (cHABS) are a naturally occurring but increasingly common phenomenon due to anthropogenic activities and climate change. cHABs reduce water quality by forming unsightly surface scums and sometimes producing algal matts on the surface of water bodies, reduce water quality, and in high densities can produce cyanotoxins that can harm humans, pets, and wildlife. Ecological forecasting of cHABs has proved elusive in part because the in-situ fluorometric methods currently employed for detecting cyanobacteria cells are subject to varied interference as water quality and the biotic community changes. In this study we seek to develop an ecological forecasting capability that overcomes both temporally and spatially derived in-situ fluorometric interferences. We obtained water samples at 26 polymictic reservoirs over a two-day period and at five polymictic reservoirs weekly during the summer of 2019. Collected water samples are being used for quantitative analysis of cyanobacterial cell densities by means of qPCR. We plan a data reduction technique (e.g. PCA, VIF screening, elastic-net regression as appropriate) followed by multivariate predictive model (e.g. multiple regression, ordination, discriminant analysis as appropriate).