CyanoHAB forecasting

This project, funded through the NASA Earth eXchange (NEX) and the NASA Ames High End Computing Center (HECC) will apply novel water quality inversion algorithms from the SWIPE ecosystem to roughly three decades of satellite imagery of the western United States. The primary objective of the project is to evaluate and monitor water quality over time and space, with a keen focus on assessing its relationship with various environmental factors. These models will help us quantify water quality indicators, such as sediment, and pigment concentrations of chlorophyll-a and phycocyanin, which are key indicators of the presence of harmful algal blooms. Importantly, the use of ML algorithms will allow us to process and analyze the data more efficiently, offering new insights into the temporal and spatial patterns of water quality at unprecedented fidelity and resolution. A key component of this project is the development of a spatio-temporal cyanobacteria harmful algal bloom forecasting model. By integrating our water quality data with meteorological information and watershed catchment characteristics, we expect to gain a more comprehensive understanding of the complex interactions and dynamics that lead to harmful algal blooms. Ultimately, our model aims to predict future occurrences of these blooms, which have significant implications for public health, water treatment, and ecosystem balance. This work represents a substantial step towards the application of AI in environmental science. We anticipate that the outcomes of this project will not only advance our understanding of water quality dynamics in the western United States but also provide a valuable tool for water managers and policymakers to prevent and manage the risks associated with harmful algal blooms.