Abstract Submission: The global increase in the frequency and distribution of Harmful Algal Blooms (HABs) poses escalating threats to aquatic ecosystems, public health, and economic stability. In Kansas, lakes and reservoirs are particularly vulnerable due to rising nutrient concentrations and frequent HAB occurrences, leading to significant ecological disruption and diminished recreational value. The Kansas Department of Health and Environment has established an extensive, multi-year monitoring program to assess the health of public lakes and reservoirs. However, despite substantial efforts to monitor cyanobacterial biomass and toxin levels, limitations in resources result in insufficient spatial and temporal coverage to fully capture HAB dynamics. Remote sensing technologies offer a promising solution by providing high-resolution, freely available datasets capable of estimating critical HAB indicators, such as Chlorophyll-a. While several global models exist to estimate Chlorophyll-a from remote sensing data, they are often ineffective for the turbid, nutrient-rich waters typical of Kansas. To bridge this gap, our project aims to develop an operational model to estimate near-real-time chlorophyll concentrations using freely accessible Sentinel-2 satellite remote sensing data and machine learning techniques. This model will provide early detection for harmful algal blooms, offering critical data to better understand HAB triggers in Kansas waters and enhancing the state's capacity for monitoring and response efforts. Ultimately, the goal is to provide state agencies and water managers with an advanced tool to more effectively manage and mitigate the impacts of HABs in Kansas.
