The Muskingum Watershed Conservancy District (MWCD) encompasses several reservoirs in Northeast Ohio. In addition to its flood reduction benefits, it provides recreational activities such as boating, fishing and camping which widely contributes to the local economy. As of 2014 the MWCD has seen a rise in toxic harmful algae bloom (HAB) occurrences. Increased use of synthetic fertilizer, livestock waste, pesticides containing nitrogen and phosphorous along with global climate change has caused nutrient oversaturation and heightened phosphorous load in local reservoirs leading to an influx of seasonal algae growth. Additionally, as the result of extensive coal mining, the region has experienced the effects of acid mine drainage (AMD). If left untreated, these anthropogenic catalysts can have severe consequences for aquatic ecosystems and local tourism. The effect that these processes have on the environment confirm that early warning procedures and advanced water quality monitoring systems are essential in today’s climate. To address this, we have applied a Varimax-rotated principal component analysis (VPCA) to satellite imagery from Sentinel-2 A/B MSI using a Google Earth Engine Python API combined with ground truth surveying of our field collection data to validate our remote sensing analysis. Our technique involves unsupervised classification methods that extract six components from spectral images to be identified by a spectral library. The method precisely pinpoints spectral reflectance data on water pixels and allows us to unmix the signal and identify the components of various algae, suspended sediment, and semi-submerged surface vegetation. Employing Google Earth Engine (GEE) components generated by the Kent State VPCA method, validated by our field data will allow us to distinguish suspended sediment from cyanobacteria, diatoms, and other algae. At the conclusion of this research, we will showcase an improved technique for monitoring the proliferation of algal blooms and recognizing changes in water quality over time.