 This research proposes a novel method for automating algal bloom detection using multi-temporal image series processing, spectral indices and classification with one class support vector machine, OCSVM, on Landsat 8 and Modi's imagery through the Google Earth Engine API. The method is evaluated on two bloom detection case studies and compared to spectral index thresholding approaches. While the proposed method delivers highly accurate results, its higher computational cost is a drawback. The application of the new method to a real-world bloom case is demonstrated. This article was authored by Pedro Enrique Mori Zananias and Rogerio Galanti Negri.