CyanoPampas: A Microscopy Image Dataset of Filamentous Bloom-Forming Cyanobacteria from Pampean Shallow Lakes (Argentina) for Automated Taxonomic Recognition

This dataset comprises 382 high-resolution microscopy images of filamentous cyanobacteria grouped into six classes (Anabaenopsis cunningtonii, Anabaenopsis elenkinii, Dolichospermum circinale, Planktothrix agardhii, Raphidiopsis mediterranea and “Sphaerospermopsis aphanizomenoides), plus an additional class (Others) representing other cyanobacteria or microalgae present in water samples. The images were obtained from three shallow lakes located in the province of Buenos Aires, Argentina: El Paraíso (L8, -39.065559, -62.747130, Villarino), Blanca Grande (L21, -36.482884, -60.898455, Olavarría), and Laguna de Lobos (L22, -35.281213, -59.114367, Lobos). For dominant bloom-forming cyanobacterial species at least 82 images were captured using an inverted light microscope following the Utermöhl method (1958). All images were named following the structure “LakeCode_FieldNumber_SpeciesPresent”, using the abbreviations “Anab_c” for Anabaenopsis cunningtonii, “Anab_e” for Anabaenopsis elenkinii, “Dol” for Dolichospermum circinale, “Plank” for Planktothrix agardhii, “Raph” for Raphidiopsis mediterranea, and “Sph” for Sphaerospermopsis aphanizomenoides. The dataset also includes a binary annotation table indicating the presence (1) or absence (0) of each species in each image, as well as three additional folders containing 50 AI-generated synthetic images each, representing low, medium, and high levels of recognition difficulty based on image quality and the number of classes present. This dataset provides a valuable resource for the development of machine and deep learning–based tools to detect and recognize some of the most common filamentous bloom-forming cyanobacteria species in Argentina. By automating detection, it enhances monitoring efforts and enables faster responses to harmful blooms that threaten both environmental and public health.