New approaches are described that use of the Ocean Color Remote Sensing Reflectance readings (OC Rrs) available from the existing Visible Infrared Imaging Radiometer Suite (VIIRS) bands to detect and retrieve Karenia brevis (KB) Harmful Algal Blooms (HABs) that frequently plague the coasts of the West Florida Shelf (WFS). Unfortunately, VIIRS, unlike MODIS, does not have a 678 nm channel to detect Chlorophyll fluorescence, which is used with MODIS in the normalized fluorescence height (nFLH) algorithm which has been shown to help in effectively detecting and tracking KB HABs. We present here the use of neural network (NN) algorithms for KB HABS retrievals in the WFS. These NNs, previously reported by us, were trained, using a wide range of suitably parametrized synthetic data typical of coastal waters, to form a multiband inversion algorithm which models the relationship between Rrs values at the 486, 551 and 671nm VIIRS bands against the values of phytoplankton absorption (aph), CDOM absorption (ag), non-algal particles (NAP) absorption (aNAP) and the particulate backscattering bbp coefficients, all at 443nm, and permits retrievals of these parameters. We use the NN to retrieve aph443 in the WFS. The retrieved aph443 values are then filtered by applying known limiting conditions on minimum Chlorophyll concentration [Chla] and low backscatter properties associated with KB HABS in the WFS, thereby identifying, delineating and quantifying the aph443 values, and hence [Chl] concentrations representing KB HABS. Comparisons with in-situ measurements and other techniques including MODIS nFLH confirm the viability of both the NN retrievals and the filtering approaches devised.