Water hyacinth (Eichhornia crassipes) is recognized as the most notorious invasive species over the world. Although its threats and effects are fully documented, its distribution is not yet understood, especially in complex environments, such as river systems. Thus, this study was aimed at mapping and understanding the spatio-temporal distribution of invasive water hyacinth in Lake Tana, using Landsat 8 OLI and Sentinel-2 MSI satellite. Training samples were collected for classification (i.e., with Maximum likelihood classification algorithm) of the satellite images and accuracy assessment. Image preprocessing like image enhancement was carried out before classification. Maximum likelihood classification algorithm Supervised image classification technique was applied to map spatio- temporal distribution of water hyacinth. The classification accuracy assessment result for 2020 was 96% overall accuracy and 0.95 kappa coefficient. The result indicated that water hyacinth cover 146.6 ha in 2014, 144.4 ha in 2016, 162.9ha in 2018 and 248.3ha in 2020. Between 2014 and 2016, the coverage of the invasive weed has reduced (0.5%) but increased through 2016 and 2020 periods (2.43%). Since the expansion of the weed is extremely fast and a problem for the eco hydrology of the lake, therefore appropriate intervention mechanisms should be urgently introduced. Keywords: invasive weed, Lake Tana, mapping, remote sensing, water hyacinth