Water hyacinth is one of the most aggressive alien invasive plants, which invades freshwater resources and destroys native biodiversity. The plant proliferates rapidly over a short space of time, forming thick dense layer on the surface of freshwater bodies. Monitoring and management of water hyacinth is essential to protect water resources affected by the presence of this plant. The study assessed the effectiveness of biological agent (Megamelus scutellaris) applied in the Hartbeespoort Dam from pre (2016–2017) and post (2018–2023) biological control to manage water hyacinth spread and proliferation. In achieving this main goal, the study used advanced cloud-computing machine learning techniques and multi date Sentinel-2 Multispectral Instrument (MSI) data to monitor the effectiveness of such biological control. During this analysis, remote sensing data was acquired for two time periods namely: pre-intervention (2016–2017) and post intervention (2018–2023) to establish variation in the spatio-temporal distribution of water hyacinth in the Hartbeespoort Dam using various machine learning techniques (Support Vector Machine (SVM), Classification and Regression Tree (CART), Random Forest (RF) and Naïve Bayes (NB)) in Google Earth Engine cloud computing platform, and assessed the spectral separability of water hyacinth from numerous land cover types, within and around the Hartbeespoort Dam using the Sentinel-2 derived spectral reflectance curves. The results indicated that the extent of water hyacinth area coverage decreased from 15% to below 6% between the period of 2018 and 2021, however, a significant increase was noted between November 2022 and April 2023, after the biological control was introduced. The significant increase observed during the time period of November 2022 and April 2023 can be attributed to nutrient rich water discharging into the dam from the Crocodile River during the time of flooding reported in November 2022. The result further indicate that RF produced the highest overall accuracies ranging between 93.42% and 98.70%. While NB produced the lowest accuracies ranging between 87.76% and 92.08%. These findings underscore the relevance of new generation satellite dataset and machine learning algorithms in monitoring the effectiveness of the biological controls of alien invasive spread provide information regarding alien plant invasion. Therefore, aligning with Sustainable Development Goals (SDG 6) emphasizing on the importance of implementing effective control measures to control invasive species and their impact on water resources thus ensuring the sustainability of freshwater ecosystems and the availability of clean water resources.