Algal blooms caused by lake eutrophication severely affect ecosystem diversity and water security. Satellite data with low spatial resolution such as MODIS is limited to the monitoring of large lakes. However, single medium or high spatial resolution data sources such as Landsat-8 cannot meet the high-frequency monitoring requirements of algal blooms in practice, owing to the relatively longer revisiting period. This study, taking Dianchi Lake in 2019 as an example, combined six medium- or high-spatial-resolution satellite images to monitor variations in algal blooms. Three machine learning algorithms [Random Forest (RF), Extreme Gradient Boosting Tree (XGBoost), Artificial Neural Network (ANN), and Normalized Difference Vegetation Index (NDVI)] were tested in the study. The model accuracy was compared and analyzed using the visually interpreted ground truth. The results show that: \mathrm{①} the RF model applied to Dianchi Lake had the highest accuracy (91.94% accuracy, 91.91% F1 score, 91.52% recall, 92.30% precision, Kappa 0.838 8), followed by the XGBoost and ANN models; \mathrm{②} the identification results derived from multi-source satellite data on the same day were highly consistent, and the average Relative Error (RE) was less than 8.04%; and \mathrm{③} algal blooms occurred in Dianchi Lake with a high frequency in 2019, mainly in the form of mild and moderate algal blooms. Overall, the spatial distribution presented a “heavy in the north and light in the south” pattern. The results reveal that combining multiple medium- to high-resolution remote-sensing data sources is an effective approach for monitoring cyanobacterial blooms. This approach can enhance temporal resolution and ensure spatial resolution. However, promoting multi-source satellite joint observations in the monitoring of algal blooms in cloudy and rainy areas and small to medium-sized water bodies is recommended.