The capability of synergistic satellite flood monitoring and forecasts is crucial for improving disaster preparedness and mitigation. In this study, the Soil Moisture Active Passive (SMAP) fractional water (FW) data sets were used for flood mapping over southeast Africa during the Cyclone Idai event. We then developed a machine-learning approach with the support of Google Earth Engine (GEE) for 24-hour flood forecasting and 30-m inundation mapping using observations from SMAP and Landsat coupled with rainfall forecasts from Global Forecast System (GFS) 384-Hour Predicted Atmosphere Data. The forecast results for the Idai event captured the flood dynamics at 30-m resolution and showed inundation patterns consistent with independent satellite Synthetic Aperture Radar (SAR) observations. The approach provides new capacity for flood monitoring and forecasts from synergistic satellite observations and is particularly valuable for data sparse regions.