Our system combines two riverine models that process public data:
- Hydrology Model: Forecasts the amount of water flowing in a river.
- Inundation Model: Predicts which areas will be affected and how high the river water will rise.
This enables us to provide up to 7 days advance warning to those in areas about to be impacted. By alerting people and organizations, we strive to empower them to act, minimizing damage and loss of life. We collaborate with governments, the UN, and NGOs to implement and distribute these alerts.
The Google “Hydrology Model” is the first operational model that uses Machine Learning to generate improved hydrology forecasts in locations globally. The forecasting model accepts as inputs data such as precipitation, temperature, etc., and produces as an output a forecast of river streamflow at the outlet of a specific river basin.
The Google “Inundation Maps Model” is one of the few flood models that generate maps that allow to identify which villages or areas are going to be flooded given a specific hydrology forecast.
Our system also utilizes a new model for urban Flash Floods that predict floods from heavy precipitation with a rapid onset in densely populated areas. This enables us to show urban areas at risk of flash floods within the next 24 hours.