Flood Forecasting API

Driven by the potential impact of reliable flood forecasting on people’s lives globally, we started our flood forecasting effort in 2017. Through this multi-year journey, we advanced research over the years hand-in-hand with building a real-time operational flood forecasting system that provides alerts on Google Search, Maps, Android notifications and through the Flood Hub. However, in order to scale globally, especially in places where accurate local data is not available, more research advances were required.

In “Global prediction of extreme floods in ungauged watersheds”, published in Nature, we demonstrate how machine learning (ML) technologies can significantly improve global-scale flood forecasting relative to the current state-of-the-art for countries where flood-related data is scarce. With these AI-based technologies we extended the reliability of currently-available global nowcasts, on average, from zero to 5 days, and improved forecasts across regions in Africa and Asia to be similar to what are currently available in Europe. The evaluation of the models was conducted in collaboration with the European Center for Medium Range Weather Forecasting (ECMWF). Our new model extends the reliability of global nowcasts to 7 days (as opposed to 5 days) globally. Read the related Research Blog post to learn more.

These technologies also enable Flood Hub to provide real-time river forecasts up to seven days in advance, covering river reaches across over 100 countries. This information can allow communities, governments and international organizations to take anticipatory action that can help protect vulnerable populations.

Moreover, we’ve granted pilot participants access to the flood forecasting API, which contains two types of data (also presented in the Flood Hub):

1. Flood Status: The current severity of a flood that could include inundation maps
2. Hydrologic forecast: Daily hydrologic forecast up to 7-day horizon.

Note that access to the flood forecasting API is limited to pilot participants. However, the research community is invited to register for the API pilot waiting list.

Your use of the Flood Forecasting API is subject to the Google API Terms of Service and the following “Additional Terms” which are incorporated into the Google API Terms by this reference.

Section A: Non Commercial

ALL INFORMATION PROVIDED THROUGH THIS API MAY BE USED FOR NON-COMMERCIAL PURPOSES ONLY.

Any model predictions or output provided or made available to pilot participants, including the Google Flood Forecasting Dataset or relevant tools (collectively, “Predictions”), might include publicly available information, or information that is created by Google using such public information. As a user of the Predictions, Partner agrees and acknowledges that (i) Predictions might include defects, errors, or other problems that could cause failures or other harmful effects; (ii) Predictions are provided on an "AS-IS" basis without any warranties, express or implied; and (iii) Google does not guarantee its accuracy or completeness. Partners will not use the Predictions for the preservation of life or property.

Google reserves the right to discontinue Partner’s access to the Predictions at any time and for any reason. To the extent permitted by applicable law, Partner is solely responsible for Partner’s use of the Predictions, and Partner’s use will at all times comply with the terms of the Agreement and applicable laws.

Section B: Flood Forecasting Disclaimer

This map displays the approximate flood area based on Google Flood Forecasting models that use data from public sources, such as ECMWF, NASA, and NOAA. Accuracy levels and confidence levels may vary over time and locations. You should not use the information presented on the website as a sole source of data as actual flood conditions may vary. Unless otherwise stated, the models do not use data provided by governmental entities, nor is Google Flood Forecasting project affiliated with, sponsored by, or endorsed by any governmental entity.