Skip to main content
U.S. flag

An official website of the United States government

S33. Application of machine learning to remote sensing of floods


Closing Date: May 1, 2019

This Research Opportunity will be filled depending on the availability of funds. All application materials must be submitted through USAJobs by 11:59 pm, US Eastern Standard Time, on the closing date.


The U.S. Geological Survey (USGS) seeks a postdoctoral scientist to research machine learning methods for application to remote sensing of flood inundation.  A new generation of satellites is producing remote sensing data with dramatically increased frequency, spatial detail, and variety.  There is immense potential to leverage this rapidly expanding constellation of remote sensing data for mapping flood inundation and improving situational awareness during flood events.

The scientist will join a multidisciplinary team with expertise in the fields of hydrology, hydraulic modeling, remote sensing, and machine learning from the USGS, National Aeronautics and Space Administration (NASA), and National Geospatial Intelligence Agency (NGA).  The postdoctoral scientist will be based at adjoining NASA/USGS facilities in Silicon Valley, with opportunities to interact with NGA and industry partners in the Valley. 

The focus of research under this Opportunity is on development of machine learning algorithms and development of DELTA (Deep Earth Learning Training, and Analysis) software for earth scientists to detect and verify water extent from multiple sources of aerial and satellite imagery, including low-latency multispectral and synthetic aperture radar (SAR) satellite data and from hydraulic model output.  The research is expected to contribute to development of a computational system capable of detecting flood inundation at a fine-scale (<10 m) anywhere in the US in near-real time. Challenges faced in developing such a system include: intensive computational and data storage requirements; analysis and assimilation of multiple types of data; signal interference from clouds, vegetation, and urban structures; and availability of suitable training data.

Tools and data sets available for use include the NASA Earth Exchange (NEX) computing platform, the USGS Hazard Data Distribution System (HDDS), USGS National Hydrologic Dataset (NHDPlus HR), 3D Elevation Program national elevation datasets (3DEP), the National Hydrologic Model, Amazon Web Services (AWS), and USGS Advanced Research Computing (ARC).

Applicants are encouraged to contact the advisors below early in the process to discuss project ideas and how they fit into overall agency goals for mapping flood inundation.

Proposed Duty Station: Moffett Field, CA

Areas of PhD: Computer science, artificial intelligence, machine learning, mathematics, engineering, remote sensing, geographic/cartographic sciences, hydrologic sciences, hydraulics, or related fields (candidates holding a Ph.D. in other disciplines, but with extensive knowledge and skills relevant to the Research Opportunity may be considered).

Qualifications: Applicants must meet one of the following qualifications: Research Geographer, Research Hydrologist, Research Physical Scientist, or Research Engineer

(This type of research is performed by those who have backgrounds for the occupations stated above.  However, other titles may be applicable depending on the applicant's background, education, and research proposal. The final classification of the position will be made by the Human Resources specialist.)

Human Resources Office Contact: Nina Ngo, 703-648-7431,