This proposal would fund the testing of quantitative methods for extracting total water level from imagery, with add-on applications including satellite shoreline detection, digital stream gauges, and flood detection. This project supports national scale USGS coastal hazards products.
Predictions of total water level (TWL) are necessary for long-term coastal planning and early warning systems including the USGS/NOAA Total Water Level and Coastal Change Forecast. TWL is challenging to monitor, but coastal imaging cameras are a scalable monitoring solution. However, we are still relying on laborious hand-digitization to extract TWL from imagery. This has created a bottle-neck and there are now years of extremely valuable but relatively unprocessed images. We propose to replace hand-digitization with a robust automated method. TWL extraction methods will be trained and then tested using existing USGS imagery collected in several diverse coastal settings. The methods developed will have add-on applications to other imagery collected by the USGS, including image to stage estimates, flood detection, and satellite shoreline detection. Resulting methods and code will be shared with the Center for Data Integration community.
- Overview
This proposal would fund the testing of quantitative methods for extracting total water level from imagery, with add-on applications including satellite shoreline detection, digital stream gauges, and flood detection. This project supports national scale USGS coastal hazards products.
Predictions of total water level (TWL) are necessary for long-term coastal planning and early warning systems including the USGS/NOAA Total Water Level and Coastal Change Forecast. TWL is challenging to monitor, but coastal imaging cameras are a scalable monitoring solution. However, we are still relying on laborious hand-digitization to extract TWL from imagery. This has created a bottle-neck and there are now years of extremely valuable but relatively unprocessed images. We propose to replace hand-digitization with a robust automated method. TWL extraction methods will be trained and then tested using existing USGS imagery collected in several diverse coastal settings. The methods developed will have add-on applications to other imagery collected by the USGS, including image to stage estimates, flood detection, and satellite shoreline detection. Resulting methods and code will be shared with the Center for Data Integration community.