Title: Deep Learning for Environmental and Ecological Prediction-Evaluation and Insight with Ensembles of Water Quality (DEEP-VIEW)
Presenting Author: Troy J. Ames
Organization: NASA Goddard Space Flight Center
Co-Author(s): Brian Terry, Yin-Hsuen Chen, Blake Steiner, Sridhar Katragadda, Navid Tahvildari, Soenke Dangendorf, George McLeod, Sunghoon Han, Brandon Feldhaus, Joshua Baptist, Oguz Yetkin, and Heather Richter

Abstract:
Computationally intensive artificial intelligence algorithms trained with many sources of observations have the potential to detect impairments to water quality that were not previously possible through traditional techniques. State water quality monitoring agencies currently sample 800 sites around the Chesapeake Bay in boats every month, likely missing features in time and space located in between these point source observations. Working closely with stakeholders around the Chesapeake Bay over the past couple of years, we identified priorities for satellite applications, namely water safety indices such as clarity, potability, harmful blooms. Previous work focused on a limited set of satellite data and utilized a tailored data fusion methodology. Now we are generalizing and extending our initial methodology to integrate multiple satellite data sets of different spatial, spectral, and temporal resolution within Deep Learning for Environmental and Ecological Prediction-Evaluation and Insight with Ensembles of Water Quality (DEEP-VIEW) to improve predictions of aquatic features such as water clarity, estuarine impacts of runoff from land, algal blooms and other metrics that are needed by resource managers and other stakeholders to safeguard health and safety.