Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 261 - Statistical Learning for Environmental Data Science
Type: Invited
Date/Time: Wednesday, August 11, 2021 : 1:30 PM to 3:20 PM
Sponsor: Section on Statistics and the Environment
Abstract #316973
Title: Data and Systems and Clouds - Oh My! The Science of the Data: Architectures for Environmental Learning
Author(s): Elizabeth Mannshardt* and David G Smith
Companies: US Environmental Protection Agency and US Environmental Protection Agency
Keywords: data; environment; machine learning; architecture; cloud
Abstract:

Have you ogled at the sheer amount of environmental data out there? Often at our fingertips via apps and API’s, but how did it get there? Size, portals, access – how can you navigate the vast amounts of information available? “The Science of the Data” on the IT side of data science will explore the realm of data and its technical journey on its way to your analysis. Implementing statistical methodologies including machine learning goes beyond programming, Python, R. The architecture side of environmental data is the science of the data flows behind solving key environmental statistics problems. Key architecture considerations include data management and data flows; cloud functionalities and analytic platforms; and data governance - all of which are connecting systems and databases so that statistics techniques can be applied across multiple environmental data sources. This presentation will include environmental ML/stat learning examples. It will also explore the connection to environmental policy such as federal guidance and executive orders pertaining to the use of ML & AI in government statistics. The Science of the Data is a vital side of statistics and Data Science.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program