EPA is at the beginning of a transformative stage in information management, where there are new and enhanced ways to gather data, conduct analysis, perform data visualization and use “big data” to explore and address environmental, business, and public policy challenges. Business intelligence tools, geospatial tools and visualization tools are also converging, providing opportunities for knowledge and insight from disparate data sources. 

EPA will reap huge benefits from the ability to harness this power of data corporately across the enterprise to produce knowledge on demand and drive better environmental results. The Office of Information Analysis and Access intends to work with EPA programs and regional offices to create a central platform for data analytics to evaluate information across a wide range of data collections and break through the Agency’s stove-piped set of data systems, which do not make these associations easy or common today. 

Work in this area will also fit with the Agency’s interests in advanced monitoring technology that leverages sensors, real time data and external data sources such as NASA satellites, or financial or health data in combination with EPA data sources. Expert systems and machine learning to target violations using data acquired through electronic reporting, as well as analytics with unstructured data and/or scattered data sets across the Agency are also envisioned as part of this new, emerging program at EPA.