Virtual Environmental Monitoring Network: Creating a granular environmental quality monitoring network and data resource to enable evidenced-based, data driven environmental policymaking

 

Current energy and environmental policymaking is essentially grounded in the products of limited monitoring and data gathering, and industry self-reporting. Data available today remain siloed, largely inaccessible to policymakers, the public, and the regulated community, creating a need for an integrated resource.  These limitations impair environmental decision making and the ability to prevent public harm.

A new generation of data-driven environmental protection is needed to enable the development of more effective and more targeted policies and precise, pragmatic regulatory interventions.  More comprehensive monitoring, analysis, and reporting incorporating existing data sets with hooks for future data resources – particularly as micro-sensing technologies, their networking potential, and citizen science mature – and could facilitate the next generation of environmental protection and energy policy.

Coupled with an ever more granular socio-environmental monitoring network, data science can be used to support regulatory activities and policymaking: predictive (forecasting), descriptive (data mining), and prescriptive (optimization and simulation), and enable continuous improvement.  This would allow businesses to more effectively monitor their own environmental performance. In short – data science through the envisioned data resource can help deliver maximum effectiveness from resource-limited government programs. Such a network can lead to increased transparency, greater accountability, improved environmental performance and outcomes, and greater compliance with environmental protection regulations, and empower communities to take their own actions on energy and environmental issues.

A virtual environmental quality monitoring network would bring together rich, diverse, and more granular sources of environmental data, and through the application of systems engineering and data science techniques, inform and enable more effective, evidence-based, and protective environmental policies and business decisions by the regulated community, as well as inform the public of environmental conditions that affect them and their communities in new and compelling ways.  Ultimately, the resulting data resource is envisioned as an accessible platform and application, a tool intended to better inform and improve policymaking, decision making, and environmental outcomes, and facilitate related research.

 

The Center for E3 is focusing initially on building a proof-of concept network in partnerships involving water quality in the Susquehanna River.  Initial project activities include building the network prototype by accessing available data sets:

 

  • The Center for E3 is partnering with RiverStewards to create a prototype version of the network for the Susquehanna River
  • A significant proof-of-concept of the role of data science in environmental policymaking is a partnership effort underway between the Center for E3 and the Susquehanna River Basin Commission. Kevin Purcell, Ph. D., Associate Professor of Data Science & Program Lead for the ANLY Program, and Siamak Aram, Ph. D., Assistant Professor of Analytics, and Mike Meyer, Ph.D., Assistant Professor of Earth Systems Science are leading graduate students in projects to enhance the granularity of the Commission’s analytical and decision-making capacity and to incorporate, for the first time, extensive and detailed meteorological data and management dashboarding systems.

Ongoing Center for E3 research will:

  • Identify institutional alignments, data and technology gaps, and obstacles to the development of an environmental quality monitoring network
  • Identify appropriate data science, machine learning, and networking tools and methodologies to improve predictive, descriptive, and prescriptive ability of environmental decision making and promote utilization of data acquired via the environmental monitoring network
  • Once the network approach is validated, efforts would commence to scale the network and data resources to state, regional, and larger levels
  • Design data quality standards for citizen science activities and monitoring technologies
  • Develop cheaper, more durable, and energy self-sufficient sensors and networks to enable more granular monitoring and data gathering
  • Expand the capabilities of water quality monitoring equipment/sensors to include additional parameters, chemicals (e.g. lead)

Other fields and industries are being transformed using data science, and the opportunity for environmental decision making holds no less potential.