Session Lead: Qian Zhang (University of Maryland Center for Environmental Science / USEPA Chesapeake Bay Program)

Co-Lead(s): James Webber (U.S. Geological Survey), Rebecca Murphy (University of Maryland Center for Environmental Science / USEPA Chesapeake Bay Program), Kaylyn Gootman (USEPA Chesapeake Bay Program)

Session Format: Oral presentations

Session Description: 

Restoration of complex aquatic ecosystems such as Chesapeake Bay requires sustained collaboration between the science and management communities. Alongside advances in monitoring and modeling, there is a growing need for novel analytical approaches to extract new insights from data and for effective communication strategies that translate science into actionable guidance. Sustaining progress in a rapidly changing natural and human environment demands tools that can link diverse datasets and models to better explain ecosystem responses to environmental drivers and management actions. This session focuses on the development of innovative approaches for analyzing, interpreting, and communicating results in ways that directly support management. Examples include applications of advanced statistical and mechanistic methods, as well as artificial intelligence and machine learning. Contributions are also invited that highlight science communication strategies designed to transform monitoring and model-based findings into actionable information for the management community. This is Part II of two connected sessions organized by the Chesapeake Bay Program’s Integrated Trends Analysis Team.

Presentations (Session 3 Abstracts)

  1. Ashok Jacob, ​​Raj Cibin: A Deep Learning Framework for Continuous Stream Nitrate Estimation across the Chesapeake Bay Watersheds
  2. Quinn Domanski: Investigating Bidirectional Dynamics in Chesapeake Bay Tributaries Using Long-Term Monitoring Data and Machine Learning
  3. Xueting Pu: Toward Generalizable and Interpretable Sediment Modeling with AI-Augmented HSPF
  4. Abigail Percich, Admin Husic, Allen Gellis, James F. Fox: Watershed-scale sediment source prediction using machine learning
  5. Diver Marin Palacio, Chuqiang Chen, Stanley Grant, Admin Husic, Sujay Kaushal: Capturing Event-Driven Salinity Pulses and Nonlinear SC Dynamics in Chesapeake Bay Tributaries using a Deep Learning Model
  6. Lindsey Boyle, Kelly Maloney, Rosemary Fanelli: Watershed wide predictions of specific conductance show increasing salinity across half of the Chesapeake Bay watershed
  7. Marina Metes, Matthew Cashman, Zachary Clifton: Predicting Aquatic Physical Habitat Over a 38-Year Period Using Machine Learning
  8. Chuqiang Chen, Admin Husic: Increasing event water fraction across the Chesapeake Bay Watershed under climatic and anthropogenic change
  9. Lorena Pinheiro-Silva, Xiaoxu Guo, Matthew Houser, Greg M. Silsbe: Tracking Nutrient Pollution and Best Management Practice Effectiveness in the Choptank River Using Explainable Machine Learning and Satellite Data
  10. Nivedita Priyadarshini Kamaraj, Sundarabalan V. Balasubramanian, Manoochehr Shirzaei, Susanna Werth: Multi-Sensor Nutrient Mapping in the Chesapeake Bay
  11. Breck Sullivan, ​​Jon Harcum, Elgin Perry, Rebecca Murphy, Peter Tango: Filling the Gaps: A space-time interpolation tool for Chesapeake Bay dissolved oxygen
  12. Jeremy Testa, Amir Azarnivand, Damian Brady, Walter Boynton, Lora Harris, Carl Friedrichs, Casey Hodgkins: The diversity of patterns and controls on oxygen depletion in Chesapeake Bay triblets
  13. Gabriel Duran, Jon Harcum, Elgin Perry, Breck Sullivan, Kaylyn S. Gootman, Rebecca Murphy, and Allison Welch: Utilizing Cluster Analysis to Assess Water Quality Trends in the Chesapeake Bay
  14. David Parrish, Carl Friedrichs, William Reay, and Erin Shields: Recent Shifts in Water Clarity Across Virginia’s Lower Chesapeake Tributaries: Evidence from Four Decades of Kd Observations
  15. Peichen Huang, Dante M.L. Horemans, Marjorie A.M. Friedrichs: The Importance of Mixotrophy for Phytoplankton Production and Nutrient Management