Wetland Intrinsic Potential Tool

Efforts

Efforts describe the work of workgroups

Involved Workgroups:

• Knowledge Creation
  • Adaptive Management
  • Arts and Crafts
  • Lessons
  • Monitoring
  • Research
• Protection
  • Acquisition
  • Green Infrastructure
  • Regulation
• Restoration
  • Beach Nourishment
  • Engineered Log Jams
  • Fish Passage
  • Revegetation
• Social Change
  • Advocacy
  • Coordination
  • Education
  • Funding
  • Integrated Ecosystem Management
  • Legislation
  • Planning

Effort References

• RCO's PRISM Project Search
• Salmon Recovery Portal
• Ecology's Administration of Grants and Loans
• USACE Regulatory In-lieu Fee and Bank information Tracking System

Wiki Rules

• Wiki text does not reflect the policy or opinion of any agency or organization
• Please adhere to our Social Contract and Style Guide
• Complain here, and be nice.

The Wetland Intrinsic Potential (WIP) tool is a machine learning-based program developed by researchers from the University of Washington and TerrainWorks, in collaboration with the Washington Department of Ecology. Initiated around 2022, the WIP tool aims to enhance wetland identification, particularly for cryptic wetlands obscured by forest canopy or lacking visible standing water. By analyzing multi-scale topographic indicators and remote sensing data, the tool generates probability maps highlighting areas conducive to wetland formation. This approach supports conservation efforts by providing accurate, unbiased wetland inventories, aiding in habitat restoration and management within the Salish Sea watershed.

• https://github.com/TerrainWorks-Seattle/ForestedWetlands
• https://www.nature.com/articles/s41467-024-44888-x

Notes

• The lead, Meghan Halabisky is a research scientist at UW.
• Aims to resolve challenges of identifying wetlands based on aerial sensing, given the diversity of wetland character.
• Still early in development. There is poor training methods.
• Combines imagery, DTM, Hydrologic flow modeling at multiple scales to build a "stack of indicators", relying heavily on multi-scale landform
• Generates continuous raster of wetland probability.
• Designed as an iterative workflow that can be re-run as underlying data is improved.
• Field testing suggest a significant omission of wetlands in National Wetland Inventory
• WDOE is preparing to complete local studies using WIP and LIDAR data.

Questions

• Could this be used for wetland detection in the nearshore?