Examples of semi-automation for mapping Cowardin classes and wetland vegetation in Alaska

Held Thursday, April 27, 2023 - 3:00 pm - 4:00 pm Eastern 

INTRODUCTION

• Ian Grosfelt, National Association of Wetland Managers [POWERPOINT PRESENTATION]

PRESENTER 

• Timm Nawrocki, Alaska Center for Conservation Science [POWERPOINT PRESENTATION]

ABSTRACT

Wetlands mapped according to the Cowardin Classification have frequently been delineated manually. Despite increasingly available remotely sensed data and access to large amounts of computational resources, automated approaches to mapping wetlands have been limited to ecologically coarse approaches. One challenge to automating the mapping of Cowardin classes is that the Cowardin Classification integrates contextual information that may not be directly represented in remotely sensed data. We have implemented a semi-automated strategy for wetland mapping that retains advantages of automation while enabling a wetland scientist to focus on providing the contextual information necessary to assign Cowardin classes. Additionally, we have implemented automated approaches to mapping wetland vegetation that could be modified by a wetland scientist to arrive at Cowardin classes. Semi-automation has potential to improve consistency, accuracy, and cost-efficiency of mapping Cowardin classes in Alaska and other areas where wetlands occupy large proportions of the landscape.

BIO

Timm Nawrocki received a B.S. in Biology from the University of Virginia and a M.S. in Biological Sciences from the University of Alaska Anchorage. He specializes in spatial analyses of terrestrial vegetation, soils, and wildlife; remote sensing; and identification of vascular and non-vascular plants. He is fluent in Python, R, SQL, Javascript, geographic information systems (GIS), and web development including a variety of frameworks, platforms, and languages.

Part 1: Introduction: Ian Grosfelt, National Association of Wetland Managers

Part 1: Introduction: Ian Grosfelt, National Association of Wetland Managers
Presenter: Timm Nawrocki, Alaska Center for Conservation Science, University of Alaska Anchorage

Part 2: Presenter: Timm Nawrocki, Alaska Center for Conservation Science, University of Alaska Anchorage

Part 2: Presenter: Timm Nawrocki, Alaska Center for Conservation Science, University of Alaska Anchorage
Questions & Answers

Mapping Wetland Probabilities: Tools, Models, and Applications

Held Wednesday, February 8, 2023 - 3:00 pm - 4:30 pm Eastern 

 
INTRODUCTION

• Ian Grosfelt, National Association of Wetland Managers [POWERPOINT PRESENTATION]

PRESENTERS 

• Meghan Halabisky, University of Washington Remote Sensing and Geospatial Analysis Lab
• Anthony Stewart, PhD Student, University of Washington
• Andy Robertson, GeoSpatial Services at Saint Mary’s University of Minnesota

ABSTRACTS 

Meghan Halabisky
Accurate, un-biased wetland inventories are critical to monitor and protect wetlands from future harm or land conversion. However, most wetland inventories are constructed through manual image interpretation or automated classification of multi-band imagery and are biased towards wetlands that are easy to detect directly in aerial and satellite imagery. Wetlands that are obscured by forest canopy, occur ephemerally, and those without visible standing water are, therefore, often missing from wetland maps. To aid in detection of these cryptic wetlands, we developed the Wetland Intrinsic Potential tool, based on a wetland indicator framework commonly used on the ground to detect wetlands through the presence of hydrophytic vegetation, hydrology, and hydric soils. Our tool uses a random forest model with spatially explicit input variables that represent all three wetland indicators, including novel multi-scale topographic indicators that represent the processes that drive wetland formation, to derive a map of wetland probability.

Anthony Stewart
Inland wetlands disproportionately contribute to the soil organic (SOC) carbon pool by storing 20-30% of all SOC despite occupying only 5-8% of the land surface. However, difficulty identifying wetland areas under perennial forest canopy increases uncertainty in estimates of SOC stocks across watershed to regional scales. We used a machine learning approach that utilized aerial lidar-derived hydrologic and topographic metrics to characterize the landscape surface and identify areas of potential wetland formation for three study areas in the Pacific Northwest which represent an east-to-west (low-to-high) precipitation gradient. This approach produces a spatially explicit and continuous model of wetland probability as a range from wetland to upland across a landscape. We then collected soil samples and measured SOC stocks along the wetland-to-upland probability gradient and used the probability along with surficial geology corresponding to geomorphology to model SOC stocks.

Andy Robertson
GeoSpatial Services has been focused on landscape level wetland inventory and functional assessment for over two decades. Throughout that time we have explored a variety of data development and classification tools for creating derived data that supports comprehensive resource monitoring and assessment. This presentation described several modelling efforts based on machine learning algorithms, object analysis, derived elevation surfaces, network analysis and high-resolution optical imagery. These techniques include: potential wetland landscapes, potentially restorable wetlands, derived and hydro modified surface hydrology and cumulative impact assessment based on proximity to oil field development and potential contamination. These tools will be presented in the context of wetland program plan development supported by EPA CWA Section 404 grants.

BIOS

Meghan Halabisky is a research scientist at the University of Washington Remote Sensing and Geospatial Analysis Lab (RSGAL). Her interests lie in understanding ecosystem dynamics and landscape change through the development and application of high-resolution remote sensing tools. She completed her PhD at the University of Washington, where she worked to characterize the response of wetland ecosystems to historic and future climate by reconstructing surface water hydrographs for thousands of wetlands in Washington State, and using a combination of aerial and satellite imagery. Meghan has a background in conservation management, having previously worked as an operations planner for the Oahu Invasive Species Committee. She has a concurrent master’s – MS/MPA from the Evans School of Public Affairs at the University of Washington.
   

Anthony Stewart is a PhD student at the University of Washington. He uses remote sensing to map, characterize, and model wetlands and their soil carbon stocks. Particularly, he is interested in small forested wetlands and their role in the greater landscape. 

Andy Robertson is currently Executive Director of GeoSpatial Services at Saint Mary’s University of Minnesota. In this role, Andy is responsible for oversight and management of all GeoSpatial Services projects, activities and staff. GeoSpatial Services is engaged in a wide variety of projects across the Lower 48 and Alaska including: wetland inventory; National Hydrography Dataset updates; spatial data development; and natural resource condition assessments. GeoSpatial Services has been a key partner of the USFWS and has been working for over 18 years to update legacy National Wetland Inventory data across the nation. Andy is a steering committee member for the NAWM Wetland Mapping Consortium, a NAWM Board Member and is past-chair of the Alaska GeoSpatial Council Wetland Technical Working Group.