Geospatial data, high-resolution terrain models and machine learning are creating new ways to understand what’s happening on the ground. These technologies already are influencing fields such as traffic management, agricultural production, infrastructure maintenance, watershed planning and environmental protection. One especially useful example is the Wetland Intrinsic Potential (WIP) tool, developed by researchers at the University of Washington in Seattle. WIP uses multivariable datasets, lidar-derived terrain information, multi-scale topographic analysis and a random forest machine-learning model to identify wetlands that may be missed by conventional mapping methods.

For engineers, planners, watershed managers and environmental professionals, better wetland screening is more than an academic exercise. Wetlands influence flood storage, stormwater routing, groundwater recharge, habitat protection, permitting and land-use decisions. When existing inventories miss small, seasonal, forested or otherwise difficult-to-detect wetlands, project teams may underestimate site constraints or overlook important hydrologic functions.

WIP was specifically developed to help locate “cryptic wetlands” that can be difficult to detect because they’re seasonally inundated, hidden beneath forest canopy, obscured by terrain or lacking visible standing water when aerial imagery is collected. Instead of relying only on direct visual indicators, WIP uses spatially derived proxies for wetland indicators such as hydrology, hydrophytic vegetation and hydric soils. In the Hoh River watershed test case in Washington, the tool identified 17,300 acres (27.0 square miles) of wetlands using a 0.5 probability threshold, compared with 7,500 acres (11.7 square miles) mapped by the National Wetlands Inventory.

WIP also reflects a broader movement in water resources and land-surface mapping: using newer geospatial technologies to build more detailed, accessible and up-to-date information for planning and resource management. Related national efforts, such as the U.S. Geological Survey (USGS) 3D National Topography Model, are similarly focused on improving and integrating elevation and hydrography data to support data-driven decisions.

Topography, Hidden Hydrology and Wetland Indicators

Scientists and wetland professionals have long relied on three key indicators when identifying wetlands in the field: 1) hydrophytic vegetation, 2) hydric soils and 3) wetland hydrology. WIP follows this same conceptual framework, but uses topographic and remotely sensed clues to detect the hydrologic systems that often support wetland formation.

Changes in elevation, slope gradient, land-surface curvature, depth to water, flow accumulation and other terrain attributes can reveal a lot about surface and subsurface flows, saturated soils, drainage patterns and locations where hydrophytic vegetation is more likely to occur. These indicators are especially useful where wetlands are difficult to see directly from imagery or where field access is limited.

National Agriculture Imagery Program data, USGS hydrography data, soils data, lidar-derived digital elevation models and other datasets can be used to derive important wetland indicators. These include hydraulic conductivity, soil traits influencing water retention or drainage, wetland-associated vegetation, depth-to-water indices, topographic wetness indices and other hydrologic indicators evaluated at multiple spatial scales. Considered together, these indicators provide a probability-based view of wetland potential across a given area of interest.

Training and Testing the WIP

In simplified terms, the Hoh River watershed model was trained using a multiphase process designed to minimize bias and produce a realistic reference dataset. The process used the National Wetlands Inventory, image interpretation, available landscape datasets and limited field verification to develop wetland and non-wetland reference points for model training and testing.

After training, the model evaluates the input datasets and generates a probability of wetland presence for each digital elevation model grid cell or pixel. Users then can set a probability threshold for classifying areas as wetlands. In the Hoh River watershed example, a threshold of 0.5 was used. A lower threshold would classify more land area as potential wetland, while a higher threshold would reduce the area classified as wetland. This probability-based output provides a more-nuanced picture than a simple binary wetland/non-wetland map, particularly in areas with gradual wet-to-dry transitions.

Beyond identifying additional wetland area, WIP also reduced the number of wetlands likely missed; this often is called “omission error,” meaning areas that actually are wetlands but aren’t identified as wetlands in the map or model output. In the Hoh River watershed test case, WIP reduced this missed-wetland error by more than 33 percent compared with the National Wetlands Inventory, while also improving the overall accuracy of wetland identification by approximately 8 percent. This suggests WIP can be especially useful as a screening tool in places where small, seasonal, forested or otherwise difficult-to-detect wetlands may be overlooked by existing inventories.

WIP developers recognize that wetlands display unique characteristics in different regions of the world. Accordingly, WIP is flexible—available as an ArcGIS toolbox and designed to allow users to modify the analysis and integrate region-specific landscape clues or wetland indices. New applications require region-specific training data, but the potential uses are broad. For example, a town could use WIP to support a local well-protection program. Similarly, a coastal community could use it to better understand wetland extents for shoreline erosion control and climate adaptation, as was recently done on the “Big Island” of Hawaii.

At the same time, WIP should be understood as a complementary screening and mapping tool rather than a replacement for established wetland identification protocols. Field investigation, regulatory review and formal wetland delineation procedures remain necessary where precise boundaries or permitting decisions are required. The value of WIP is that it can help planners and project teams identify areas that warrant closer review, especially where conventional mapping may miss less-visible wetlands.

Building Tools that Advance Resource Management

In recent years, there has been a marked increase in technologies designed to purify, reuse, monitor and safeguard surface water and groundwater resources. The steady rise in Managed Aquifer Recharge projects illustrates this trend. There’s no better time to restore watershed planning initiatives and strengthen a true “one water” management framework.

It’s in the public interest to continue building a deeper understanding of complex hydrologic systems such as wetlands, which provide important infrastructure and ecosystem services such as stormwater filtration, flood mitigation, groundwater recharge, wildlife habitat, carbon storage and support for broader watershed resilience.

The growth of methodologies that combine geospatial data, terrain analysis, remote sensing and machine learning charts a path toward more integrated and fact-based decision-making. Tools that help us locate and understand hydrologic systems—and the many interconnected parts that sustain them—can only advance the critical water-resource planning, protection and restoration efforts needed in the years ahead.