Wetlands in the state of Arizona
December 1, 2023
We created a single map of surface water presence by intersecting water classes from available land cover products (National Wetland Inventory, Gap Analysis Program, National Land Cover Database, and Dynamic Surface Water Extent) across the U.S. state of Arizona. We derived classified samples for four wetland classes from the harmonized map: water, herbaceous wetlands, wooded wetlands, and non-wetland cover. In Google Earth Engine (GEE) we developed a random forest model that combined the training data with spatially explicit predictor variables of vegetation greenness indices, wetness indices, seasonal index variation, topographic variables, and hydrologic parameters. The final product is a wall-to-wall map of general wetland types covering all of Arizona. Results show that the final model separates the four wetland classes with an overall accuracy of 86.2%. This data release comprises the raster map file (TIF format) resulting from the training data and random forest model. The 30-m resolution map has 4 classes: not water or wetland (class 0), open water (class 1), herbaceous wetland (class 2), and wooded wetland (class 3).
Citation Information
Publication Year | 2023 |
---|---|
Title | Wetlands in the state of Arizona |
DOI | 10.5066/P9BC3WKD |
Authors | Christopher E Soulard, Jessica J Walker, Britt W Smith, Jason R Kreitler |
Product Type | Data Release |
Record Source | USGS Asset Identifier Service (AIS) |
USGS Organization | Western Geographic Science Center - Main Office |
Rights | This work is marked with CC0 1.0 Universal |
Related
The feasibility of using national-scale datasets for classifying wetlands in Arizona with machine learning
The advent of machine learning techniques has led to a proliferation of landscape classification products. These approaches can fill gaps in wetland inventories across the United States (U.S.) provided that large reference datasets are available to develop accurate models. In this study, we tested the feasibility of expediting the classification process by sourcing requisite training and...
Authors
Christopher Soulard, Jessica J. Walker, Britt Windsor Smith, Jason R. Kreitler
Christopher Soulard
Supervisory Research Geographer
Supervisory Research Geographer
Email
Phone
Britt W Smith
Geographer
Geographer
Email
Related
The feasibility of using national-scale datasets for classifying wetlands in Arizona with machine learning
The advent of machine learning techniques has led to a proliferation of landscape classification products. These approaches can fill gaps in wetland inventories across the United States (U.S.) provided that large reference datasets are available to develop accurate models. In this study, we tested the feasibility of expediting the classification process by sourcing requisite training and...
Authors
Christopher Soulard, Jessica J. Walker, Britt Windsor Smith, Jason R. Kreitler
Christopher Soulard
Supervisory Research Geographer
Supervisory Research Geographer
Email
Phone
Britt W Smith
Geographer
Geographer
Email