Data used in “Enguehard et al. 2022, Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie”

Dataset · Fri Jul 08 04:00:00 EDT 2022

DOI:https://doi.org/10.15485/1876578· OSTI ID:1876578

Enguehard, Lea ^[1]; Falco, Nicola ^[2]; Schmutz, Myriam ^[3]; Newcomer, Michelle E. ^[2]; Ladau, Joshua ^[2]; Brown, James B. ^[2]; Bourgeau-Chavez, Laura; Wainwright, Haruko M. ^[2]

---

1. Lawrence Berkeley National Laboratory; Lawrence Berkeley National Laboratory
2. Lawrence Berkeley National Laboratory
3. Bordeaux Institut National Polytechnique

The package contains the data layers used in “Enguehard et al. 2022, Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie”. Spatial data layers include: topography, wetland vegetation cover, time series of Landsat’s enhanced vegetation index (EVI) between 1990 and 2020. The study aims to characterize coastal wetlands with particular focus on the co-variability between plant dynamics, topography, soil, and other environmental factors. We proposed a functional zonation approach based on machine learning clustering to identify the spatial regions, i.e., zones that capture these co-varied properties. This approach was applied to publicly available datasets along Lake Erie, in the Great Lakes Region

• Research Organization: Environmental System Science Data Infrastructure for a Virtual Ecosystem; COMPASS-FME
• Sponsoring Organization: U.S. DOE > Office of Science > Biological and Environmental Research (BER)
• OSTI ID: 1876578
• Country of Publication: United States
• Language: English

Related Subjects

54 ENVIRONMENTAL SCIENCES
COASTAL WETLANDS
EARTH SCIENCE > LAND SURFACE > TOPOGRAPHY > TERRAIN ELEVATION > DIGITAL ELEVATION/TERRAIN MODEL (DEM)
ECOSYSTEM CHARACTERIZATION
Enhanced Vegetation Index
FUNCTIONAL ZONATION
LAKE ERIE
Land covers
PLANT PRODUCTIVITY
REMOTE SENSING
Soil texture
TERRESTRIAL-ACQUATIC INTERFACE
Topographical metrics