High-resolution leaf area index maps generated from unoccupied aerial system, Teller Mile 27, Seward Peninsula, Alaska
Abstract
Leaf area index (LAI), a measure of the amount of one-side leaf area per ground unit, is an important indicator of plant carbon, energy, and water cycle. In the heterogeneous Arctic landscapes, it has been challenging to accurately measure LAI across species and space needed for Earth system model validation. Here, we use multispectral unoccupied aerial systems (UASs) to scale up and map leaf area index (LAI) , in a low-Arctic tundra landscape on the Seward Peninsula, Alaska. We linked previous published LAI measurements with high-resolution, UAS-collected multispectral data collected over the region of Next Generation Ecosystem Experiments in the Arctic (NGEE Arctic)’s Teller Mile Maker 27 site in 2022 to develop random forest (RF) machine learning models to predict and map LAI. 100 RF models were developed to account for uncertainties in ground LAI plot measurements and process scaling. This dataset includes a raster (*.tif) map of the mean LAI value of the 100 RF models, a raster (*.tif) map of the standard deviation of the RF-modeled LAI data, and a user guide (*.pdf).
- Authors:
-
- State University of New York at New Paltz
- Los Alamos National Laboratory
- NASA Goddard Space Flight Center
- Oak Ridge National Laboratory
- Publication Date:
- Other Number(s):
- NGA576; LA-UR-25-30098
- DOE Contract Number:
- AC02-05CH11231
- Research Org.:
- Next-Generation Ecosystem Experiments (NGEE) Arctic
- Sponsoring Org.:
- U.S. DOE > Office of Science > Biological and Environmental Research (BER)
- Subject:
- 54 ENVIRONMENTAL SCIENCES; Alaska; EARTH SCIENCE > BIOSPHERE > VEGETATION > LEAF CHARACTERISTICS > LEAF AREA INDEX (LAI); ESS-DIVE File Level Metadata Reporting Format; Seward Peninsula
- OSTI Identifier:
- 2588597
- DOI:
- https://doi.org/10.15485/2588597
Citation Formats
Hanzl, Julia Mei, Farley, Margaret, Serbin, Shawn, and Yang, Daryl. High-resolution leaf area index maps generated from unoccupied aerial system, Teller Mile 27, Seward Peninsula, Alaska. United States: N. p., 2024.
Web. doi:10.15485/2588597.
Hanzl, Julia Mei, Farley, Margaret, Serbin, Shawn, & Yang, Daryl. High-resolution leaf area index maps generated from unoccupied aerial system, Teller Mile 27, Seward Peninsula, Alaska. United States. doi:https://doi.org/10.15485/2588597
Hanzl, Julia Mei, Farley, Margaret, Serbin, Shawn, and Yang, Daryl. 2024.
"High-resolution leaf area index maps generated from unoccupied aerial system, Teller Mile 27, Seward Peninsula, Alaska". United States. doi:https://doi.org/10.15485/2588597. https://www.osti.gov/servlets/purl/2588597. Pub date:Tue Dec 31 23:00:00 EST 2024
@article{osti_2588597,
title = {High-resolution leaf area index maps generated from unoccupied aerial system, Teller Mile 27, Seward Peninsula, Alaska},
author = {Hanzl, Julia Mei and Farley, Margaret and Serbin, Shawn and Yang, Daryl},
abstractNote = {Leaf area index (LAI), a measure of the amount of one-side leaf area per ground unit, is an important indicator of plant carbon, energy, and water cycle. In the heterogeneous Arctic landscapes, it has been challenging to accurately measure LAI across species and space needed for Earth system model validation. Here, we use multispectral unoccupied aerial systems (UASs) to scale up and map leaf area index (LAI) , in a low-Arctic tundra landscape on the Seward Peninsula, Alaska. We linked previous published LAI measurements with high-resolution, UAS-collected multispectral data collected over the region of Next Generation Ecosystem Experiments in the Arctic (NGEE Arctic)’s Teller Mile Maker 27 site in 2022 to develop random forest (RF) machine learning models to predict and map LAI. 100 RF models were developed to account for uncertainties in ground LAI plot measurements and process scaling. This dataset includes a raster (*.tif) map of the mean LAI value of the 100 RF models, a raster (*.tif) map of the standard deviation of the RF-modeled LAI data, and a user guide (*.pdf).},
doi = {10.15485/2588597},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Dec 31 23:00:00 EST 2024},
month = {Tue Dec 31 23:00:00 EST 2024}
}
