Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019)
Prescribed fires and wildfires are common in wetland ecosystems across the Southeastern United States. However, the wetland burned area has been chronically underestimated across the region due to (1) spectral confusion between open water and burned area, (2) rapid post-fire vegetation regrowth, and...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Fire |
Subjects: | |
Online Access: | https://www.mdpi.com/2571-6255/4/3/52 |
id |
doaj-17d1039cf7bf44439e72f332cc4490e5 |
---|---|
record_format |
Article |
spelling |
doaj-17d1039cf7bf44439e72f332cc4490e52021-09-26T00:08:15ZengMDPI AGFire2571-62552021-08-014525210.3390/fire4030052Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019)Melanie K. Vanderhoof0Todd J. Hawbaker1Casey Teske2Andrea Ku3Joe Noble4Josh Picotte5U.S. Geological Survey, Geosciences and Environmental Change Science Center, Denver Federal Center, MS980, Denver, CO 80225, USAU.S. Geological Survey, Geosciences and Environmental Change Science Center, Denver Federal Center, MS980, Denver, CO 80225, USAUS Fish and Wildlife Service, Fire Management Branch, 3833 S Development Ave., Boise, ID 83705, USAU.S. Geological Survey, Geosciences and Environmental Change Science Center, Denver Federal Center, MS980, Denver, CO 80225, USATall Timbers Research Station, 13093 Henry Beadel Dr, Tallahassee, FL 32312, USAASRC Federal Data Solutions Contractor to USGS Earth Resource Observation and Science (EROS) Center, Sioux Falls, SD 57198, USAPrescribed fires and wildfires are common in wetland ecosystems across the Southeastern United States. However, the wetland burned area has been chronically underestimated across the region due to (1) spectral confusion between open water and burned area, (2) rapid post-fire vegetation regrowth, and (3) high annual precipitation limiting clear-sky satellite observations. We developed a machine learning algorithm specifically for burned area in wetlands, and applied the algorithm to the Sentinel-2 archive (2016–2019) across the Southeastern US (>290,000 km<sup>2</sup>). Combining Landsat-8 imagery with Sentinel-2 increased the annual clear-sky observation count from 17 to 46 in 2016 and from 16 to 78 in 2019. When validated with WorldView imagery, the Sentinel-2 burned area had a 29% and 30% omission and commission rates of error for burned area, respectively, compared to the US Geological Survey Landsat-8 Burned Area Product (L8 BA), which had a 47% and 8% omission and commission rate of error, respectively. The Sentinel-2 algorithm and the L8 BA mapped burned area within 78% and 60% of wetland fire perimeters (<i>n</i> = 555) compiled from state and federal agencies, respectively. This analysis demonstrated the potential of Sentinel-2 to support efforts to track the burned area, especially across challenging ecosystem types, such as wetlands.https://www.mdpi.com/2571-6255/4/3/52droughtEvergladesGoogle Earth Enginemachine learningprescribed firewildland fire |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Melanie K. Vanderhoof Todd J. Hawbaker Casey Teske Andrea Ku Joe Noble Josh Picotte |
spellingShingle |
Melanie K. Vanderhoof Todd J. Hawbaker Casey Teske Andrea Ku Joe Noble Josh Picotte Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) Fire drought Everglades Google Earth Engine machine learning prescribed fire wildland fire |
author_facet |
Melanie K. Vanderhoof Todd J. Hawbaker Casey Teske Andrea Ku Joe Noble Josh Picotte |
author_sort |
Melanie K. Vanderhoof |
title |
Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) |
title_short |
Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) |
title_full |
Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) |
title_fullStr |
Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) |
title_full_unstemmed |
Mapping Wetland Burned Area from Sentinel-2 across the Southeastern United States and Its Contributions Relative to Landsat-8 (2016–2019) |
title_sort |
mapping wetland burned area from sentinel-2 across the southeastern united states and its contributions relative to landsat-8 (2016–2019) |
publisher |
MDPI AG |
series |
Fire |
issn |
2571-6255 |
publishDate |
2021-08-01 |
description |
Prescribed fires and wildfires are common in wetland ecosystems across the Southeastern United States. However, the wetland burned area has been chronically underestimated across the region due to (1) spectral confusion between open water and burned area, (2) rapid post-fire vegetation regrowth, and (3) high annual precipitation limiting clear-sky satellite observations. We developed a machine learning algorithm specifically for burned area in wetlands, and applied the algorithm to the Sentinel-2 archive (2016–2019) across the Southeastern US (>290,000 km<sup>2</sup>). Combining Landsat-8 imagery with Sentinel-2 increased the annual clear-sky observation count from 17 to 46 in 2016 and from 16 to 78 in 2019. When validated with WorldView imagery, the Sentinel-2 burned area had a 29% and 30% omission and commission rates of error for burned area, respectively, compared to the US Geological Survey Landsat-8 Burned Area Product (L8 BA), which had a 47% and 8% omission and commission rate of error, respectively. The Sentinel-2 algorithm and the L8 BA mapped burned area within 78% and 60% of wetland fire perimeters (<i>n</i> = 555) compiled from state and federal agencies, respectively. This analysis demonstrated the potential of Sentinel-2 to support efforts to track the burned area, especially across challenging ecosystem types, such as wetlands. |
topic |
drought Everglades Google Earth Engine machine learning prescribed fire wildland fire |
url |
https://www.mdpi.com/2571-6255/4/3/52 |
work_keys_str_mv |
AT melaniekvanderhoof mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 AT toddjhawbaker mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 AT caseyteske mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 AT andreaku mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 AT joenoble mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 AT joshpicotte mappingwetlandburnedareafromsentinel2acrossthesoutheasternunitedstatesanditscontributionsrelativetolandsat820162019 |
_version_ |
1717366911233163264 |