IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS
Peatlands occur in ecozones from the tropics to the arctic, and are estimated to globally cover just under 450 million ha, roughly 3-5% of the Earth's land surface [8]. Although they cover a small amount of land globally, peatlands are estimated to store more than 30% of the Earth's soil c...
Published in: | 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS |
---|---|
Main Authors: | , , , , , |
Format: | Text |
Language: | unknown |
Published: |
Digital Commons @ Michigan Tech
2021
|
Subjects: | |
Online Access: | https://digitalcommons.mtu.edu/michigantech-p/16694 https://doi.org/10.1109/IGARSS47720.2021.9553620 |
id |
ftmichigantuniv:oai:digitalcommons.mtu.edu:michigantech-p-35995 |
---|---|
record_format |
openpolar |
spelling |
ftmichigantuniv:oai:digitalcommons.mtu.edu:michigantech-p-35995 2023-05-15T15:08:38+02:00 IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS Bourgeau-Chavez, Laura Battaglia, Michael Poley, Andrew Leisman, Dorthea Graham, Jeremy Grelik, Sarah 2021-01-01T08:00:00Z https://digitalcommons.mtu.edu/michigantech-p/16694 https://doi.org/10.1109/IGARSS47720.2021.9553620 unknown Digital Commons @ Michigan Tech https://digitalcommons.mtu.edu/michigantech-p/16694 https://doi.org/10.1109/IGARSS47720.2021.9553620 Michigan Tech Publications Google earth engine Open SARLabs PALSAR Peatlands SAR Sentinel Wetlands text 2021 ftmichigantuniv https://doi.org/10.1109/IGARSS47720.2021.9553620 2023-01-05T18:49:03Z Peatlands occur in ecozones from the tropics to the arctic, and are estimated to globally cover just under 450 million ha, roughly 3-5% of the Earth's land surface [8]. Although they cover a small amount of land globally, peatlands are estimated to store more than 30% of the Earth's soil carbon (C) and are at risk from land use and climate change. An approach of multi-source SAR and optical imagery from multiple dates in machine learning classifiers has demonstrated to be of high value in accurately mapping peatlands from boreal, temperate and tropical regions. Cloud-computing has recently been integrated into a multi-date SAR-optical wetland classification workflow that has high accuracy for peatland mapping. Leveraging the large datasets in Google Earth Engine and Alaska Satellite Facility's OpenSARLabs is improving our capability to access large optical and SAR datasets to integrate into our processing/analysis workflow that was previously cumbersome and time consuming. Such analysis is allowing for larger regional areas to be mapped more efficiently. In this paper we review one study conducted completely outside of cloud computing and two examples of how cloud computing is improving our wetland mapping capability in terms of efficiency, but also in more robust input data sets. Text Arctic Climate change Alaska Michigan Technological University: Digital Commons @ Michigan Tech Arctic 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS 92 95 |
institution |
Open Polar |
collection |
Michigan Technological University: Digital Commons @ Michigan Tech |
op_collection_id |
ftmichigantuniv |
language |
unknown |
topic |
Google earth engine Open SARLabs PALSAR Peatlands SAR Sentinel Wetlands |
spellingShingle |
Google earth engine Open SARLabs PALSAR Peatlands SAR Sentinel Wetlands Bourgeau-Chavez, Laura Battaglia, Michael Poley, Andrew Leisman, Dorthea Graham, Jeremy Grelik, Sarah IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
topic_facet |
Google earth engine Open SARLabs PALSAR Peatlands SAR Sentinel Wetlands |
description |
Peatlands occur in ecozones from the tropics to the arctic, and are estimated to globally cover just under 450 million ha, roughly 3-5% of the Earth's land surface [8]. Although they cover a small amount of land globally, peatlands are estimated to store more than 30% of the Earth's soil carbon (C) and are at risk from land use and climate change. An approach of multi-source SAR and optical imagery from multiple dates in machine learning classifiers has demonstrated to be of high value in accurately mapping peatlands from boreal, temperate and tropical regions. Cloud-computing has recently been integrated into a multi-date SAR-optical wetland classification workflow that has high accuracy for peatland mapping. Leveraging the large datasets in Google Earth Engine and Alaska Satellite Facility's OpenSARLabs is improving our capability to access large optical and SAR datasets to integrate into our processing/analysis workflow that was previously cumbersome and time consuming. Such analysis is allowing for larger regional areas to be mapped more efficiently. In this paper we review one study conducted completely outside of cloud computing and two examples of how cloud computing is improving our wetland mapping capability in terms of efficiency, but also in more robust input data sets. |
format |
Text |
author |
Bourgeau-Chavez, Laura Battaglia, Michael Poley, Andrew Leisman, Dorthea Graham, Jeremy Grelik, Sarah |
author_facet |
Bourgeau-Chavez, Laura Battaglia, Michael Poley, Andrew Leisman, Dorthea Graham, Jeremy Grelik, Sarah |
author_sort |
Bourgeau-Chavez, Laura |
title |
IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
title_short |
IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
title_full |
IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
title_fullStr |
IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
title_full_unstemmed |
IMPROVING PEATLAND MAPPING AND MONITORING CAPABILITY ACROSS BROAD REGIONS USING SAR IN CLOUD COMPUTING PLATFORMS |
title_sort |
improving peatland mapping and monitoring capability across broad regions using sar in cloud computing platforms |
publisher |
Digital Commons @ Michigan Tech |
publishDate |
2021 |
url |
https://digitalcommons.mtu.edu/michigantech-p/16694 https://doi.org/10.1109/IGARSS47720.2021.9553620 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Alaska |
genre_facet |
Arctic Climate change Alaska |
op_source |
Michigan Tech Publications |
op_relation |
https://digitalcommons.mtu.edu/michigantech-p/16694 https://doi.org/10.1109/IGARSS47720.2021.9553620 |
op_doi |
https://doi.org/10.1109/IGARSS47720.2021.9553620 |
container_title |
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS |
container_start_page |
92 |
op_container_end_page |
95 |
_version_ |
1766339951926968320 |