Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance

Disturbance monitoring is an important application of the Landsat times series, both to monitor forest dynamics and to support wise forest management at a variety of spatial and temporal scales. In the last decade, there has been an acceleration in the development of approaches designed to put the L...

Full description

Bibliographic Details
Main Authors: Warren B. Cohen, Sean P. Healey, Zhiqiang Yang, Zhe Zhu, Noel Gorelick
Format: Article
Language:English
Published: MDPI AG 2020-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/12/10/1673
id doaj-35d158d48e6946babe24b264a021c3a1
record_format Article
spelling doaj-35d158d48e6946babe24b264a021c3a12020-11-25T03:05:36ZengMDPI AGRemote Sensing2072-42922020-05-01121673167310.3390/rs12101673Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest DisturbanceWarren B. Cohen0Sean P. Healey1Zhiqiang Yang2Zhe Zhu3Noel Gorelick4Department of Forest Ecosystems and Society, 321 Richardson Hall, Oregon State University, Corvallis, OR 97331, USARocky Mountain Research Station, USDA Forest Service, Ogden, UT 84401, USARocky Mountain Research Station, USDA Forest Service, Ogden, UT 84401, USADepartment of Natural Resources and the Environment, University of Connecticut, Storrs, CT 06269, USAGoogle Switzerland (GmbH) and Department of Geography, University of Zurich, Zurich CH 8002, SwitzerlandDisturbance monitoring is an important application of the Landsat times series, both to monitor forest dynamics and to support wise forest management at a variety of spatial and temporal scales. In the last decade, there has been an acceleration in the development of approaches designed to put the Landsat archive to use towards these causes. Forest disturbance mapping has moved from using individual change-detection algorithms, which implement a single set of decision rules that may not apply well to a range of scenarios, to compiling ensembles of such algorithms. One approach that has greatly reduced disturbance detection error has been to combine individual algorithm outputs in Random Forest (RF) ensembles trained with disturbance reference data, a process called stacking (or secondary classification). Previous research has demonstrated more robust and sensitive detection of disturbance using stacking with both multialgorithm ensembles and multispectral ensembles (which make use of a single algorithm applied to multiple spectral bands). In this paper, we examined several additional dimensions of this problem, including: 1) type of algorithm (represented by processes using one image per year vs. all historical images); 2) spectral band choice (including both the basic Landsat reflectance bands and several popular indices based on those bands); 3) number of algorithm/spectral-band combinations needed; and 4) the value of including both algorithm and spectral band diversity in the ensembles. We found that ensemble performance substantially improved per number of model inputs if those inputs were drawn from a diversity of both algorithms and spectral bands. The best models included inputs from both algorithms, using different variants of shortwave-infrared (SWIR) and near-infrared (NIR) reflectance. Further disturbance detection improvement may depend upon the development of algorithms which either interrogate SWIR and NIR in new ways or better highlight disturbance signals in the visible wavelengths.https://www.mdpi.com/2072-4292/12/10/1673Landsat-time-seriesforest disturbancestackingTimeSyncLandTrendrCOLD
collection DOAJ
language English
format Article
sources DOAJ
author Warren B. Cohen
Sean P. Healey
Zhiqiang Yang
Zhe Zhu
Noel Gorelick
spellingShingle Warren B. Cohen
Sean P. Healey
Zhiqiang Yang
Zhe Zhu
Noel Gorelick
Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
Remote Sensing
Landsat-time-series
forest disturbance
stacking
TimeSync
LandTrendr
COLD
author_facet Warren B. Cohen
Sean P. Healey
Zhiqiang Yang
Zhe Zhu
Noel Gorelick
author_sort Warren B. Cohen
title Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
title_short Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
title_full Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
title_fullStr Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
title_full_unstemmed Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance
title_sort diversity of algorithm and spectral band inputs improves landsat monitoring of forest disturbance
publisher MDPI AG
series Remote Sensing
issn 2072-4292
publishDate 2020-05-01
description Disturbance monitoring is an important application of the Landsat times series, both to monitor forest dynamics and to support wise forest management at a variety of spatial and temporal scales. In the last decade, there has been an acceleration in the development of approaches designed to put the Landsat archive to use towards these causes. Forest disturbance mapping has moved from using individual change-detection algorithms, which implement a single set of decision rules that may not apply well to a range of scenarios, to compiling ensembles of such algorithms. One approach that has greatly reduced disturbance detection error has been to combine individual algorithm outputs in Random Forest (RF) ensembles trained with disturbance reference data, a process called stacking (or secondary classification). Previous research has demonstrated more robust and sensitive detection of disturbance using stacking with both multialgorithm ensembles and multispectral ensembles (which make use of a single algorithm applied to multiple spectral bands). In this paper, we examined several additional dimensions of this problem, including: 1) type of algorithm (represented by processes using one image per year vs. all historical images); 2) spectral band choice (including both the basic Landsat reflectance bands and several popular indices based on those bands); 3) number of algorithm/spectral-band combinations needed; and 4) the value of including both algorithm and spectral band diversity in the ensembles. We found that ensemble performance substantially improved per number of model inputs if those inputs were drawn from a diversity of both algorithms and spectral bands. The best models included inputs from both algorithms, using different variants of shortwave-infrared (SWIR) and near-infrared (NIR) reflectance. Further disturbance detection improvement may depend upon the development of algorithms which either interrogate SWIR and NIR in new ways or better highlight disturbance signals in the visible wavelengths.
topic Landsat-time-series
forest disturbance
stacking
TimeSync
LandTrendr
COLD
url https://www.mdpi.com/2072-4292/12/10/1673
work_keys_str_mv AT warrenbcohen diversityofalgorithmandspectralbandinputsimproveslandsatmonitoringofforestdisturbance
AT seanphealey diversityofalgorithmandspectralbandinputsimproveslandsatmonitoringofforestdisturbance
AT zhiqiangyang diversityofalgorithmandspectralbandinputsimproveslandsatmonitoringofforestdisturbance
AT zhezhu diversityofalgorithmandspectralbandinputsimproveslandsatmonitoringofforestdisturbance
AT noelgorelick diversityofalgorithmandspectralbandinputsimproveslandsatmonitoringofforestdisturbance
_version_ 1724677667298476032