Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method
Foliage fuel load (FFL) is a critical factor affecting crown fire intensity and rate of spread. Satellite observations provide the potential for monitoring FFL dynamics across large areas. Previous studies commonly used empirical methods to estimate FFL, which potentially lacks reproducibility. This...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9363533/ |
id |
doaj-058157527f0546fe9187456a9577940c |
---|---|
record_format |
Article |
spelling |
doaj-058157527f0546fe9187456a9577940c2021-06-03T23:07:56ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01145100511010.1109/JSTARS.2021.30620739363533Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning MethodXingwen Quan0https://orcid.org/0000-0001-5344-1801Yanxi Li1Binbin He2https://orcid.org/0000-0002-0668-6520Geoffrey J. Cary3Gengke Lai4School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaFenner School of Environment and Society, Australian National University, Canberra, ACT, AustraliaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaFoliage fuel load (FFL) is a critical factor affecting crown fire intensity and rate of spread. Satellite observations provide the potential for monitoring FFL dynamics across large areas. Previous studies commonly used empirical methods to estimate FFL, which potentially lacks reproducibility. This study applied Landsat 7 ETM+ and 8 OLI data for FFL retrieval using radiative transfer model (RTM) and machine learning method. To this end, the GeoSail, SAIL, and PROSPECT RTMs were first coupled together to model the near-realistic scenario of a two-layered forest structure. Second, available ecological information was applied to constrain the coupled RTM modeling phases in order to decrease the probability of generating unrealistic simulations. Third, the coupled RTMs were linked to three machine learning models—random forest, support vector machine, and multilayer perceptron—as well as the traditional lookup table. Finally, the performance of each method was validated by FFL measurements from Southwest China and Sweden. The resulting multilayer perceptron (<italic>R</italic><sup>2</sup> = 0.77, RMSE = 0.13, and rRMSE = 0.43) outperformed the other three methods. The evaluation of the applicability of the FFL estimates was conducted in a southwest China forest where two occurred in 2014 and 2020. The FFL dynamics from 2013 through 2020 showed that the fire was likely to occur when the FFL accumulated to a critical point (around 27 × 10<sup>6</sup> kg), highlighting the relevance of remote sensing derived FFL estimates for understanding potential fire occurrence.https://ieeexplore.ieee.org/document/9363533/Firefire dangerfoliage fuel load (FFL)forestinversionLandsat |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xingwen Quan Yanxi Li Binbin He Geoffrey J. Cary Gengke Lai |
spellingShingle |
Xingwen Quan Yanxi Li Binbin He Geoffrey J. Cary Gengke Lai Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Fire fire danger foliage fuel load (FFL) forest inversion Landsat |
author_facet |
Xingwen Quan Yanxi Li Binbin He Geoffrey J. Cary Gengke Lai |
author_sort |
Xingwen Quan |
title |
Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method |
title_short |
Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method |
title_full |
Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method |
title_fullStr |
Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method |
title_full_unstemmed |
Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method |
title_sort |
application of landsat etm+ and oli data for foliage fuel load monitoring using radiative transfer model and machine learning method |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2021-01-01 |
description |
Foliage fuel load (FFL) is a critical factor affecting crown fire intensity and rate of spread. Satellite observations provide the potential for monitoring FFL dynamics across large areas. Previous studies commonly used empirical methods to estimate FFL, which potentially lacks reproducibility. This study applied Landsat 7 ETM+ and 8 OLI data for FFL retrieval using radiative transfer model (RTM) and machine learning method. To this end, the GeoSail, SAIL, and PROSPECT RTMs were first coupled together to model the near-realistic scenario of a two-layered forest structure. Second, available ecological information was applied to constrain the coupled RTM modeling phases in order to decrease the probability of generating unrealistic simulations. Third, the coupled RTMs were linked to three machine learning models—random forest, support vector machine, and multilayer perceptron—as well as the traditional lookup table. Finally, the performance of each method was validated by FFL measurements from Southwest China and Sweden. The resulting multilayer perceptron (<italic>R</italic><sup>2</sup> = 0.77, RMSE = 0.13, and rRMSE = 0.43) outperformed the other three methods. The evaluation of the applicability of the FFL estimates was conducted in a southwest China forest where two occurred in 2014 and 2020. The FFL dynamics from 2013 through 2020 showed that the fire was likely to occur when the FFL accumulated to a critical point (around 27 × 10<sup>6</sup> kg), highlighting the relevance of remote sensing derived FFL estimates for understanding potential fire occurrence. |
topic |
Fire fire danger foliage fuel load (FFL) forest inversion Landsat |
url |
https://ieeexplore.ieee.org/document/9363533/ |
work_keys_str_mv |
AT xingwenquan applicationoflandsatetmx002bandolidataforfoliagefuelloadmonitoringusingradiativetransfermodelandmachinelearningmethod AT yanxili applicationoflandsatetmx002bandolidataforfoliagefuelloadmonitoringusingradiativetransfermodelandmachinelearningmethod AT binbinhe applicationoflandsatetmx002bandolidataforfoliagefuelloadmonitoringusingradiativetransfermodelandmachinelearningmethod AT geoffreyjcary applicationoflandsatetmx002bandolidataforfoliagefuelloadmonitoringusingradiativetransfermodelandmachinelearningmethod AT gengkelai applicationoflandsatetmx002bandolidataforfoliagefuelloadmonitoringusingradiativetransfermodelandmachinelearningmethod |
_version_ |
1721398527487115264 |