Utility of hyperspectral compared to multispectral remote sensing data in estimating forest biomass and structure variables in Finnish boreal forest

Eelis Halme, Petri Pellikka, Matti Mõttus

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Three-quarters of Finland’s land surface area is filled with forests, which compose a great part of the country’s biomass, carbon pools and carbon sinks. In order to acquire up-to-date information on the forests, optical remote sensing techniques are commonly used. Moreover, in the future hyperspectral satellite missions will start providing data to support the needs of natural resource management practices, such as forestry. It is, however, unclear what would be the additional value from using hyperspectral data compared to multispectral in quantifying forest variables of Finnish boreal forest. In this study, we used the remote sensing data by hyperspectral AISA imager (128 bands, 400–1000 nm, resolution 0.7 m) and Sentinel-2 (10 bands, resolution 10 m) to assess the possible benefits of higher spectral resolution. As reference data, we used a new nationwide forest resource dataset (stand-level data), which has a high potential in further remote sensing applications. In addition, we used a set of independent in situ measurements (plot-level data) for validation. We applied two kernel-based machine learning regression algorithms (Gaussian process and support vector regression) to relate boreal forest variables with the remote sensing data. The variables of interest were mean height, basal area, leaf area index (LAI), stem biomass and main tree species. The regression algorithms were trained with stand-level data and estimations were evaluated with stand- and plot-level holdout sets. The estimation accuracies were examined with absolute and relative root-mean-square errors. Successful variable estimations showed that kernel-based regression algorithms are suitable tools for forest structure estimation. Based on the results, the additional value of hyperspectral remote sensing data in forest variable estimation in Finnish boreal forest is mainly related to variables with species-specific information, such as main tree species and LAI. The more interesting variables for forestry industry, such as mean height, basal area and stem biomass, can also be estimated accurately with more traditional multispectral remote sensing data.
Original languageEnglish
Article number101942
JournalInternational Journal of Applied Earth Observation and Geoinformation
Volume83
DOIs
Publication statusPublished - 23 Aug 2019
MoE publication typeA1 Journal article-refereed

Fingerprint

boreal forest
Remote sensing
Biomass
remote sensing
biomass
Forestry
Natural resources management
Carbon
basal area
leaf area index
Spectral resolution
forestry
Image sensors
Mean square error
Learning systems
stem
Satellites
satellite mission
carbon sink
forest resource

Keywords

  • Hyperspectral imaging
  • Sentinel-2
  • Forest structure variables
  • Machine learning
  • Support vector regression
  • Gaussian process regression

Cite this

@article{2ae6cec0220e43f1a8728ac38c3110d9,
title = "Utility of hyperspectral compared to multispectral remote sensing data in estimating forest biomass and structure variables in Finnish boreal forest",
abstract = "Three-quarters of Finland’s land surface area is filled with forests, which compose a great part of the country’s biomass, carbon pools and carbon sinks. In order to acquire up-to-date information on the forests, optical remote sensing techniques are commonly used. Moreover, in the future hyperspectral satellite missions will start providing data to support the needs of natural resource management practices, such as forestry. It is, however, unclear what would be the additional value from using hyperspectral data compared to multispectral in quantifying forest variables of Finnish boreal forest. In this study, we used the remote sensing data by hyperspectral AISA imager (128 bands, 400–1000 nm, resolution 0.7 m) and Sentinel-2 (10 bands, resolution 10 m) to assess the possible benefits of higher spectral resolution. As reference data, we used a new nationwide forest resource dataset (stand-level data), which has a high potential in further remote sensing applications. In addition, we used a set of independent in situ measurements (plot-level data) for validation. We applied two kernel-based machine learning regression algorithms (Gaussian process and support vector regression) to relate boreal forest variables with the remote sensing data. The variables of interest were mean height, basal area, leaf area index (LAI), stem biomass and main tree species. The regression algorithms were trained with stand-level data and estimations were evaluated with stand- and plot-level holdout sets. The estimation accuracies were examined with absolute and relative root-mean-square errors. Successful variable estimations showed that kernel-based regression algorithms are suitable tools for forest structure estimation. Based on the results, the additional value of hyperspectral remote sensing data in forest variable estimation in Finnish boreal forest is mainly related to variables with species-specific information, such as main tree species and LAI. The more interesting variables for forestry industry, such as mean height, basal area and stem biomass, can also be estimated accurately with more traditional multispectral remote sensing data.",
keywords = "Hyperspectral imaging, Sentinel-2, Forest structure variables, Machine learning, Support vector regression, Gaussian process regression",
author = "Eelis Halme and Petri Pellikka and Matti M{\~o}ttus",
year = "2019",
month = "8",
day = "23",
doi = "10.1016/j.jag.2019.101942",
language = "English",
volume = "83",
journal = "International Journal of Applied Earth Observation and Geoinformation",
issn = "1569-8432",
publisher = "Elsevier",

}

TY - JOUR

T1 - Utility of hyperspectral compared to multispectral remote sensing data in estimating forest biomass and structure variables in Finnish boreal forest

AU - Halme, Eelis

AU - Pellikka, Petri

AU - Mõttus, Matti

PY - 2019/8/23

Y1 - 2019/8/23

N2 - Three-quarters of Finland’s land surface area is filled with forests, which compose a great part of the country’s biomass, carbon pools and carbon sinks. In order to acquire up-to-date information on the forests, optical remote sensing techniques are commonly used. Moreover, in the future hyperspectral satellite missions will start providing data to support the needs of natural resource management practices, such as forestry. It is, however, unclear what would be the additional value from using hyperspectral data compared to multispectral in quantifying forest variables of Finnish boreal forest. In this study, we used the remote sensing data by hyperspectral AISA imager (128 bands, 400–1000 nm, resolution 0.7 m) and Sentinel-2 (10 bands, resolution 10 m) to assess the possible benefits of higher spectral resolution. As reference data, we used a new nationwide forest resource dataset (stand-level data), which has a high potential in further remote sensing applications. In addition, we used a set of independent in situ measurements (plot-level data) for validation. We applied two kernel-based machine learning regression algorithms (Gaussian process and support vector regression) to relate boreal forest variables with the remote sensing data. The variables of interest were mean height, basal area, leaf area index (LAI), stem biomass and main tree species. The regression algorithms were trained with stand-level data and estimations were evaluated with stand- and plot-level holdout sets. The estimation accuracies were examined with absolute and relative root-mean-square errors. Successful variable estimations showed that kernel-based regression algorithms are suitable tools for forest structure estimation. Based on the results, the additional value of hyperspectral remote sensing data in forest variable estimation in Finnish boreal forest is mainly related to variables with species-specific information, such as main tree species and LAI. The more interesting variables for forestry industry, such as mean height, basal area and stem biomass, can also be estimated accurately with more traditional multispectral remote sensing data.

AB - Three-quarters of Finland’s land surface area is filled with forests, which compose a great part of the country’s biomass, carbon pools and carbon sinks. In order to acquire up-to-date information on the forests, optical remote sensing techniques are commonly used. Moreover, in the future hyperspectral satellite missions will start providing data to support the needs of natural resource management practices, such as forestry. It is, however, unclear what would be the additional value from using hyperspectral data compared to multispectral in quantifying forest variables of Finnish boreal forest. In this study, we used the remote sensing data by hyperspectral AISA imager (128 bands, 400–1000 nm, resolution 0.7 m) and Sentinel-2 (10 bands, resolution 10 m) to assess the possible benefits of higher spectral resolution. As reference data, we used a new nationwide forest resource dataset (stand-level data), which has a high potential in further remote sensing applications. In addition, we used a set of independent in situ measurements (plot-level data) for validation. We applied two kernel-based machine learning regression algorithms (Gaussian process and support vector regression) to relate boreal forest variables with the remote sensing data. The variables of interest were mean height, basal area, leaf area index (LAI), stem biomass and main tree species. The regression algorithms were trained with stand-level data and estimations were evaluated with stand- and plot-level holdout sets. The estimation accuracies were examined with absolute and relative root-mean-square errors. Successful variable estimations showed that kernel-based regression algorithms are suitable tools for forest structure estimation. Based on the results, the additional value of hyperspectral remote sensing data in forest variable estimation in Finnish boreal forest is mainly related to variables with species-specific information, such as main tree species and LAI. The more interesting variables for forestry industry, such as mean height, basal area and stem biomass, can also be estimated accurately with more traditional multispectral remote sensing data.

KW - Hyperspectral imaging

KW - Sentinel-2

KW - Forest structure variables

KW - Machine learning

KW - Support vector regression

KW - Gaussian process regression

U2 - 10.1016/j.jag.2019.101942

DO - 10.1016/j.jag.2019.101942

M3 - Article

VL - 83

JO - International Journal of Applied Earth Observation and Geoinformation

JF - International Journal of Applied Earth Observation and Geoinformation

SN - 1569-8432

M1 - 101942

ER -