Detecting forest changes using dense Landsat 8 and Sentinel-1 time series data in tropical seasonal forests

Katsuto Shimizu, Tetsuji Ota, Nobuya Mizoue

研究成果: ジャーナルへの寄稿記事

抄録

The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6% for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3%) or Sentinel-1 (75.5%). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.

元の言語英語
記事番号1899
ジャーナルRemote Sensing
11
発行部数16
DOI
出版物ステータス出版済み - 1 1 2019

Fingerprint

Landsat
time series
disturbance
detection
forest management
seasonality
pixel
synthetic aperture radar

All Science Journal Classification (ASJC) codes

  • Earth and Planetary Sciences(all)

これを引用

Detecting forest changes using dense Landsat 8 and Sentinel-1 time series data in tropical seasonal forests. / Shimizu, Katsuto; Ota, Tetsuji; Mizoue, Nobuya.

:: Remote Sensing, 巻 11, 番号 16, 1899, 01.01.2019.

研究成果: ジャーナルへの寄稿記事

@article{ac82d0a6dfee48f0928249b0896385e8,
title = "Detecting forest changes using dense Landsat 8 and Sentinel-1 time series data in tropical seasonal forests",
abstract = "The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6{\%} for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3{\%}) or Sentinel-1 (75.5{\%}). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.",
author = "Katsuto Shimizu and Tetsuji Ota and Nobuya Mizoue",
year = "2019",
month = "1",
day = "1",
doi = "10.3390/rs11161899",
language = "English",
volume = "11",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "16",

}

TY - JOUR

T1 - Detecting forest changes using dense Landsat 8 and Sentinel-1 time series data in tropical seasonal forests

AU - Shimizu, Katsuto

AU - Ota, Tetsuji

AU - Mizoue, Nobuya

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6% for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3%) or Sentinel-1 (75.5%). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.

AB - The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6% for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3%) or Sentinel-1 (75.5%). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.

UR - http://www.scopus.com/inward/record.url?scp=85071547553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071547553&partnerID=8YFLogxK

U2 - 10.3390/rs11161899

DO - 10.3390/rs11161899

M3 - Article

AN - SCOPUS:85071547553

VL - 11

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 16

M1 - 1899

ER -