Combining Sentinel-1 and Landsat 8 Does Not Improve Classification Accuracy of Tropical Selective Logging

被引:3
作者
Hethcoat, Matthew G. [1 ,2 ,3 ]
Carreiras, Joao M. B. [1 ,4 ]
Bryant, Robert G. [5 ]
Quegan, Shaun [1 ,4 ]
Edwards, David P. [2 ]
机构
[1] Univ Sheffield, Sch Math & Stat, Environm Dynam Grp, Sheffield S3 7RH, S Yorkshire, England
[2] Univ Sheffield, Sch Biosci, Ecol & Evolutionary Biol, Sheffield S10 2TN, S Yorkshire, England
[3] Univ Sheffield, Grantham Ctr Sustainable Futures, Sheffield S10 2TN, S Yorkshire, England
[4] Univ Sheffield, Natl Ctr Earth Observat, Sheffield S3 7RH, S Yorkshire, England
[5] Univ Sheffield, Dept Geog, Sheffield S3 7ND, S Yorkshire, England
基金
英国自然环境研究理事会;
关键词
Brazil; degradation; forest disturbance; Grey Level Co-occurrence Matrix (GLCM); optical; random forest; reduced-impact logging; satellite; synthetic aperture radar; tropical forest; TIME-SERIES; FOREST; DEFORESTATION; IMPACTS; BIODIVERSITY; DISTURBANCE; SATELLITE;
D O I
10.3390/rs14010179
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Tropical forests play a key role in the global carbon and hydrological cycles, maintaining biological diversity, slowing climate change, and supporting the global economy and local livelihoods. Yet, rapidly growing populations are driving continued degradation of tropical forests to supply wood products. The United Nations (UN) has developed the Reducing Emissions from Deforestation and Forest Degradation (REDD+) programme to mitigate climate impacts and biodiversity losses through improved forest management. Consistent and reliable systems are still needed to monitor tropical forests at large scales, however, degradation has largely been left out of most REDD+ reporting given the lack of effective monitoring and countries mainly focus on deforestation. Recent advances in combining optical data and Synthetic Aperture Radar (SAR) data have shown promise for improved ability to monitor forest losses, but it remains unclear if similar improvements could be made in detecting and mapping forest degradation. We used detailed selective logging records from three lowland tropical forest regions in the Brazilian Amazon to test the effectiveness of combining Landsat 8 and Sentinel-1 for selective logging detection. We built Random Forest models to classify pixel-based differences in logged and unlogged regions to understand if combining optical and SAR improved the detection capabilities over optical data alone. We found that the classification accuracy of models utilizing optical data from Landsat 8 alone were slightly higher than models that combined Sentinel-1 and Landsat 8. In general, detection of selective logging was high with both optical only and optical-SAR combined models, but our results show that the optical data was dominating the predictive performance and adding SAR data introduced noise, lowering the detection of selective logging. While we have shown limited capabilities with C-band SAR, the anticipated opening of the ALOS-PALSAR archives and the anticipated launch of NISAR and BIOMASS in 2023 should stimulate research investigating similar methods to understand if longer wavelength SAR might improve classification of areas affected by selective logging when combined with optical data.
引用
收藏
页数:15
相关论文
共 62 条
  • [1] Selective logging in the Brazilian Amazon
    Asner, GP
    Knapp, DE
    Broadbent, EN
    Oliveira, PJC
    Keller, M
    Silva, JN
    [J]. SCIENCE, 2005, 310 (5747) : 480 - 482
  • [2] Condition and fate of logged forests in the Brazilian Amazon
    Asner, Gregory P.
    Broadbent, Eben N.
    Oliveira, Paulo J. C.
    Keller, Michael
    Knapp, David E.
    Silva, Jose N. M.
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2006, 103 (34) : 12947 - 12950
  • [3] Asner GP, 2009, GEOPHYS MONOGR SER, V186, P25, DOI 10.1029/2008GM000723
  • [4] Tropical forests are a net carbon source based on aboveground measurements of gain and loss
    Baccini, A.
    Walker, W.
    Carvalho, L.
    Farina, M.
    Sulla-Menashe, D.
    Houghton, R. A.
    [J]. SCIENCE, 2017, 358 (6360) : 230 - 233
  • [5] SAR data for tropical forest disturbance alerts in French Guiana: Benefit over optical imagery
    Ballere, Marie
    Bouvet, Alexandre
    Mermoz, Stephane
    Le Toan, Thuy
    Koleck, Thierry
    Bedeau, Caroline
    Andre, Mathilde
    Forestier, Elodie
    Frison, Pierre-Louis
    Lardeux, Cedric
    [J]. REMOTE SENSING OF ENVIRONMENT, 2021, 252
  • [6] Anthropogenic disturbance in tropical forests can double biodiversity loss from deforestation
    Barlow, Jos
    Lennox, Gareth D.
    Ferreira, Joice
    Berenguer, Erika
    Lees, Alexander C.
    Mac Nally, Ralph
    Thomson, James R.
    de Barros Ferraz, Silvio Frosini
    Louzada, Julio
    Fonseca Oliveira, Victor Hugo
    Parry, Luke
    de Castro Solar, Ricardo Ribeiro
    Vieira, Ima C. G.
    Aragao, Luiz E. O. C.
    Begotti, Rodrigo Anzolin
    Braga, Rodrigo F.
    Cardoso, Thiago Moreira
    de Oliveira, Raimundo Cosme, Jr.
    Souza, Carlos M., Jr.
    Moura, Nargila G.
    Nunes, Samia Serra
    Siqueira, Joao Victor
    Pardini, Renata
    Silveira, Juliana M.
    Vaz-de-Mello, Fernando Z.
    Stulpen Veiga, Ruan Carlo
    Venturieri, Adriano
    Gardner, Toby A.
    [J]. NATURE, 2016, 535 (7610) : 144 - +
  • [7] Impacts of selective logging on tree diversity across a rainforest landscape: the importance of spatial scale
    Berry, Nicholas J.
    Phillips, Oliver L.
    Ong, Robert C.
    Hamer, Keith C.
    [J]. LANDSCAPE ECOLOGY, 2008, 23 (08) : 915 - 929
  • [8] Improved timber harvest techniques maintain biodiversity in tropical forests
    Bicknell, Jake E.
    Struebig, Matthew J.
    Edwards, David P.
    Davies, Zoe G.
    [J]. CURRENT BIOLOGY, 2014, 24 (23) : R1119 - R1120
  • [9] Use of the SAR Shadowing Effect for Deforestation Detection with Sentinel-1 Time Series
    Bouvet, Alexandre
    Mermoz, Stephane
    Ballere, Marie
    Koleck, Thierry
    Le Toan, Thuy
    [J]. REMOTE SENSING, 2018, 10 (08)
  • [10] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32