Multisensor data to derive peatland vegetation communities using a fixed-wing unmanned aerial vehicle

被引:35
作者
Beyer, Florian [1 ]
Jurasinski, Gerald [1 ]
Couwenberg, John [2 ]
Grenzdoerffer, Goerres [1 ]
机构
[1] Univ Rostock, Fac Agr & Environm Sci, Rostock, Germany
[2] Greifswald Univ, Inst Bot & Landscape Ecol, Greifswald, Germany
关键词
RANDOM FOREST; IMAGE CLASSIFICATION; BOREAL WETLAND; RESTORATION; CARBON; ACCURACY; PLANT; REFLECTANCE; INDEXES; COMPLEX;
D O I
10.1080/01431161.2019.1580825
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
The restoration of drained peatlands to re-establish biodiverse peat-forming plant communities and typical habitats is a long-term process. To document this process, monitoring concepts must be found that are as operational, cost-effective and non-invasive as possible for the new sensitive ecosystems. The monitoring of the developing plant communities using multisensory Unmanned Aerial Vehicle (UAV) data has great potential. We investigated two fen sites in north-eastern Germany that were rewetted in the late 1990s. The areas were flown with a Fixed-Wing UAV and three sensors (RGB, multispectral, thermal). A multisensor dataset consisting of the sensor data, plant height and five spectral indices was classified with a random forest algorithm. The classification accuracies were 87.1 and 89.0% for 10 and 11 classes for the respective sites. Furthermore, the band importance was analyzed using the Gini index. Plant height in combination with the multispectral information were the most important variables. This study underlines the suitability of UAVs for monitoring spectrally similar vegetation because of their capability to generate 3D surface models using structure-from-motion methods and to carry different sensor systems. In addition, they can be used on a regional scale and mostly independent of cloud cover. Secondary results of the study are that the band importance can be determined by Random Forest algorithms even with few trees (e.g. 10 trees), because the order remains very stable independently of the number of trees.
引用
收藏
页码:9103 / 9125
页数:23
相关论文
共 75 条
[1]   Tree phenology and carbon dioxide fluxes: use of digital photography at for process-based interpretation the ecosystem scale [J].
Ahrends, H. E. ;
Etzold, S. ;
Kutsch, W. L. ;
Stoeckli, R. ;
Bruegger, R. ;
Jeanneret, F. ;
Wanner, H. ;
Buchmann, N. ;
Eugster, W. .
CLIMATE RESEARCH, 2009, 39 (03) :261-274
[2]   Modeling peatland carbon stock in a delineated portion of the Nayshkootayaow river watershed in Far North, Ontario using an integrated GIS and remote sensing approach [J].
Akumu, Clement E. ;
McLaughlin, James W. .
CATENA, 2014, 121 :297-306
[3]   Spectral analysis of wetlands using multi-source optical satellite imagery [J].
Amani, Meisam ;
Salehi, Bahram ;
Mandavi, Sahel ;
Brisco, Brian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 144 :119-136
[4]   Empirical characterization of random forest variable importance measures [J].
Archer, Kelfie J. ;
Kirnes, Ryan V. .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (04) :2249-2260
[5]   Evaluation of phenospectral dynamics with Sentinel-2A using a bottom-up approach in a northern ombrotrophic peatland [J].
Arroyo-Mora, J. P. ;
Kalacska, M. ;
Soffer, R. ;
Ifimov, G. ;
Leblanc, G. ;
Schaaf, E. S. ;
Lucanus, O. .
REMOTE SENSING OF ENVIRONMENT, 2018, 216 :544-560
[6]   Spectro-spatial relationship between UAV derived high resolution DEM and SWIR hyperspectral data: application to an ombrotrophic peatland [J].
Arroyo-Mora, J. Pablo ;
Kalacska, Margaret ;
Lucanus, Oliver ;
Soffer, Raymond ;
Leblanc, George .
REMOTE SENSING FOR AGRICULTURE, ECOSYSTEMS, AND HYDROLOGY XIX, 2017, 10421
[7]   A classification-based assessment of the optimal spectral and spatial resolutions for Great Lakes coastal wetland imagery [J].
Becker, Brian L. ;
Lusch, David P. ;
Qi, Jiaguo .
REMOTE SENSING OF ENVIRONMENT, 2007, 108 (01) :111-120
[8]   Random forest in remote sensing: A review of applications and future directions [J].
Belgiu, Mariana ;
Dragut, Lucian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31
[9]  
Beyer F, 2015, 2015 8TH INTERNATIONAL WORKSHOP ON THE ANALYSIS OF MULTITEMPORAL REMOTE SENSING IMAGES (MULTI-TEMP)
[10]   Identification of Agricultural Crop Types in Northern Israel using Multitemporal RapidEye Data [J].
Beyer, Florian ;
Jarmer, Thomas ;
Siegmann, Bastian .
PHOTOGRAMMETRIE FERNERKUNDUNG GEOINFORMATION, 2015, (01) :21-32