Estimating Stand and Fire-Related Surface and Canopy Fuel Variables in Pine Stands Using Low-Density Airborne and Single-Scan Terrestrial Laser Scanning Data

被引:23
作者
Alonso-Rego, Cecilia [1 ]
Arellano-Perez, Stefano [1 ]
Guerra-Hernandez, Juan [2 ]
Molina-Valero, Juan Alberto [1 ]
Martinez-Calvo, Adela [1 ]
Perez-Cruzado, Cesar [3 ]
Castedo-Dorado, Fernando [4 ]
Gonzalez-Ferreiro, Eduardo [5 ,6 ]
alvarez-Gonzalez, Juan Gabriel [1 ]
Ruiz-Gonzalez, Ana Daria [1 ]
机构
[1] Univ Santiago de Compostela, Dept Ingn Agroforestal, Escuela Politecn Super Ingn, Unidad Gest Ambiental & Forestal Sostenible UXAFO, Benigno Ledo S-N,Campus Terra, Lugo 27002, Spain
[2] Univ Lisbon, Inst Super Agron ISA, Sch Agr, Forest Res Ctr, P-1349017 Lisbon, Portugal
[3] Univ Santiago de Compostela, Proyectos & Planificac PROEPLA, Dept Prod Vegetal & Proyectos Ingn, Escuela Politecn Super Ingn, Benigno Ledo S-N,Campus Terra, Lugo 27002, Spain
[4] Univ Leon, Dept Ingn & Ciencias Agr, Grp Invest Geomat & Ingn Cartog GI 202 GEOINC, Campus Ponferrada, Ponferrada 24401, Spain
[5] Univ Leon, Dept Tecnol Minera Topog & Estruct, Grp Invest Geomat & Ingn Cartog GI 202 GEOINC, Escuela Super & Tecn Ingenieros Minas, Av Astorga S-N,Campus Ponferrada, Ponferrada 24401, Spain
[6] Univ Leon, Dept Tecnol Minera Topog & Estruct, Grp Invest Geomat & Ingn Cartog GI 202 GEOINC, Escuela Ingn Agr & Forestal, Av Astorga S-N,Campus Ponferrada, Ponferrada 24401, Spain
关键词
forest fuel modeling; ALS; TLS; canopy fuel characterization; understory fuel characterization; WAVE-FORM LIDAR; RADIATA D. DON; MEASURING FOREST STRUCTURE; GROUND-BASED LIDAR; INTEGRATING AIRBORNE; ABOVEGROUND BIOMASS; NW SPAIN; PARAMETERS; STEM; ATTRIBUTES;
D O I
10.3390/rs13245170
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In this study, we used data from a thinning trial conducted on 34 different sites and 102 sample plots established in pure and even-aged Pinus radiata and Pinus pinaster stands, to test the potential use of low-density airborne laser scanning (ALS) metrics and terrestrial laser scanning (TLS) metrics to provide accurate estimates of variables related to surface and canopy fires. An exhaustive field inventory was carried out in each plot to estimate the main stand variables and the main variables related to fire hazard: surface fuel loads by layers, fuel strata gap, surface fuel height, stand mean height, canopy base height, canopy fuel load and canopy bulk density. In addition, the point clouds from low-density ALS and single-scan TLS of each sample plot were used to calculate metrics related to the vertical and horizontal distribution of forest fuels. The comparative performance of the following three non-parametric machine learning techniques used to estimate the main stand- and fire-related variables from those metrics was evaluated: (i) multivariate adaptive regression splines (MARS), (ii) support vector machine (SVM), and (iii) random forest (RF). The selection of the best modeling approach was based on a comparison of the root mean square error (RMSE), obtained by optimizing the parameters of each technique and performing cross-validation. Overall, the best results were obtained with the MARS techniques for data from both sensors. The TLS data provided the best results for variables associated with the internal characteristics of canopy structure and understory fuel but were less reliable for estimating variables associated with the upper canopy, due to occlusion by mid-canopy foliage. The combination of ALS and TLS metrics improved the accuracy of estimates for all variables analyzed, except the height and the biomass of the understory shrubs. The variability demonstrated by the combined use of both types of metrics ranged from 43.11% for the biomass of duff litter layers to 94.25% for dominant height. The results suggest that the combination of machine learning techniques and metrics derived from low-density ALS data, drawn from a single-scan TLS or a combination of both metrics, may represent a promising alternative to traditional field inventories for obtaining valuable information about surface and canopy fuel variables at large scales.
引用
收藏
页数:26
相关论文
共 106 条
[11]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[12]   Prediction of Forest Canopy and Surface Fuels from Lidar and Satellite Time Series Data in a Bark Beetle-Affected Forest [J].
Bright, Benjamin C. ;
Hudak, Andrew T. ;
Meddens, Arjan J. H. ;
Hawbaker, Todd J. ;
Briggs, Jennifer S. ;
Kennedy, Robert E. .
FORESTS, 2017, 8 (09)
[13]  
Brolly G., 2009, Acta Silvatica & Lignaria Hungarica, V5, P119
[14]  
Brown J. K., 1974, USDA Forest Service General Technical Report, Intermountain Forest and Range Experiment Station
[15]  
BROWN JK, 1971, FOREST SCI, V17, P93
[16]   Quantifying understory vegetation density using small-footprint airborne lidar [J].
Campbell, Michael J. ;
Dennison, Philip E. ;
Hudak, Andrew T. ;
Parham, Lucy M. ;
Butler, Bret W. .
REMOTE SENSING OF ENVIRONMENT, 2018, 215 :330-342
[17]   Using Small-Footprint Discrete and Full-Waveform Airborne LiDAR Metrics to Estimate Total Biomass and Biomass Components in Subtropical Forests [J].
Cao, Lin ;
Coops, Nicholas C. ;
Hermosilla, Txomin ;
Innes, John ;
Dai, Jinsong ;
She, Guanghui .
REMOTE SENSING, 2014, 6 (08) :7110-7135
[18]  
Cao Q.V, 1982, 182 FWS STAT U VIRG
[19]   Airborne lidar provides reliable estimates of canopy base height and canopy bulk density in southwestern ponderosa pine forests [J].
Chamberlain, Caden P. ;
Meador, Andrew J. Sanchez ;
Thode, Andrea E. .
FOREST ECOLOGY AND MANAGEMENT, 2021, 481
[20]  
Chasmer L, 2004, REMOTE SENS SPAT INF, V36, P8