Classifying Forest Type in the National Forest Inventory Context with Airborne Hyperspectral and Lidar Data

Forest structure and composition regulate a range of ecosystem services, including biodiversity, water and nutrient cycling, and wood volume for resource extraction. Forest type is an important metric measured in the US Forest Service Forest Inventory and Analysis (FIA) program, the national forest inventory of the USA. Forest type information can be used to quantify carbon and other forest resources within specific domains to support ecological analysis and forest management decisions, such as managing for disease and pests. In this study, we developed a methodology that uses a combination of airborne hyperspectral and lidar data to map FIA-defined forest type between sparsely sampled FIA plot data collected in interior Alaska. To determine the best classification algorithm and remote sensing data for this task, five classification algorithms were tested with six different combinations of raw hyperspectral data, hyperspectral vegetation indices, and lidar-derived canopy and topography metrics. Models were trained using forest type information from 632 FIA subplots collected in interior Alaska. Of the thirty model and input combinations tested, the random forest classification algorithm with hyperspectral vegetation indices and lidar-derived topography and canopy height metrics had the highest accuracy (78% overall accuracy). This study supports random forest as a powerful classifier for natural resource data. It also demonstrates the benefits from combining both structural (lidar) and spectral (imagery) data for forest type classification.

[1]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[2]  A. Wood,et al.  Climate model based consensus on the hydrologic impacts of climate change to the Rio Lempa basin of Central America , 2008 .

[3]  G. Carter,et al.  Early detection of plant stress by digital imaging within narrow stress-sensitive wavebands , 1994 .

[4]  H. Andersen,et al.  Using multilevel remote sensing and ground data to estimate forest biomass resources in remote regions: a case study in the boreal forests of interior Alaska , 2011 .

[5]  William Stafford Noble,et al.  Support vector machine , 2013 .

[6]  J. Retana,et al.  Overstory structure and topographic gradients determining diversity and abundance of understory shrub species in temperate forests in central Pyrenees (NE Spain) , 2007 .

[7]  C. Kwak,et al.  Multinomial Logistic Regression , 2002, Nursing research.

[8]  Liviu Theodor Ene,et al.  Large-area hybrid estimation of aboveground biomass in interior Alaska using airborne laser scanning data , 2018 .

[9]  John A. Gamon,et al.  Assessing leaf pigment content and activity with a reflectometer , 1999 .

[10]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[11]  G. A. Blackburn,et al.  Spectral indices for estimating photosynthetic pigment concentrations: A test using senescent tree leaves , 1998 .

[12]  A. Gitelson,et al.  Non‐destructive optical detection of pigment changes during leaf senescence and fruit ripening , 1999 .

[13]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[14]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[15]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001 .

[16]  Bangwen Wang,et al.  Relationship between topography and the distribution of understory vegetation in a Pinus massoniana forest in Southern China , 2015, International Soil and Water Conservation Research.

[17]  Lawrence A. Corp,et al.  NASA Goddard's LiDAR, Hyperspectral and Thermal (G-LiHT) Airborne Imager , 2013, Remote. Sens..

[18]  Yoonsuh Jung.  Multiple predicting K-fold cross-validation for model selection , 2018 .

[19]  Carl A. Roland,et al.  Landscape‐scale patterns in tree occupancy and abundance in subarctic Alaska , 2013 .

[20]  Craig S. T. Daughtry,et al.  A visible band index for remote sensing leaf chlorophyll content at the canopy scale , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[21]  S. McNeeley,et al.  Anatomy of a closing window: Vulnerability to changing seasonality in , 2011 .

[22]  D. Hand,et al.  Idiot's Bayes—Not So Stupid After All? , 2001 .

[23]  Carlos Alberto Silva,et al.  Mapping Forest Structure and Composition from Low-Density LiDAR for Informed Forest, Fuel, and Fire Management at Eglin Air Force Base, Florida, USA , 2016 .

[24]  L. Bruzzone,et al.  Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data , 2012 .

[25]  S. Hurlbert.  Pseudoreplication and the Design of Ecological Field Experiments , 1984 .

[26]  Randall K. Kolka,et al.  Carbon pools and productivity in a 1-km2 heterogeneous forest and peatland mosaic in Minnesota, USA , 2009 .

[27]  Valerie A. Thomas,et al.  Estimating tree canopy cover using harmonic regression coefficients derived from multitemporal Landsat data , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[28]  Shanyu Huang,et al.  Non-destructive estimation of rice plant nitrogen status with Crop Circle multispectral active canopy sensor , 2013 .

[29]  B. Datt,et al.  Visible/near infrared reflectance and chlorophyll content in Eucalyptus leaves , 1999 .

[30]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[31]  W. Cohen,et al.  Testing a Landsat-based approach for mapping disturbance causality in U.S. forests , 2017 .

[32]  L. M. Moskal,et al.  Object-Based Tree Species Classification in Urban Ecosystems Using LiDAR and Hyperspectral Data , 2016 .

[33]  Julian D Olden,et al.  Machine Learning Methods Without Tears: A Primer for Ecologists , 2008, The Quarterly Review of Biology.

[34]  Galina A. Kuryakova,et al.  Influence of topography on some vegetation cover properties , 1996 .

[35]  Leif E. Peterson.  K-nearest neighbor , 2009, Scholarpedia.

[36]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[37]  J. Guinan,et al.  Multiscale Terrain Analysis of Multibeam Bathymetry Data for Habitat Mapping on the Continental Slope , 2007 .

[38]  Corinne Le Quéré,et al.  Trends in the sources and sinks of carbon dioxide , 2009 .

[39]  Yanchen Bo,et al.  A shadow identification method using vegetation indices derived from hyperspectral data , 2017 .

[40]  Daniel G. Brown.  Predicting vegetation types at treeline using topography and biophysical disturbance variables , 1994 .

[41]  David B. Lindenmayer,et al.  Re-evaluation of forest biomass carbon stocks and lessons from the world's most carbon-dense forests , 2009, Proceedings of the National Academy of Sciences.

[42]  Jacob Strunk,et al.  Using Airborne Light Detection and Ranging as a Sampling Tool for Estimating Forest Biomass Resources in the Upper Tanana Valley of Interior Alaska , 2011 .