Integrating National Ecological Observatory Network (NEON) Airborne Remote Sensing and In-Situ Data for Optimal Tree Species Classification

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 9; p. 1414
• Main Authors: Scholl, Victoria, Cattau, Megan, Joseph, Maxwell, Balch, Jennifer
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2020
• Subjects: Accuracy; Airborne observation; airborne remote sensing; Airborne sensing; Algorithms; Biodiversity; Classification; Composition; Coniferous trees; Data collection; Datasets; Decision analysis; Decision trees; Detection; Diameters; Ecology; Forestry research; hyperspectral; Image detection; Learning algorithms; Lidar; Machine learning; Mapping; Mountains; multispectral; National Ecological Observatory Network; Neon; Neural networks; Observatories; Plant diversity; Polygons; Remote observing; Remote sensing; Remote sensing systems; Species classification; Species composition; Species diversity; Support vector machines; Training; tree species classification; Trees; Vegetation; Workflow; United States > US; Colorado
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12091414

Accurately mapping tree species composition and diversity is a critical step towards spatially explicit and species-specific ecological understanding. The National Ecological Observatory Network (NEON) is a valuable source of open ecological data across the United States. Freely available NEON data include in-situ measurements of individual trees, including stem locations, species, and crown diameter, along with the NEON Airborne Observation Platform (AOP) airborne remote sensing imagery, including hyperspectral, multispectral, and light detection and ranging (LiDAR) data products. An important aspect of predicting species using remote sensing data is creating high-quality training sets for optimal classification purposes. Ultimately, manually creating training data is an expensive and time-consuming task that relies on human analyst decisions and may require external data sets or information. We combine in-situ and airborne remote sensing NEON data to evaluate the impact of automated training set preparation and a novel data preprocessing workflow on classifying the four dominant subalpine coniferous tree species at the Niwot Ridge Mountain Research Station forested NEON site in Colorado, USA. We trained pixel-based Random Forest (RF) machine learning models using a series of training data sets along with remote sensing raster data as descriptive features. The highest classification accuracies, 69% and 60% based on internal RF error assessment and an independent validation set, respectively, were obtained using circular tree crown polygons created with half the maximum crown diameter per tree. LiDAR-derived data products were the most important features for species classification, followed by vegetation indices. This work contributes to the open development of well-labeled training data sets for forest composition mapping using openly available NEON data without requiring external data collection, manual delineation steps, or site-specific parameters.