skip to main content

Title: Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
The spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tree species in a timely and accurate manner. At present, a large amount of remote sensing data have been accumulated, including high-spatial-resolution images, time-series images, light detection and ranging (LiDAR) data, etc. However, these data have not been fully utilized. To accurately identify the tree species of forest stands, various and complementary data need to be synthesized for classification. A curve matching based method called the fusion of spectral image and point data (FSP) algorithm was developed to fuse high-spatial-resolution images, time-series images, and LiDAR data for forest stand classification. In this method, the multispectral Sentinel-2 image and high-spatial-resolution aerial images were first fused. Then, the fused images were segmented to derive forest stands, which are the basic unit for classification. To extract features from forest stands, the gray histogram of each band was extracted from the aerial images. The average reflectance in each stand was calculated and stacked for the time-series images. The profile curve more » of forest structure was generated from the LiDAR data. Finally, the features of forest stands were compared with training samples using curve matching methods to derive the tree species. The developed method was tested in a forest farm to classify 11 tree species. The average accuracy of the FSP method for ten performances was between 0.900 and 0.913, and the maximum accuracy was 0.945. The experiments demonstrate that the FSP method is more accurate and stable than traditional machine learning classification methods. « less
; ; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
Remote Sensing
Page Range or eLocation-ID:
Sponsoring Org:
National Science Foundation
More Like this
  1. The ability to automatically delineate individual tree crowns using remote sensing data opens the possibility to collect detailed tree information over large geographic regions. While individual tree crown delineation (ITCD) methods have proven successful in conifer-dominated forests using Light Detection and Ranging (LiDAR) data, it remains unclear how well these methods can be applied in deciduous broadleaf-dominated forests. We applied five automated LiDAR-based ITCD methods across fifteen plots ranging from conifer- to broadleaf-dominated forest stands at Harvard Forest in Petersham, MA, USA, and assessed accuracy against manual delineation of crowns from unmanned aerial vehicle (UAV) imagery. We then identified tree- and plot-level factors influencing the success of automated delineation techniques. There was relatively little difference in accuracy between automated crown delineation methods (51–59% aggregated plot accuracy) and, despite parameter tuning, none of the methods produced high accuracy across all plots (27—90% range in plot-level accuracy). The accuracy of all methods was significantly higher with increased plot conifer fraction, and individual conifer trees were identified with higher accuracy (mean 64%) than broadleaf trees (42%) across methods. Further, while tree-level factors (e.g., diameter at breast height, height and crown area) strongly influenced the success of crown delineations, the influence of plot-level factorsmore »varied. The most important plot-level factor was species evenness, a metric of relative species abundance that is related to both conifer fraction and the degree to which trees can fill canopy space. As species evenness decreased (e.g., high conifer fraction and less efficient filling of canopy space), the probability of successful delineation increased. Overall, our work suggests that the tested LiDAR-based ITCD methods perform equally well in a mixed temperate forest, but that delineation success is driven by forest characteristics like functional group, tree size, diversity, and crown architecture. While LiDAR-based ITCD methods are well suited for stands with distinct canopy structure, we suggest that future work explore the integration of phenology and spectral characteristics with existing LiDAR as an approach to improve crown delineation in broadleaf-dominated stands.« less
  2. 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 onmore »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.« less
  3. Infrequent stand-replacing wildfires are characteristic of mesic and/or cool conifer forests in western North America, where forest recovery within high-severity burn patch interiors can be slow, yet successful over long temporal periods (decades to centuries). Increasing fire frequency and high-severity burn patch size, under a warming climate, however, may challenge post-fire forest recovery, promoting landscape-level shifts in forest structure, composition, and distribution of non-forest patches. Crucial to a delay and/or impediment to this shift, fire refugia (i.e., remnant seed sources) may determine forest recovery trajectories and potential forest state-transitions. To examine how fire refugia attributes (i.e. extent, composition, and structure) interact with local climate and environmental conditions to determine post-fire forest recovery responses, we developed fine-grain maps of fire refugia via remote sensing and conducted field-based assessment of post-fire conifer tree establishment largely originating (i.e., dispersed) from fire refugium in the Central Cascade Range of the Pacific Northwest United States. We found that limitations on seed availability, represented by the distance 2 -weighted density (D 2 WD) of fine-grain refugia extent, largely explained post-fire tree establishment responses within our relatively mesic and cool subalpine study sites. Interactions between seed availability, climate, and environmental conditions indicated that the structural attributes ofmore »refugia (e.g., tree height) and site abiotic/biotic environmental controls (e.g., climate water deficit, canopy cover, and coarse woody debris cover) interplayed to constrain or enhance species-specific tree establishment responses. Importantly, these interactions illustrate that when seed availability is critically low for a given area, climate-environment conditions may strongly determine whether forests recover following fire(s). Toward modelling and predicting tree establishment responses and potential forest state-transitions after large stand-replacing fires(s), our study demonstrates the importance of accurately quantifying seed availability via the fine-grain extent, configuration, and attributes of remnant seed source legacies.« less
  4. Airborne remote sensing offers unprecedented opportunities to efficiently monitor vegetation, but methods to delineate and classify individual plant species using the collected data are still actively being developed and improved. The Integrating Data science with Trees and Remote Sensing (IDTReeS) plant identification competition openly invited scientists to create and compare individual tree mapping methods. Participants were tasked with training taxon identification algorithms based on two sites, to then transfer their methods to a third unseen site, using field-based plant observations in combination with airborne remote sensing image data products from the National Ecological Observatory Network (NEON). These data were captured by a high resolution digital camera sensitive to red, green, blue (RGB) light, hyperspectral imaging spectrometer spanning the visible to shortwave infrared wavelengths, and lidar systems to capture the spectral and structural properties of vegetation. As participants in the IDTReeS competition, we developed a two-stage deep learning approach to integrate NEON remote sensing data from all three sensors and classify individual plant species and genera. The first stage was a convolutional neural network that generates taxon probabilities from RGB images, and the second stage was a fusion neural network that “learns” how to combine these probabilities with hyperspectral and lidarmore »data. Our two-stage approach leverages the ability of neural networks to flexibly and automatically extract descriptive features from complex image data with high dimensionality. Our method achieved an overall classification accuracy of 0.51 based on the training set, and 0.32 based on the test set which contained data from an unseen site with unknown taxa classes. Although transferability of classification algorithms to unseen sites with unknown species and genus classes proved to be a challenging task, developing methods with openly available NEON data that will be collected in a standardized format for 30 years allows for continual improvements and major gains for members of the computational ecology community. We outline promising directions related to data preparation and processing techniques for further investigation, and provide our code to contribute to open reproducible science efforts.« less
  5. Sankey, Temuulen ; Van Den Broeke, Matthew (Ed.)
    Rapid impact assessment of cyclones on coastal ecosystems is critical for timely rescue and rehabilitation operations in highly human-dominated landscapes. Such assessments should also include damage assessments of vegetation for restoration planning in impacted natural landscapes. Our objective is to develop a remote sensing-based approach combining satellite data derived from optical (Sentinel-2), radar (Sentinel-1), and LiDAR (Global Ecosystem Dynamics Investigation) platforms for rapid assessment of post-cyclone inundation in nonforested areas and vegetation damage in a primarily forested ecosystem. We apply this multi-scalar approach for assessing damages caused by the cyclone Amphan that hit coastal India and Bangladesh in May 2020, severely flooding several districts in the two countries, and causing destruction to the Sundarban mangrove forests. Our analysis shows that at least 6821 sq. km. land across the 39 study districts was inundated even after 10 days after the cyclone. We further calculated the change in forest greenness as the difference in normalized difference vegetation index (NDVI) pre- and post-cyclone. Our findings indicate a <0.2 unit decline in NDVI in 3.45 sq. km. of the forest. Rapid assessment of post-cyclone damage in mangroves is challenging due to limited navigability of waterways, but critical for planning of mitigation and recovery measures.more »We demonstrate the utility of Otsu method, an automated statistical approach of the Google Earth Engine platform to identify inundated areas within days after a cyclone. Our radar-based inundation analysis advances current practices because it requires minimal user inputs, and is effective in the presence of high cloud cover. Such rapid assessment, when complemented with detailed information on species and vegetation composition, can inform appropriate restoration efforts in severely impacted regions and help decision makers efficiently manage resources for recovery and aid relief. We provide the datasets from this study on an open platform to aid in future research and planning endeavors.« less