An official website of the United States government
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 factors 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.
more »
« less
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 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.
more »
« less
- Award ID(s):
- 1826839
- PAR ID:
- 10346156
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 13
- Issue:
- 1
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 144
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Information about the spatial distribution of species lies at the heart of many important questions in ecology. Logistical limitations and collection biases, however, limit the availability of such data at ecologically relevant scales. Remotely sensed information can alleviate some of these concerns, but presents challenges associated with accurate species identification and limited availability of field data for validation, especially in high diversity ecosystems such as tropical forests.Recent advances in machine learning offer a promising and cost‐efficient approach for gathering a large amount of species distribution data from aerial photographs. Here, we propose a novel machine learning framework, artificial perceptual learning (APL), to tackle the problem of weakly supervised pixel‐level mapping of tree species in forests. Challenges arise from limited availability of ground labels for tree species, lack of precise segmentation of tree canopies and misalignment between visible canopies in the aerial images and stem locations associated with ground labels. The proposed APL framework addresses these challenges by constructing a workflow using state‐of‐the‐art machine learning algorithms.We develop and illustrate the proposed framework by implementing a fine‐grain mapping of three species, the palmPrestoea acuminataand the tree speciesCecropia schreberianaandManilkara bidentata, over a 5,000‐ha area of El Yunque National Forest in Puerto Rico. These large‐scale maps are based on unlabelled high‐resolution aerial images of unsegmented tree canopies. Misaligned ground‐based labels, available for <1% of these images, serve as the only weak supervision. APL performance is evaluated using ground‐based labels and high‐quality human segmentation using Amazon Mechanical Turk, and compared to a basic workflow that relies solely on labelled images.Receiver operating characteristic (ROC) curves and Intersection over Union (IoU) metrics demonstrate that APL substantially outperforms the basic workflow and attains human‐level cognitive economy, with 50‐fold time savings. For the palm andC. schreberiana, the APL framework has high pixelwise accuracy and IoU with reference to human segmentations. ForM.bidentata, APL predictions are congruent with ground‐based labels. Our approach shows great potential for leveraging existing data from global forest plot networks coupled with aerial imagery to map tree species at ecologically meaningful spatial scales.more » « less
-
Successional, second-growth forests dominate much of eastern North America; thus, patterns of biomass accumulation in standing trees and downed wood are of great interest for forest management and carbon accounting. The timing and magnitude of biomass accumulation in later stages of forest development are not fully understood. We applied a “chronosequence with resampling” approach to characterize live and dead biomass accumulation in 16 northern hardwood stands in the White Mountains of New Hampshire. Live aboveground biomass increased rapidly and leveled off at about 350 Mg/ha by 145 years. Downed wood biomass fluctuated between 10 and 35 Mg/ha depending on disturbances. The species composition of downed wood varied predictably with overstory succession, and total mass of downed wood increased with stand age and the concomitant production of larger material. Fine woody debris peaked at 30–50 years during the self-thinning of early successional species, notably pin cherry. Our data support a model of northern hardwood forest development wherein live tree biomass accumulates asymptotically and begins to level off at ∼140–150 years. Still, 145-year-old second-growth stands differed from old-growth forests in their live ( p = 0.09) and downed tree diameter distributions ( p = 0.06). These patterns of forest biomass accumulation would be difficult to detect without a time series of repeated measurements of stands of different ages.more » « less
-
null (Ed.)Eastern redcedar (Juniperus virginiana L., redcedar) encroachment is transitioning the oak-dominated Cross-Timbers of the southern Great Plain of the USA into mixed-species forests. However, it remains unknown how the re-assemblage of tree species in a semiarid to sub-humid climate affects species-specific water use and competition, and ultimately the ecosystem-level water budget. We selected three sites representative of oak, redcedar, and oak and redcedar mixed stands with a similar total basal area (BA) in a Cross-Timbers forest near Stillwater, Oklahoma. Sap flow sensors were installed in a subset of trees in each stand representing the distribution of diameter at breast height (DBH). Sap flow of each selected tree was continuously monitored over a period of 20 months, encompassing two growing seasons between May 2017 and December 2018. Results showed that the mean sap flow density (Sd) of redcedar was usually higher than post oaks (Quercus stellata Wangenh.). A structural equation model showed a significant correlation between Sd and shallow soil moisture for redcedar but not for post oak. At the stand level, the annual water use of the mixed species stand was greater than the redcedar or oak stand of similar total BA. The transition of oak-dominated Cross-Timbers to redcedar and oak mixed forest will increase stand-level transpiration, potentially reducing the water available for runoff or recharge to groundwater.more » « less
-
Abstract Transpiration and stomatal conductance in deciduous needleleaf boreal forests of northern Siberia can be highly sensitive to water stress, permafrost thaw, and atmospheric dryness. Additionally, north‐eastern Siberian boreal forests are fire‐driven, and larch (Larixspp.) are the sole tree species. We examined differences in tree water use, stand characteristics, and stomatal responses to environmental drivers between high and low tree density stands that burned 76 years ago in north‐eastern Siberia. Our results provide process‐level insight to climate feedbacks related to boreal forest productivity, water cycles, and permafrost across Arctic regions. The high density stand had shallower permafrost thaw depths and deeper moss layers than the low density stand. Rooting depths and shallow root biomass were similar between stands. Daily transpiration was higher on average in the high‐density stand 0.12 L m−2 day−1(SE: 0.004) compared with the low density stand 0.10 L m−2 day−1(SE: 0.001) throughout the abnormally wet summer of 2016. Transpiration rates tended to be similar at both stands during the dry period in 2017 in both stands of 0.10 L m−2 day−1(SE: 0.002). The timing of precipitation impacted stomatal responses to environmental drivers, and the high density stand was more dependent on antecedent precipitation that occurred over longer periods in the past compared with the low density stand. Post‐fire tree density differences in plant–water relations may lead to different trajectories in plant mortality, water stress, and ecosystem water cycles across Siberian landscapes.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs13010144
