Barro Colorado Island 50-ha plot crown maps: manually segmented and instance segmented.

**Data Citation**

Please cite this dataset as follows:

Vasquez, V., Cushman, K., Ramos, P., Williamson, C., Villareal, P., Gomez
Correa, L. F., & Muller-Landau, H. (2023). Barro Colorado Island 50-ha plot
crown maps: manually segmented and instance segmented. (Version 2).
Smithsonian Tropical Research Institute.
https://doi.org/10.25573/data.24784053

This data is licensed as CC BY 4.0 and is thus freely available for reuse with
proper citation. We ask that data users share any resulting publications,
preprints, associated analysis code, and derived data products with us by
emailing [e-mail]. We are open to contributing our expert knowledge of
the study site and datasets to projects that use these data; please direct
queries regarding potential collaboration to Vicente Vasquez, [e-mail],
and Helene Muller-Landau, [e-mail].

Note that this dataset is part of a collection of Panama UAV data on
Smithsonian Figshare, which can be viewed at
<https://smithsonian.figshare.com/projects/Panama_Forest_Landscapes_UAV/115572>

Additional information about this research can be found at the Muller-Landau
lab web site at <https://hmullerlandau.com/>

All required code is freely available at
<https://github.com/P-polycephalum/ForestLandscapes/blob/main/LandscapeScripts/segmentation.py>
and it can be cited as:

Vicente Vasquez. (2023). P-polycephalum/ForestLandscapes: segmentwise
(v0.0.2-beta). Zenodo. <https://doi.org/10.5281/zenodo.10380517>

**Data Description**

This dataset is part of a larger initiative monitoring forests in Panama using
drones (unoccupied aerial vehicles), an initiative led by Dr. Helene Muller-
Landau at the Smithsonian Tropical Research Institute. As part of this
initiative, we have been collecting repeat imagery of the 50-ha forest
dynamics plot on Barro Colorado Island (BCI), Panama, since October 2014 (see
Garcia et al. 2021a, b for data products for 2014-2019).

Contained within this dataset are two sets of field-derived crown maps,
presented in both their raw and improved versions. The 2021 crown mapping
campaign was overseen by KC Cushman, accompanied by field technician Pablo
Ramos and Paulino Villarreal. Additionally, Cecilia Williamson and KC Cushman
reviewed polygon quality and made necessary corrections. Image data occurred
on August 1, 2020, utilizing a DJI Phantom 4 Pro at a resolution of 4cm per
pixel. A total of 2454 polygons were manually delineated, encompassing
insightful metrics like crown completeness and liana load.

The 2023 crown mapping campaign, led by Vicente Vasquez and field technicians
Pablo Ramos, Paulino Villarreal, involved quality revisions and corrections
performed by Luisa Fernanda Gomez Correa and Vicente Vasquez. Image data
collection occurred on September 29, 2022, utilizing a DJI Phantom 4 Pro drone
at a 4cm per pixel resolution. The 2023 campaign integrated model
230103_randresize_full of the detectree2 model garden (Ball, 2023). Tree crown
polygons were generated pre-field visit, with those attaining a field
validation score of 7 or higher retained as true tree crowns.

The data collection forms are prepared using ArcGIS field maps. The creator of
the data forms uses the spatial points from the trees in the ForestGeo 50-ha
censuses to facilitate finding the tree tags in the field (Condit et al.,
2019). The field technicians confirm that the tree crown is visible from the
drone imagery, they proceed to collect variables of interest and delineate the
tree crown manually. In the case of the 2023 field campaign, the field
technicians were able to skip manual delineation when the polygons generated
by 230103_randresize_full were evaluated as true detection.

The improved version of the 2023 and 2021 crown map data collection takes as
input the raw crown maps and the globally aligned orthomosaics to refine the
edges of the crown. We use the model SAM from segment-anything module
developed my Meta AI (Krillov, 2023). We adapted the use of their instance
segmentation algorithm to take geospatial imagery in the form of tiles. We
inputted multiple bounding boxes in the form of CPU torch tensors for each of
the files. Furthermore, we perform several tasks to clean the crowns and
remove the polygons overlaps to avoid ambiguity. This results in a very well
delineated crown map with no overlapping between tree crowns. Despite our
diligent efforts in detecting, delineating, and evaluating all visible tree
crowns from drone imagery, this dataset exhibits certain limitations. These
include missing tags denoted as -9999, erroneous manual delineations or
instance segmentation of tree crown polygons, duplicated tags, and undetected
tree crowns. These limitations are primarily attributed to human error,
logistical constraints, and the challenge of confirming individual tree crown
emergence above the canopy. In numerous instances, particularly within densely
vegetated areas, delineating polygons and assigning tags to numerous small
trees posed significant challenges.

**Metadata**

The dataset comprises four sets of crown maps bundled within .zip files,
adhering to the naming convention MacroSite_plot_year_month_day_crownmap_type.
As an illustration, a sample file name follows the structure:
BCI_50ha_2020_08_01_improved.

For a comprehensive understanding of variable nomenclature within each
shapefile, exhaustive details are provided in the file named
variables_description.csv. Additionally, our dataset incorporates
visualization figures corresponding to both raw and refined crown maps.

The raw crown maps contain:

* A GeoTiff-formatted raster image reflecting the image acquisition date during field data collection.
* The tiles folder housing all tiles utilized for instance segmentation.
* The most recent version of the raw crown map manually revised and retaining its original naming scheme.
* A reformatted iteration of the raw crown map, involving column renaming and the reprojection of its coordinate reference system.

The improved crown maps contain:

* "_crownmap_segmented.shp" version: This subproduct has all polygons segmented via the SAM model from the segment-anything process.
* "_crownmap_cleaned.shp" version: This subproduct features one polygon allocated per GlobalID, specifically the one with the highest segment-anything score.
* "_crownmap_avoidance.shp" version: This subproduct is devoid of any overlapping polygons.
* "_crownmap_improved.shp" version: The outcome of the instance crown segmentation workflow, incorporating all original crown map fields.

**Author contributions**

VV wrote the code for standardized workflow for processing, alignment, and
segmentation of the tree crowns. MG and MH led the drone imagery collection.
HCM conceived the study, wrote the grant proposals to obtain funding, and
supervised the research.

**Acknowledgments**

Vicente Vasquez and KC Cushman created the field map forms and coordinated the
2023 and 2021 crown map field campaign. Milton Solano assistance with the
ArcGIS platform. Field technicians Pablo Ramos, Paulino Villareal, and Melvin
Hernandez delineated and evaluated tree crown polygons. Luisa Gomez-Correa and
Cecilia Williamson assisted with quality assurance and quality control after
field data collection. Milton Garcia and additional interns in the Muller-
Landau lab assisted with drone data collection. Funding and/or in-kind support
was provided by the Smithsonian Institution Scholarly Studies grant program
(HCM), the Smithsonian Institution Equipment fund (HCM), Smithsonian
ForestGEO, the Smithsonian Tropical Research Institute.

**References**

Ball, J.G.C., Hickman, S.H.M., Jackson, T.D., Koay, X.J., Hirst, J., Jay, W.,
Archer, M., Aubry-Kientz, M., Vincent, G. and Coomes, D.A. (2023), Accurate
delineation of individual tree crowns in tropical forests from aerial RGB
imagery using Mask R-CNN. _Remote Sens Ecol Conserv_. 9(5):641-655.
<https://doi.org/10.1002/rse2.332>

Condit, Richard et al. (2019). Complete data from the Barro Colorado 50-ha
plot: 423617 trees, 35 years [Dataset]. Dryad.
<https://doi.org/10.15146/5xcp-0d46>

Garcia, M., J. P. Dandois, R. F. Araujo, S. Grubinger, and H. C. Muller-
Landau. 2021b. Surface elevation models and associated canopy height change
models for the 50-ha plot on Barro Colorado Island, Panama, for 2014-2019. .
In Smithsonian Figshare, edited by S. T. R. Institute.
https://doi.org/10.25573/data.14417933

Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao,
T., Whitehead, S., Berg, A. C., Lo, W.-Y., Dollár, P., & Girshick, R. (2023).
Segment Anything. arXiv preprint arXiv:2304.02643.

Scheffler D, Hollstein A, Diedrich H, Segl K, Hostert P. AROSICS: An Automated
and Robust Open-Source Image Co-Registration Software for Multi-Sensor
Satellite Data. Remote Sensing. 2017; 9(7):676.