date: 2023-07-03T02:25:38Z
pdf:unmappedUnicodeCharsPerPage: 0
pdf:PDFVersion: 1.7
pdf:docinfo:title: Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence
xmp:CreatorTool: LaTeX with hyperref
Keywords: mangrove forests; forest inventory; monitoring; habitat mapping; UAV; UAS; artificial intelligence; machine learning; instance segmentation; semantic segmentation; above ground biomass; carbon stock
access_permission:modify_annotations: true
access_permission:can_print_degraded: true
subject: Mangrove forests provide valuable ecosystem services to coastal communities across tropical and subtropical regions. Current anthropogenic stressors threaten these ecosystems and urge researchers to create improved monitoring methods for better environmental management. Recent efforts that have focused on automatically quantifying the above-ground biomass using image analysis have found some success on high resolution imagery of mangrove forests that have sparse vegetation. In this study, we focus on stands of mangrove forests with dense vegetation consisting of the endemic Pelliciera rhizophorae and the more widespread Rhizophora mangle mangrove species located in the remote Utrķa National Park in the Colombian Pacific coast. Our developed workflow used consumer-grade Unoccupied Aerial System (UAS) imagery of the mangrove forests, from which large orthophoto mosaics and digital surface models are built. We apply cnn for instance segmentation to accurately delineate (33% instance average precision) individual tree canopies for the Pelliciera rhizophorae species. We also apply cnn for semantic segmentation to accurately identify (97% precision and 87% recall) the area coverage of the Rhizophora mangle mangrove tree species as well as the area coverage of surrounding mud and water land-cover classes. We provide a novel algorithm for merging predicted instance segmentation tiles of trees to recover tree shapes and sizes in overlapping border regions of tiles. Using the automatically segmented ground areas we interpolate their height from the digital surface model to generate a digital elevation model, significantly reducing the effort for ground pixel selection. Finally, we calculate a canopy height model from the digital surface and elevation models and combine it with the inventory of Pelliciera rhizophorae trees to derive the height of each individual mangrove tree. The resulting inventory of a mangrove forest, with individual P. rhizophorae tree height information, as well as crown shape and size descriptions, enables the use of allometric equations to calculate important monitoring metrics, such as above-ground biomass and carbon stocks.
dc:creator: Daniel Schürholz, Gustavo A. Castellanos-Galindo, Elisa Casella, Juan C. Mejķa-Renterķa, Arjun Chennu
dcterms:created: 2023-06-29T13:13:26Z
Last-Modified: 2023-07-03T02:25:38Z
dcterms:modified: 2023-07-03T02:25:38Z
dc:format: application/pdf; version=1.7
title: Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence
Last-Save-Date: 2023-07-03T02:25:38Z
pdf:docinfo:creator_tool: LaTeX with hyperref
access_permission:fill_in_form: true
pdf:docinfo:keywords: mangrove forests; forest inventory; monitoring; habitat mapping; UAV; UAS; artificial intelligence; machine learning; instance segmentation; semantic segmentation; above ground biomass; carbon stock
pdf:docinfo:modified: 2023-07-03T02:25:38Z
meta:save-date: 2023-07-03T02:25:38Z
pdf:encrypted: false
dc:title: Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence
modified: 2023-07-03T02:25:38Z
cp:subject: Mangrove forests provide valuable ecosystem services to coastal communities across tropical and subtropical regions. Current anthropogenic stressors threaten these ecosystems and urge researchers to create improved monitoring methods for better environmental management. Recent efforts that have focused on automatically quantifying the above-ground biomass using image analysis have found some success on high resolution imagery of mangrove forests that have sparse vegetation. In this study, we focus on stands of mangrove forests with dense vegetation consisting of the endemic Pelliciera rhizophorae and the more widespread Rhizophora mangle mangrove species located in the remote Utrķa National Park in the Colombian Pacific coast. Our developed workflow used consumer-grade Unoccupied Aerial System (UAS) imagery of the mangrove forests, from which large orthophoto mosaics and digital surface models are built. We apply cnn for instance segmentation to accurately delineate (33% instance average precision) individual tree canopies for the Pelliciera rhizophorae species. We also apply cnn for semantic segmentation to accurately identify (97% precision and 87% recall) the area coverage of the Rhizophora mangle mangrove tree species as well as the area coverage of surrounding mud and water land-cover classes. We provide a novel algorithm for merging predicted instance segmentation tiles of trees to recover tree shapes and sizes in overlapping border regions of tiles. Using the automatically segmented ground areas we interpolate their height from the digital surface model to generate a digital elevation model, significantly reducing the effort for ground pixel selection. Finally, we calculate a canopy height model from the digital surface and elevation models and combine it with the inventory of Pelliciera rhizophorae trees to derive the height of each individual mangrove tree. The resulting inventory of a mangrove forest, with individual P. rhizophorae tree height information, as well as crown shape and size descriptions, enables the use of allometric equations to calculate important monitoring metrics, such as above-ground biomass and carbon stocks.
pdf:docinfo:subject: Mangrove forests provide valuable ecosystem services to coastal communities across tropical and subtropical regions. Current anthropogenic stressors threaten these ecosystems and urge researchers to create improved monitoring methods for better environmental management. Recent efforts that have focused on automatically quantifying the above-ground biomass using image analysis have found some success on high resolution imagery of mangrove forests that have sparse vegetation. In this study, we focus on stands of mangrove forests with dense vegetation consisting of the endemic Pelliciera rhizophorae and the more widespread Rhizophora mangle mangrove species located in the remote Utrķa National Park in the Colombian Pacific coast. Our developed workflow used consumer-grade Unoccupied Aerial System (UAS) imagery of the mangrove forests, from which large orthophoto mosaics and digital surface models are built. We apply cnn for instance segmentation to accurately delineate (33% instance average precision) individual tree canopies for the Pelliciera rhizophorae species. We also apply cnn for semantic segmentation to accurately identify (97% precision and 87% recall) the area coverage of the Rhizophora mangle mangrove tree species as well as the area coverage of surrounding mud and water land-cover classes. We provide a novel algorithm for merging predicted instance segmentation tiles of trees to recover tree shapes and sizes in overlapping border regions of tiles. Using the automatically segmented ground areas we interpolate their height from the digital surface model to generate a digital elevation model, significantly reducing the effort for ground pixel selection. Finally, we calculate a canopy height model from the digital surface and elevation models and combine it with the inventory of Pelliciera rhizophorae trees to derive the height of each individual mangrove tree. The resulting inventory of a mangrove forest, with individual P. rhizophorae tree height information, as well as crown shape and size descriptions, enables the use of allometric equations to calculate important monitoring metrics, such as above-ground biomass and carbon stocks.
Content-Type: application/pdf
pdf:docinfo:creator: Daniel Schürholz, Gustavo A. Castellanos-Galindo, Elisa Casella, Juan C. Mejķa-Renterķa, Arjun Chennu
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Daniel Schürholz, Gustavo A. Castellanos-Galindo, Elisa Casella, Juan C. Mejķa-Renterķa, Arjun Chennu
meta:author: Daniel Schürholz, Gustavo A. Castellanos-Galindo, Elisa Casella, Juan C. Mejķa-Renterķa, Arjun Chennu
dc:subject: mangrove forests; forest inventory; monitoring; habitat mapping; UAV; UAS; artificial intelligence; machine learning; instance segmentation; semantic segmentation; above ground biomass; carbon stock
meta:creation-date: 2023-06-29T13:13:26Z
created: 2023-06-29T13:13:26Z
access_permission:extract_for_accessibility: true
access_permission:assemble_document: true
xmpTPg:NPages: 24
Creation-Date: 2023-06-29T13:13:26Z
pdf:charsPerPage: 3665
access_permission:extract_content: true
access_permission:can_print: true
meta:keyword: mangrove forests; forest inventory; monitoring; habitat mapping; UAV; UAS; artificial intelligence; machine learning; instance segmentation; semantic segmentation; above ground biomass; carbon stock
Author: Daniel Schürholz, Gustavo A. Castellanos-Galindo, Elisa Casella, Juan C. Mejķa-Renterķa, Arjun Chennu
producer: pdfTeX-1.40.21
access_permission:can_modify: true
pdf:docinfo:producer: pdfTeX-1.40.21
pdf:docinfo:created: 2023-06-29T13:13:26Z