Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence

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 Utría 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 convolutional neural networks (CNNs) for instance segmentation to accurately delineate (33% instance average precision) individual tree canopies for the Pelliciera rhizophorae species. We also apply CNNs 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.

[1]  Yanjun Su,et al.  Field-measured canopy height may not be as accurate and heritable as believed: evidence from advanced 3D sensing , 2023, Plant Methods.

[2]  Jing Li,et al.  Swin-UperNet: A Semantic Segmentation Model for Mangroves and Spartina alterniflora Loisel Based on UperNet , 2023, Electronics.

[3]  Xiang Niu,et al.  A Review of Research on Forest Ecosystem Quality Assessment and Prediction Methods , 2023, Forests.

[4]  K. Joyce,et al.  The unique value proposition for using drones to map coastal ecosystems , 2022, Cambridge Prisms: Coastal Futures.

[5]  D. Hoai,et al.  Mangrove health assessment using spatial metrics and multi-temporal remote sensing data , 2022, PloS one.

[6]  G. Ståhl,et al.  Quantify and account for field reference errors in forest remote sensing studies , 2022, Remote Sensing of Environment.

[7]  A. Nothdurft,et al.  Automatic tree crown segmentation using dense forest point clouds from Personal Laser Scanning (PLS) , 2022, Int. J. Appl. Earth Obs. Geoinformation.

[8]  G. Lassalle,et al.  Tracking canopy gaps in mangroves remotely using deep learning , 2022, Remote Sensing in Ecology and Conservation.

[9]  G. Lassalle,et al.  Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery , 2022, ISPRS Journal of Photogrammetry and Remote Sensing.

[10]  A. Chennu,et al.  Digitizing the coral reef: machine learning of underwater spectral images enables dense taxonomic mapping of benthic habitats , 2022, bioRxiv.

[11]  Robert J. Nicholls,et al.  Assessment and Attribution of Mangrove Forest Changes in the Indian Sundarbans from 2000 to 2020 , 2021, Remote. Sens..

[12]  Clinton B. Edwards,et al.  TagLab: AI‐assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages , 2021, J. Field Robotics.

[13]  Christopher J. Post,et al.  Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN) , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[14]  Raul Queiroz Feitosa,et al.  Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data , 2021, ArXiv.

[15]  Sven Rahmann,et al.  Sustainable data analysis with Snakemake , 2021, F1000Research.

[16]  Ruonan Li,et al.  An improved quality assessment framework to better inform large-scale forest restoration management , 2021 .

[17]  Stefan Hinz,et al.  Review on Convolutional Neural Networks (CNN) in vegetation remote sensing , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[18]  Sebastian Schmidtlein,et al.  Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[19]  Paolo Cignoni,et al.  On Improving the Training of Models for the Semantic Segmentation of Benthic Communities from Orthographic Imagery , 2020, Remote. Sens..

[20]  Plamen Angelov,et al.  Deep Learning-Based Automated Forest Health Diagnosis From Aerial Images , 2020, IEEE Access.

[21]  D. Lagomasino,et al.  Global declines in human‐driven mangrove loss , 2020, Global change biology.

[22]  A. M. Hafiz,et al.  A survey on instance segmentation: state of the art , 2020, International Journal of Multimedia Information Retrieval.

[23]  Blake M. Allan,et al.  The application of Unmanned Aerial Vehicles (UAVs) to estimate above-ground biomass of mangrove ecosystems , 2020, Remote Sensing of Environment.

[24]  Alvin Sarraga Alon,et al.  Tree Extraction of Airborne LiDAR Data Based on Coordinates of Deep Learning Object Detection from Orthophoto over Complex Mangrove Forest , 2020, International Journal of Emerging Trends in Engineering Research.

[25]  Thorsten Hoeser,et al.  Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends , 2020, Remote. Sens..

[26]  Alexander J. Felson,et al.  Mangrove Rehabilitation and Restoration as Experimental Adaptive Management , 2020, Frontiers in Marine Science.

[27]  Ricardo Dalagnol,et al.  Tree Crown Delineation Algorithm Based on a Convolutional Neural Network , 2020, Remote. Sens..

[28]  I. Losada,et al.  The Global Flood Protection Benefits of Mangroves , 2020, Scientific Reports.

[29]  Sergio Marconi,et al.  Cross-site learning in deep learning RGB tree crown detection , 2020, Ecol. Informatics.

[30]  Kerrylee Rogers,et al.  Mangroves give cause for conservation optimism, for now , 2020, Current Biology.

[31]  Fabian Ewald Fassnacht,et al.  Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery , 2019, Scientific Reports.

[32]  E. Casella,et al.  Habitat mapping of remote coasts: Evaluating the usefulness of lightweight unmanned aerial vehicles for conservation and monitoring , 2019, Biological Conservation.

[33]  Ana Cristina Murillo,et al.  CoralSeg: Learning coral segmentation from sparse annotations , 2019, J. Field Robotics.

[34]  Neil Flood,et al.  Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[35]  Wang Jiamin,et al.  Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning , 2019, Forests.

[36]  Le Wang,et al.  Individual mangrove tree measurement using UAV-based LiDAR data: Possibilities and challenges , 2019, Remote Sensing of Environment.

[37]  Marc Simard,et al.  Mangrove canopy height globally related to precipitation, temperature and cyclone frequency , 2018, Nature Geoscience.

[38]  Richard M. Lucas,et al.  Mapping Mangrove Extent and Change: A Globally Applicable Approach , 2018, Remote. Sens..

[39]  R. Danovaro,et al.  Impact of mangrove forests degradation on biodiversity and ecosystem functioning , 2018, Scientific Reports.

[40]  N. Koedam,et al.  The advantages of using drones over space-borne imagery in the mapping of mangrove forests , 2018, PloS one.

[41]  R. Lucas,et al.  Managing mangrove forests from the sky: Forest inventory using field data and Unmanned Aerial Vehicle (UAV) imagery in the Matang Mangrove Forest Reserve, peninsular Malaysia , 2018 .

[42]  Christiane Schmullius,et al.  Estimation of forest aboveground biomass and uncertainties by integration of field measurements, airborne LiDAR, and SAR and optical satellite data in Mexico , 2018, Carbon Balance and Management.

[43]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.

[44]  Masahiko Nagai,et al.  Extraction of Mangrove Biophysical Parameters Using Airborne LiDAR , 2013, Remote. Sens..

[45]  U. Krumme,et al.  Spatial variability of mangrove fish assemblage composition in the tropical eastern Pacific Ocean , 2013, Reviews in Fish Biology and Fisheries.

[46]  D. Alongi.  Carbon sequestration in mangrove forests , 2012 .

[47]  N. H. Ravindranath,et al.  Carbon Inventory Methods : Chinese translation of the English language edition: Carbon Inventory Methods – handbook for greenhouse gas inventory, carbon mitigation and roundwood production projects , 2007 .

[48]  J. Chambers,et al.  Tree allometry and improved estimation of carbon stocks and balance in tropical forests , 2005, Oecologia.

[49]  Marco Ferretti,et al.  Forest Health Assessment and Monitoring – Issues for Consideration , 1997 .

[50]  H. Fuchs.  ECOLOGICAL AND PALYNOLOGICAL NOTES ON PELLICIERA RHIZOPHORAE , 1970 .

[51]  E. Akagunduz,et al.  Deep Semantic Segmentation of Trees Using Multispectral Images , 2022, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[52]  Mathias Kneubühler,et al.  Individual tree crown delineation from high-resolution UAV images in broadleaf forest , 2021, Ecol. Informatics.

[53]  Tariq Kamal,et al.  Remote Sensing: An Automated Methodology for Olive Tree Detection and Counting in Satellite Images , 2018, IEEE Access.

[54]  A. Suhardiman,et al.  Estimating Mean Tree Crown Diameter of Mangrove Stands Using Aerial Photo , 2016 .

[55]  A. Ellison,et al.  The Loss of Species: Mangrove Extinction Risk and Geographic Areas of Global Concern , 2010 .

[56]  James A Allen,et al.  Rhizophora mangle L , 2002 .

[57]  B. Clough,et al.  Allometric Relationships for Estimating Biomass in Multi-stemmed Mangrove Trees , 1997 .