Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation

The global decline in wild bee populations poses significant risks to ecosystem stability given bees' essential role as pollinators. Conserving bee-friendly habitats is critical for the promotion of wild bees and prevention of further losses, which requires a good understanding of the bee'...

Full description

Saved in:
Bibliographic Details
Main Authors: Robbe Neyns, Hanna Gardein, Markus Münzinger, Robert Hecht, Henri Greil, Frank Canters
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233601665695744
author Robbe Neyns
Hanna Gardein
Markus Münzinger
Robert Hecht
Henri Greil
Frank Canters
author_facet Robbe Neyns
Hanna Gardein
Markus Münzinger
Robert Hecht
Henri Greil
Frank Canters
author_sort Robbe Neyns
collection DOAJ
description The global decline in wild bee populations poses significant risks to ecosystem stability given bees' essential role as pollinators. Conserving bee-friendly habitats is critical for the promotion of wild bees and prevention of further losses, which requires a good understanding of the bee's ecology. This study explores the relationship between nesting sites of the ground-nesting bee Andrena vaga and the distribution of Salix trees, an essential pollen source for this and other bee species, within the city of Braunschweig, Germany. Our approach integrates multi-temporal PlanetScope imagery, a tabular transformer deep learning model, and a LiDAR-derived 3D tree model to automate the mapping of Salix trees. The mapping achieved an F1 score of 0.73 (precision: 0.69, recall: 0.78). Field surveys were conducted, documenting Andrena vaga nest aggregations and aggregation sizes. On average, the nearest Salix tree was located approximately 150 m from an aggregation, while the nearest five trees were within 300 m. Literature-guided estimates of the required Salix density for a given aggregation size showed that, on average, the theoretically necessary number of trees was found within 300 m, though for one aggregation the distance exceeded 1000 m. While overall the number of Salix trees around nest aggregations seems to increase with aggregation size, the relationship did not prove to be statistically significant. Our study illustrates the potential of remote sensed based mapping of tree species to enhance our understanding of floral resource availability in pollinator habitats, thereby supporting informed conservation of essential resources for bees and other insects. It also highlights how advances in remote sensing can play an important role in ecological research and habitat conservation.
format Article
id doaj-art-6018bb2d39bf4bdd8cf440ee4cae091f
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-6018bb2d39bf4bdd8cf440ee4cae091f2025-08-20T05:05:34ZengElsevierEcological Informatics1574-95412025-12-019010328810.1016/j.ecoinf.2025.103288Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservationRobbe Neyns0Hanna Gardein1Markus Münzinger2Robert Hecht3Henri Greil4Frank Canters5Cartography and GIS Research Group, Vrije Universiteit Brussel (VUB), Pleinlaan 2, 1050 Brussels, Flemish Brabant, Belgium; AI Lab, Vrije Universiteit Brussel (VUB), Pleinlaan 2, 1050 Brussels, Flemish Brabant, Belgium; Corresponding author at: Cartography and GIS Research Group, Vrije Universiteit Brussel (VUB), Pleinlaan 2, 1050 Brussels, Flemish Brabant, Belgium.Julius Kühn Institute (JKI) - Federal Research Centre for Cultivated Plants, Institute for Bee Protection, Messeweg 11/12, 38104 Braunschweig, GermanyLeibniz Institute of Ecological Urban and Regional Development (IOER), Weberplatz 1, 01217 Dresden, GermanyLeibniz Institute of Ecological Urban and Regional Development (IOER), Weberplatz 1, 01217 Dresden, Germany; Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig (ScaDS.AI), GermanyJulius Kühn Institute (JKI) - Federal Research Centre for Cultivated Plants, Institute for Bee Protection, Messeweg 11/12, 38104 Braunschweig, GermanyCartography and GIS Research Group, Vrije Universiteit Brussel (VUB), Pleinlaan 2, 1050 Brussels, Flemish Brabant, BelgiumThe global decline in wild bee populations poses significant risks to ecosystem stability given bees' essential role as pollinators. Conserving bee-friendly habitats is critical for the promotion of wild bees and prevention of further losses, which requires a good understanding of the bee's ecology. This study explores the relationship between nesting sites of the ground-nesting bee Andrena vaga and the distribution of Salix trees, an essential pollen source for this and other bee species, within the city of Braunschweig, Germany. Our approach integrates multi-temporal PlanetScope imagery, a tabular transformer deep learning model, and a LiDAR-derived 3D tree model to automate the mapping of Salix trees. The mapping achieved an F1 score of 0.73 (precision: 0.69, recall: 0.78). Field surveys were conducted, documenting Andrena vaga nest aggregations and aggregation sizes. On average, the nearest Salix tree was located approximately 150 m from an aggregation, while the nearest five trees were within 300 m. Literature-guided estimates of the required Salix density for a given aggregation size showed that, on average, the theoretically necessary number of trees was found within 300 m, though for one aggregation the distance exceeded 1000 m. While overall the number of Salix trees around nest aggregations seems to increase with aggregation size, the relationship did not prove to be statistically significant. Our study illustrates the potential of remote sensed based mapping of tree species to enhance our understanding of floral resource availability in pollinator habitats, thereby supporting informed conservation of essential resources for bees and other insects. It also highlights how advances in remote sensing can play an important role in ecological research and habitat conservation.http://www.sciencedirect.com/science/article/pii/S1574954125002973Solitary beesOligolectyForaging distancePlanetScopeLiDARDeep learning
spellingShingle Robbe Neyns
Hanna Gardein
Markus Münzinger
Robert Hecht
Henri Greil
Frank Canters
Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
Ecological Informatics
Solitary bees
Oligolecty
Foraging distance
PlanetScope
LiDAR
Deep learning
title Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
title_full Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
title_fullStr Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
title_full_unstemmed Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
title_short Deep learning based mapping of bee-friendly trees through remote sensing: A novel approach to enhance pollinator conservation
title_sort deep learning based mapping of bee friendly trees through remote sensing a novel approach to enhance pollinator conservation
topic Solitary bees
Oligolecty
Foraging distance
PlanetScope
LiDAR
Deep learning
url http://www.sciencedirect.com/science/article/pii/S1574954125002973
work_keys_str_mv AT robbeneyns deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation
AT hannagardein deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation
AT markusmunzinger deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation
AT roberthecht deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation
AT henrigreil deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation
AT frankcanters deeplearningbasedmappingofbeefriendlytreesthroughremotesensinganovelapproachtoenhancepollinatorconservation