Multilabel classification of peatland plant species from high-resolution drone images

Biodiversity monitoring programs are essential for detecting changes in species distributions and correlating these changes with biotic and abiotic factors. This information is crucial for identifying early problems before they become too difficult to address and for implementing effective managemen...

Full description

Saved in:
Bibliographic Details
Main Authors: Charles Picard-Krashevski, Mickaël Germain, Etienne Laliberté
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125003759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233575000408064
author Charles Picard-Krashevski
Mickaël Germain
Etienne Laliberté
author_facet Charles Picard-Krashevski
Mickaël Germain
Etienne Laliberté
author_sort Charles Picard-Krashevski
collection DOAJ
description Biodiversity monitoring programs are essential for detecting changes in species distributions and correlating these changes with biotic and abiotic factors. This information is crucial for identifying early problems before they become too difficult to address and for implementing effective management strategies. Traditionally, biodiversity monitoring for small plant species has relied on the quadrat method, which requires botanists to identify species in the field. While this method has its advantages, it is limited by the availability of botanists, restricting the scale of monitoring programs. In this study, we explored the potential of using high-resolution photos and artificial intelligence to estimate small plant species cover in peatlands, thereby reducing the need for field-based species identification by botanists. Our approach involves dividing quadrat images into smaller tiles, applying a multi-label classification model to each tile, and calculating species cover based on the identified tiles. Data were collected from 32 sites across Quebec, and images were annotated for five common species: Chamaedaphne calyculata, Kalmia angustifolia, Andromeda polifolia, Rhododendron groenlandicum, and Larix laricina. Our model achieved a global F1 score of 71.68 %, with the highest-performing species (Larix laricina) reaching 87.17 %. Although some species showed lower performance, the estimated species cover by our model in a whole quadrat was comparable to traditional methods. Our results demonstrate that this method offers significant advantages for monitoring broad changes in vegetation.
format Article
id doaj-art-d37ded3ea7a340bcb8c3d4cc89190408
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-d37ded3ea7a340bcb8c3d4cc891904082025-08-20T05:05:59ZengElsevierEcological Informatics1574-95412025-12-019010336610.1016/j.ecoinf.2025.103366Multilabel classification of peatland plant species from high-resolution drone imagesCharles Picard-Krashevski0Mickaël Germain1Etienne Laliberté2Institut de recherche en biologie végétale, Département de sciences biologiques, Université de Montréal, Université de Montréal, 4101 Sherbrooke Est, Montréal, Québec H1X 2B2, Canada; Corresponding author.Centre d'applications et de recherches en télédétection (CARTEL), Département de géomatique appliquée, Université de Sherbrooke, 2500, boulevard de l'Université, Sherbrooke, QC J1K 2R1, CanadaInstitut de recherche en biologie végétale, Département de sciences biologiques, Université de Montréal, Université de Montréal, 4101 Sherbrooke Est, Montréal, Québec H1X 2B2, CanadaBiodiversity monitoring programs are essential for detecting changes in species distributions and correlating these changes with biotic and abiotic factors. This information is crucial for identifying early problems before they become too difficult to address and for implementing effective management strategies. Traditionally, biodiversity monitoring for small plant species has relied on the quadrat method, which requires botanists to identify species in the field. While this method has its advantages, it is limited by the availability of botanists, restricting the scale of monitoring programs. In this study, we explored the potential of using high-resolution photos and artificial intelligence to estimate small plant species cover in peatlands, thereby reducing the need for field-based species identification by botanists. Our approach involves dividing quadrat images into smaller tiles, applying a multi-label classification model to each tile, and calculating species cover based on the identified tiles. Data were collected from 32 sites across Quebec, and images were annotated for five common species: Chamaedaphne calyculata, Kalmia angustifolia, Andromeda polifolia, Rhododendron groenlandicum, and Larix laricina. Our model achieved a global F1 score of 71.68 %, with the highest-performing species (Larix laricina) reaching 87.17 %. Although some species showed lower performance, the estimated species cover by our model in a whole quadrat was comparable to traditional methods. Our results demonstrate that this method offers significant advantages for monitoring broad changes in vegetation.http://www.sciencedirect.com/science/article/pii/S1574954125003759Artificial intelligenceComputer visionConvolutional neural networkDeep learningMulti-label classificationRemote sensing
spellingShingle Charles Picard-Krashevski
Mickaël Germain
Etienne Laliberté
Multilabel classification of peatland plant species from high-resolution drone images
Ecological Informatics
Artificial intelligence
Computer vision
Convolutional neural network
Deep learning
Multi-label classification
Remote sensing
title Multilabel classification of peatland plant species from high-resolution drone images
title_full Multilabel classification of peatland plant species from high-resolution drone images
title_fullStr Multilabel classification of peatland plant species from high-resolution drone images
title_full_unstemmed Multilabel classification of peatland plant species from high-resolution drone images
title_short Multilabel classification of peatland plant species from high-resolution drone images
title_sort multilabel classification of peatland plant species from high resolution drone images
topic Artificial intelligence
Computer vision
Convolutional neural network
Deep learning
Multi-label classification
Remote sensing
url http://www.sciencedirect.com/science/article/pii/S1574954125003759
work_keys_str_mv AT charlespicardkrashevski multilabelclassificationofpeatlandplantspeciesfromhighresolutiondroneimages
AT mickaelgermain multilabelclassificationofpeatlandplantspeciesfromhighresolutiondroneimages
AT etiennelaliberte multilabelclassificationofpeatlandplantspeciesfromhighresolutiondroneimages