A deep learning-based pipeline combining UAV imagery and YOLO models for intertidal population dynamics monitoring
Abstract
Coastal ecosystems are biodiversity hotspots, but the increasing anthropogenic pressure makes them vulnerable. The resulting ecosystem degradation has led to a rise of the scientific and local communities' concern, calling for monitoring systems. In this line, the adoption of remote sensing technologies is increasing as their costs decrease, especially Unmanned Aerial Vehicles (UAVs) in aerial imaging. However, its deep-learning based image analysis remains limited in coastal ecology, particularly for monitoring intertidal population dynamics. Existing methods often rely on labor-intensive in situ sampling, restricting spatial and/or temporal scales. In this work, we develop a UAV-deep learning pipeline for monitoring small, cryptic intertidal species, overcoming limitations of traditional methods. We use the faecal casts of Arenicola marina as a case study to demonstrate the methodology. The workflow combines two You-Only-Look-Once (YOLO) models for object detection and instance segmentation to estimate population abundance and size structure respectively. The models are trained on UAV high-resolution images annotated for faecal casts, recruit casts, and cast tubes. Our detection model achieved a precision and recall over 80%. For the instance segmentation model, a filtering process (detection filter prior to segmentation) was included to reduce false positive ratio. The instance segmentation model measured over 28,700 cast tubes in around 8600 faecal casts, with a strong correlation between manual and automated measurements. Compared to traditional methodologies, the UAV-deep learning one expanded the surveyed area by a factor of 2.5, increased the number of samples by a factor of 90, and notably reduced the sampling effort.
Related
- A review on the use of Synthetic Aperture Radar (SAR) for monitoring shorelines and intertidal areas
- Microbial endolithic symbionts shape the behaviour of intertidal mussels: a multispecies perspective
- Deciphering genomic adaptations and climate resilience in the intertidal seagrass Zostera japonica
- IceWatch: a multimodal deep-learning framework for monitoring glacial lake outburst floods, evaluated at Shisper Glacier, Karakoram
- Predicting habitat associations of five intertidal crab species among estuaries
BibTeX
@article{fernandezalias2026deep,
title = {{A deep learning-based pipeline combining UAV imagery and YOLO models for intertidal population dynamics monitoring}},
author = {Alfredo Fernández-Alías and Olivier Losson and Camille Hennion and Éric Lécuyer and Nicolas Bur and Sylvie Marylène Gaudron and Sébastien Lefebvre},
journal = {Ecological Informatics},
year = {2026},
month = oct,
doi = {10.1016/j.ecoinf.2026.104026},
url = {https://hal.science/hal-05739156v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A deep learning-based pipeline combining UAV imagery and YOLO models for intertidal population dynamics monitoring
AU - Alfredo Fernández-Alías
AU - Olivier Losson
AU - Camille Hennion
AU - Éric Lécuyer
AU - Nicolas Bur
AU - Sylvie Marylène Gaudron
AU - Sébastien Lefebvre
PY - 2026
DA - 2026/10/26
JO - Ecological Informatics
DO - 10.1016/j.ecoinf.2026.104026
UR - https://hal.science/hal-05739156v1
AB - Coastal ecosystems are biodiversity hotspots, but the increasing anthropogenic pressure makes them vulnerable. The resulting ecosystem degradation has led to a rise of the scientific and local communities' concern, calling for monitoring systems. In this line, the adoption of remote sensing technologies is increasing as their costs decrease, especially Unmanned Aerial Vehicles (UAVs) in aerial imaging. However, its deep-learning based image analysis remains limited in coastal ecology, particularly for monitoring intertidal population dynamics. Existing methods often rely on labor-intensive in situ sampling, restricting spatial and/or temporal scales. In this work, we develop a UAV-deep learning pipeline for monitoring small, cryptic intertidal species, overcoming limitations of traditional methods. We use the faecal casts of Arenicola marina as a case study to demonstrate the methodology. The workflow combines two You-Only-Look-Once (YOLO) models for object detection and instance segmentation to estimate population abundance and size structure respectively. The models are trained on UAV high-resolution images annotated for faecal casts, recruit casts, and cast tubes. Our detection model achieved a precision and recall over 80%. For the instance segmentation model, a filtering process (detection filter prior to segmentation) was included to reduce false positive ratio. The instance segmentation model measured over 28,700 cast tubes in around 8600 faecal casts, with a strong correlation between manual and automated measurements. Compared to traditional methodologies, the UAV-deep learning one expanded the surveyed area by a factor of 2.5, increased the number of samples by a factor of 90, and notably reduced the sampling effort.
SN - 1574-9541
ER -