Model Garden

JCU Seagrass Coverage Model

A computer vision model designed to classify seagrass coverage from subtidal images into 3 cover categories : low seagrass cover (≥3 <10%), medium seagrass cover
(≥10 <30%), and high seagrass cover (≥30%). The percent coverage used as reference is from Seagrass-Watch percent cover standards on a 50x50cm quadrat. Please only use the model on images with at least 3% seagrass cover.

Open in Playground

Input

The model is trained on an image dataset composed of photoquadrats
collected by drop-camera and SCUBA divers as part as the MMP
(Mckenzie et al., 2022a), the Seagrass-Watch Global Seagrass
Observing Network (Seagrass-Watch, 2022) and the Torres Strait
Ranger Subtidal Monitoring Program (Carter et al., 2021b). Images
were captured between 2014 and 2024 from 28 sites across 18 unique
locations within the coastal and reef subtidal habitats from Torres
Strait to Hervey Bay.

The training dataset included :
- 896 low seagrass cover images
- 1250 medium seagrass cover images
- 537 high seagrass cover images

Model architecture and training parameters

The seagrass cover class model was developped using YOLO11 classification models. We used the yolo11l-cls.pt as a base for our training. We standardised our input images size to 1088x1088 pixels and used the random augmentation function from ultralytics to prevent overfitting. The model converged after 62 epochs.

Jocher, G., Qiu, J., & Chaurasia, A. (2023). Ultralytics YOLO (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics

Model Performance

The testing dataset included :
- 257 low seagrass cover images
- 368 medium seagrass cover images
- 141 high seagrass cover images

Model performance metrics :

Accuracy: 0.81
Precision (weighted): 0.81
Recall (weighted): 0.81
F1 Score (weighted): 0.81

Class-wise Metrics:
low_cover: Precision=0.86, Recall=0.71, F1=0.78
med_cover: Precision=0.83, Recall=0.82, F1=0.82
hi_cover: Precision=0.78, Recall=0.85, F1=0.81

Input

Input

Example

Example Low cover Example Medium cover Example High cover
Input Input Input

Classes

This model classifies seagrass cover classes into the following categories:

  • Low cover = ≥3 <10%
  • Medium cover = ≥10 <30%
  • High cover = ≥30%

For more information about seagrass percent cover estimates, refer to the Seagrass-Watch percent cover standards.

Annotation Method

Each image was visually assessed for seagrass cover and species composition by a trained seagrass scientist and underwent QAQC according to Seagrass-Watch protocols.

Model Limitations

This model was trained on specific dataset and therefore is finetuned for these specific locations. Model performance will vary on new images and we cannot garanty satifactory results. Please use the result output with caution and determine if this model is suited for your data.

Model Metadata

Tags:

Credits: Lucas A. Langlois, Catherine J. Collier and Len J. McKenzie

Example Output