NMFS-OSI/yolo11m-cls-noaa-pacific-benthic-cover-t1

Model Summary

YOLO11m-cls is a medium-sized image classification model designed for identifying broad benthic cover categories in underwater reef imagery from NOAA Pacific Islands surveys. It achieves 71.0% top-1 accuracy and 98.8% top-5 accuracy on test data, supporting coral reef monitoring and marine ecosystem research.

A YOLO11m image classification model trained to classify broad benthic cover categories (Tier-1) in underwater reef imagery from NOAA Pacific Islands surveys. The model achieves 71.0% top-1 accuracy and 98.8% top-5 accuracy on held-out test data.

Model Architecture: YOLO11m-cls (medium)
Task: Image Classification
Image Size: 224 × 224 pixels
Classes: 8 broad benthic functional groups

Class	Code	Description
0	CCA	Crustose Coralline Algae
1	CORAL	Hard Coral
2	I	Sessile Invertebrate
3	MA	Macroalgae
4	MF	Mobile Fauna
5	SC	Soft Coral
6	SED	Sediment
7	TURF	Turf Algae

Intended Use

Primary Applications

Automated benthic cover estimation from underwater survey imagery
Coral reef monitoring and ecosystem health assessment
Training baseline for transfer learning to regional datasets
Research in marine biology and ecosystem science

Out-of-Scope Use

Species-level identification (model predicts broad functional groups only)
Regulatory or policy decisions without expert validation
Regions outside the Pacific without additional fine-tuning
Low-resolution or poorly-lit imagery may reduce accuracy

Model Performance

Metric	Value	Meaning
Top-1 Accuracy	71.000	Share of samples whose top prediction is correct
Top-5 Accuracy	98.800	Share of samples whose correct label appears in the top five predictions
Best Validation Loss	0.875	Image-classification evaluation metric
Epochs Trained	87.000	Image-classification evaluation metric
Accuracy	70.500	Share of predictions that match the true label
Balanced Accuracy	64.800	Average recall across classes
Macro F1	0.677	Average F1 score across classes
Macro Precision	0.722	Average precision across classes
Macro Recall	0.648	Average recall across classes

Training Details

Dataset: NOAA Pacific Benthic Cover T1
Total Images: 257,265 (train/val/test split: 70/15/15)
Source: NOAA PIFSC Ecosystem Sciences Division (ESD) — NCRMP surveys
Regions: Hawaii, Marianas, American Samoa, Pacific Remote Island Areas
Annotation Method: Human analysts using CoralNet interface with Tier-1 functional group labels

Parameter	Value
Base Model	`yolo11m-cls.pt` (pretrained)
Dataset	NMFS-OSI/noaa-pacific-benthic-cover-t1
Training Split	180,087 images
Validation Split	38,589 images
Test Split	38,589 images
Epochs	150 (early stopped at 87)
Patience	25
Batch Size	64
Image Size	224 × 224
Optimizer	AdamW
Initial LR	0.001
LR Schedule	Cosine annealing (`cos_lr: true`)
Final LR	0.01 × initial
Warmup Epochs	5
Dropout	0.2
Weight Decay	0.01
Precision	AMP (mixed precision)
Seed	42

Augmentations

Augmentation	Value
HSV Hue	0.02
HSV Saturation	0.4
HSV Value	0.3
Rotation	±20°
Translation	0.1
Scale	0.3
Shear	10°
Flip UD	0.5
Flip LR	0.5
Mosaic	1.0

Usage Guide

```python from ultralytics import YOLO

Technical Details

Architecture: YOLO11m-cls (medium)
Input Size: 224x224
Training Data: NMFS-OSI/noaa-pacific-benthic-cover-t1

Limitations

Geographic Bias: Trained on Pacific Islands data (Hawaii, Marianas, Samoa/PRIA); may not generalize to Caribbean, Atlantic, or Indo-Pacific regions without fine-tuning
Class Imbalance: Minority classes (MF, I, SC) have fewer training examples and lower per-class accuracy
Annotation Uncertainty: Some functional group boundaries are subjective (e.g., turf vs. macroalgae)
Image Quality: Performance degrades on images with poor lighting, motion blur, or heavy particulates

Model Metadata

Repository Metadata

Model Type: image-classification
License: agpl-3.0
Downloads: 61
Library: ultralytics
Base Model: Ultralytics/YOLO11
Datasets: NMFS-OSI/noaa-pacific-benthic-cover-t1
Tags: yolo, yolo11, yolo11m, coral, coral-reef, benthic, image-classification, NOAA, marine-ecology, underwater-imagery, pacific, ncrmp