COTSpotter

Fast image analysis · focused validation

Turn reef imagery into trusted evidence.

COTSpotter combines automated QAC, AI detection and efficient human review to turn large reef image surveys into accurate, reviewable evidence for crown-of-thorns starfish (COTS) management.

Follow the evidence Log in to COTSpotter
ObserveAnalyse ValidateDecide
Begin the dive
A crown-of-thorns starfish among coral 01 / NATIVE PREDATOR

The challenge

Native to the Reef.
Destructive at outbreak scale.

Crown-of-thorns starfish naturally feed on coral. The management problem begins when their abundance reaches outbreak levels and coral loss outpaces recovery.

Why do we need COTSpotter?

Cryptic Starfish are often hidden within complex reef structure
Mobile Outbreaks can spread across connected reef systems
Cyclical Outbreaks recur, making earlier detection especially valuable
Scale Surveillance and control effort must be directed where it has most impact

From balance to outbreak

Outbreaks are cyclical. Earlier detection provides more time to target surveillance and control before coral predation accelerates.

Illustrated reef continuum from ecological balance to crown-of-thorns outbreak

Three complementary views

Each method sees the Reef differently.

Manta tow provides broadscale surveillance. Cull operations provide direct observations during targeted control. Each method answers a different question, with different constraints in coverage, timing and effort.

Manta tow, ReefScan image survey and crown-of-thorns culling methods
Manta tow Broadscale observations recorded by a towed observer.
Targeted control Divers locate and control COTS on priority reefs.

Image surveys add persistent, high-detail, reviewable evidence. COTSpotter makes that evidence fast and accurate enough to use at operational scale.

The COTSpotter workflow

AI accelerates the search.
People verify the result.

COTSpotter reduces the time between image collection and reviewable evidence by automating routine image analysis and strategically allocating human effort for difficult cases, validation and feedback.

Upload & QAC

Large surveys are checked before they become evidence.

COTSpotter keeps image evidence tied to the right metadata: location, timestamp, environmental parameters and source context. Automated checks flag missing metadata and filter out imagery that is too blurry, too dark or otherwise unreliable for analysis.

  • Browser uploads go directly to Google Cloud storage.
  • One trip can contain about 200,000 images and 400 GB of data.
  • Modern browser upload APIs can move that volume in 2-3 hours.
AI detection Candidate COTS are marked with bounding boxes for review.
Human validation Reviewers verify likely evidence rather than every frame.

Evidence across scales

Early evidence suggests the signals align.

Early comparisons show promising correlation between image-derived detections and established manta tow and cull evidence. While encouraging, image surveys need to scale to support more robust analysis and stronger evidence.

Image COTS Image survey Manta tow Cull sites

Colour: COTS observed · Gray: zero COTS observed

Image detections, blue image surveys, purple and gray manta tow tracks, and brown and gray cull-site areas aligned on the same reef
Blue: image survey · Purple/gray: manta tow · Brown/gray: cull sites
Image detections compared with manta tow evidence at reef scale
Image detections compared with manta tow evidence
Image detections compared with broad cull evidence
Image detections compared with broad cull evidence

Read with care: blank areas are often gaps in effort or timing—not evidence that methods disagree. Robust comparison requires calibration for differences in method, detectability, coverage, location and timing. That calibration is also necessary before using image-derived evidence for historical trends, time-series inference or operational thresholds within COTS integrated pest management.

The current constraint

Image collection must scale.

The June 2026 snapshot covers approximately 30 months of data from January 2024. Image surveys covered about one-tenth the manta tow records, reflecting lower deployment effort. COTSpotter's automated QAC, AI triage and focused validation will make the expected 10x expansion operationally feasible.

Measured survey distance 9.04× gap
Manta tow8,184 km
Image survey905 km

8,184 km ÷ 905 km = 9.04

June 2026 snapshot covering data from January 2024. Counts and effort use method-specific units and should not be interpreted as directly equivalent measures.
Method COTS evidence Survey / records Effort What it contributes
Cull ~125,000 ~28,000 1,444 days Direct control evidence and a large operational record
Manta tow ~3,000 ~41,000 8,184 km Long-running, broadscale visual surveillance
Image 251 618 905 km Persistent, reviewable, high-detail evidence

Built through collaboration

Reef evidence often sits across organisational, technical and operational boundaries. Important context can be delayed or lost when field observations, imagery, analysis and management systems remain disconnected.

Shared evidence closes gaps between institutions.

COTSpotter provides a traceable evidence layer across organizational boundaries—connecting provenance, review decisions, maps and data products while preserving each partner's responsibilities and data governance.

01

GBRF

Funding, COTS Control Innovation leadership and coordination.

02

GBRMPA + QPWS

Management context, RJFMP field operations and workflow collaboration.

03

AIMS

ReefScan platforms, image generation, provenance and deployment of edge AI.

04

Google

TensorFlow/Kaggle origins, large-scale data collection support, and cloud, Vertex AI and Gemini technology.

05

CSIRO

AI research, integration, validation, analytics and data products.

Information for Sea Country

Sea Country health and condition.

COTSpotter data can help Traditional Custodians see where and when COTS surveys have occurred and what was observed. Initial engagement is planned for the coming months, with the project fact sheet providing a practical starting point for those conversations.

Download the project fact sheet

The COTSpotter workflow is built

Contact coming soon Log in to COTSpotter