Running now
Founder's reef tank pilot
Peter Skliros is conducting the first pilot on his own reef system, building the initial longitudinal image, sensor, and intervention history.
AI early warning for reef aquariums
See reef failure
before it becomes visible.
ReeferVision combines coral computer vision, continuous sensor telemetry, and offline edge safety into one operational model of the entire water system — so reef keepers can investigate drift before livestock shows the damage.
DISPLAY · 450 L mixed reef
DEMO
pH
8.21
Temp
26.1°C
Salinity
1.0250sg
Alk
8.4dKH
NO₃
4.2ppm
PO₄
0.040ppm
94
CORAL HEALTH INDEX
Vision model tracking 23 colonies. 1 watch item: minor polyp retraction on Acropora frag F-07, rear-left rack. Trend stable.
14:02:11 · alk dose pump cycle verified · 14.2 mL delivered
uptime 247d
Why this exists
Reef tanks don't crash suddenly.
They crash while you're at work.
01
Testing is intermittent. A manual reading shows one moment, while dosing, evaporation, equipment, and livestock keep changing between tests.
02
The system is fragmented. Cameras, controllers, test results, maintenance notes, and alerts rarely share one operational picture.
03
Visible stress is a late signal. ReeferVision is designed to connect earlier changes in chemistry, equipment behaviour, and coral appearance.
You're testing at 11pm with a Hanna checker and a headlamp. Your alkalinity was drifting for two days before that test. The data was there. Nothing was reading it.
Current stage
Validation has started
on the founder's reef tank.
The current pilot is focused on reliable sensor capture, repeatable camera observations, per-tank baselines, and whether the resulting information improves real maintenance decisions.
Explore today
Product experience
Interactive monitoring, graded-alert, workflow, and digital-twin concepts show how the system is intended to work end to end.
Next proof point
External pilot tanks
Expand beyond the founder's system, compare different reef configurations, measure alert usefulness, and test the installation workflow.
What you are seeing: dashboard values on this site are realistic sample data, not production customer telemetry. Model-performance claims will be published only after pilot validation.
What ReeferVision watches
One model of your entire reef.
Every reading feeds a per-tank baseline — so when something's wrong, the alert is about your tank, not a generic threshold someone else set.
AI Coral Vision
The planned vision pipeline will score each colony for polyp extension, tissue colour shift, and recession against that tank's own photographic baseline. Founding-pilot images will determine which changes can be detected reliably.
planned · Vertex AI vision · longitudinal pilot dataset
Predictive Alerts
Time-series models are designed to learn dosing rhythm, evaporation, and consumption rates, then flag meaningful off-trend behaviour. Pilot evaluation will measure warning time and false-alarm rate before performance is claimed.
planned · BigQuery ML baselines and forecasting
24/7 IoT Sensor Fusion
The edge hub is being designed to combine chemistry, level, flow, leak, and camera signals in one timeline. Cross-signal checks can then distinguish likely probe drift from genuine system change.
in development · edge capture + managed event pipeline
Fleet Intelligence
With explicit opt-in and enough validated systems, anonymised patterns could reveal shared equipment failures or consumable issues while keeping each tank's operating data isolated.
roadmap · opt-in cross-fleet anomaly research
Digital Twin
A 3D flow-and-light map of your tank, built from your wavemaker positions, fixture, and camera view. Move a pump in the app and watch the flow map react — before you move it in the water.
interactive scape builder · PAR & flow estimates per spot
Guided Workflows
Acclimation timed by actual bag readings, water changes from a matched mix vat, placement recommendations per species. The hands-on moments where tanks go wrong — walked through, step by step.
live acclimation timer · per-species placement advice
Setup
Designed for an afternoon setup.
Personalised through observation.
Connect sensors + camera
The target experience pairs an edge hub with supported controllers and a calibrated camera module, without replacing monitoring hardware the owner already trusts.
planned · Wi-Fi or Ethernet · integration validation required
AI learns your baseline
As history accumulates, the system learns daily chemistry swings, photoperiod response, dosing signatures, and each colony's normal appearance. The tank becomes its own reference.
design principle · per-tank baselines before fleet models
Get alerts before escalation
Drift, stress, or equipment anomalies trigger graded alerts — watch, warn, act — with the evidence right there: the trend chart, the camera frame, what probably caused it.
push · SMS · email · webhook
How it all works
From probe to phone,
and back again.
No magic. Sensors and a camera at the tank, a managed cloud pipeline, models that learn your system, and a loop back down to the hardware when something needs doing.
Local sensors & hub
Probes, level and flow sensors, leak sensors, and the camera all feed the ReeferVision hub at the tank. The hub buffers everything locally and runs the safety-critical rules itself — stop the return pump, lock out the ATO — so flood protection keeps working even when your internet doesn't.
edge device · local rule engine · works offline
Up to the cloud
Readings and camera frames travel encrypted to a managed ingestion service, land on an event backbone, and settle into a time-series warehouse — frames into object storage. Nothing for you to maintain, and it costs nearly nothing while a tank is quiet.
Cloud Run ingestion · Pub/Sub · BigQuery · Cloud Storage
The AI layer
Two kinds of models. A vision model scores each coral colony against your tank's own photographic history. Time-series models learn your daily pH swing, dosing rhythm, and evaporation curve, then forecast forward and flag anything off-trend — including equipment failure signatures like a heater starting to oscillate.
Vertex AI vision · BigQuery ML forecasting · per-tank baselines
Useful information, not noise
Everything the models find gets turned into things you can act on: graded alerts (watch / warn / act) with the chart and camera frame attached, maintenance clocks, consumable forecasts, and a dashboard that syncs to your phone in real time.
Firebase sync · push notifications · evidence attached to every alert
Automation closes the loop
For flood-risk and livestock-risk events, decisions flow back down to the hub: throttle the return pump, pause dosing, lock the top-off. The same safety rules are mirrored locally on the hub, so the protective actions never depend on a working connection.
cloud decisions → hub commands · safety mirrored at the edge
Live demo · sample data
It's not just the display tank.
It's the whole water system.
A reef is a chain of processes — RO production, mixing, quarantine, top-off, the display itself. A crash can start anywhere in that chain. ReeferVision watches all of it as one system. Here's what a real setup looks like in the dashboard:
RO/DI Station
STN-01 · 4-stage + DI
Where every drop starts. ReeferVision tracks TDS in and out, membrane pressure, and production rate — and learns when your DI resin or membrane is on the way out.
TDS in
187ppm
TDS out
0ppm
Output
2.1L/h
Filtered tank
82%
Waste tank
34%
Membrane
62psi
TDS out · 30 daysresin depletion curve emerging
model note: membrane rejection normal · DI resin at ~78% capacity, replacement forecast 6–7 weeks · filtered tank covers ~5 days of top-off · waste tank empty reminder at 85%
Salt Mix Vat
STN-02 · 100 L mixing reservoir
Water change water, monitored while it mixes and brought to match the display before it ever touches your tank. No more guessing whether the batch is ready.
Salinity
1.0255sg
Temp
25.9°C
pH
8.3
Vat level
88%
Salt stock
4.2kg
Buy salt in
23days
Salinity · 14 h mix cyclereached target, holding
model note: batch matched to display, safe to transfer · salt consumption learned from your water-change rhythm · reorder reminder lands ~5 days before you'd run out
Quarantine / Hospital Tank
STN-03 · 75 L bare-bottom QT
QT systems are unstable by design — small volume, no mature filtration, medicated water. The vision model scores corals in treatment, and the float valve gets cleanliness tracking, because a gunked-up QT float is how hospital tanks overflow.
NH₃
0.05ppm
Temp
26.0°C
Salinity
1.0250sg
Coral health
87/100
Float clean
71%
Clean due
6days
NH₃ · 48 hslow rise since yesterday's feeding
watch item: trace ammonia rising since yesterday's feeding · suggested: small water change from matched mix vat (STN-02) · coral in treatment trending up from 79 over 8 days · float clean scheduled with next water change
Top-Off & Fill Process
STN-04 · ATO reservoir + transfer pump
The quiet failure point in most systems. ReeferVision tracks reservoir level, fill events, and pump behaviour — a stuck float valve looks very different from normal evaporation, and the model knows it.
Reservoir
64%
Evap rate
1.9L/d
Fill events
11/24h
Reservoir level · 7 daysrefill sawtooth, normal cadence
model note: fill cadence matches learned evaporation curve · reservoir lasts ~8 more days · refill reminder scheduled
Sump & Filtration
STN-05 · sump, skimmer, return · whole-of-system maintenance
The engine room. Sock loading, skimmer behaviour, and return pump draw all have learned signatures — and every serviceable part in the system gets a maintenance clock, so cleans and seal replacements happen on schedule instead of after a failure.
Sock loading
86%
Sump level
22.4cm
Skimmate cup
41%
Return pump
41.2W
Return flow
3400L/h
Skimmer air
9.4L/m
Sock loading · since last changerestriction building, change soon
Maintenance clocks · whole of system
Filter sock changedue in 2 days
Skimmer cup & neck cleandue in 5 days
QT float valve cleandue in 6 days
Return pump impeller cleandue in 3 weeks
Probe recalibrationdue in 5 weeks
Pipe seals & O-ringsreplace in 4 months
model note: clocks aren't fixed timers — sock loading is read from the level differential across it, and the schedule adjusts to how your system actually fouls
And when something does go wrong, it reaches your phone — graded, with the evidence.
Overflow restrictions, leaks, stuck floats, drain blockages — the failures that flood floors don't announce themselves. ReeferVision grades every alert so you know at a glance whether it can wait until you're home:
- WatchSomething's drifting. Logged and tracked — no action needed yet, but the model is paying closer attention.
- WarnIntervene soon. A trend is heading toward a threshold. You get the chart, the camera frame, and the likely cause.
- ActRight now. Flood-risk and livestock-risk events. Where it's safe to, ReeferVision responds first — throttling the return pump or locking out the ATO — then tells you what it did.
21:4798%
ReeferVision
Act · Overflow21:46
Drain flow down 38% — possible blockage
Sump level rising while drain flow falls. Return pump throttled to 60% automatically. Tap to see the flow chart.
Warn · QT-0318:12
Ammonia trending up in quarantine
+0.03 ppm over 24 h. Suggested: 15% water change from mix vat (matched and ready).
Watch · RO/DI14:30
DI resin ~78% capacity
TDS creep detected on output. Replacement forecast: 6–7 weeks at current production.
This is sample data, cycling live so you can see how the dashboard behaves — the numbers are realistic but not from a real tank (yet). Every station feeds the same per-system model, so an anomaly upstream (rising TDS, an off-spec mix batch) is connected to what it will mean downstream in the display.
Guided workflows
Monitoring is half of it.
The other half is doing things right.
The moments where tanks actually go wrong are the hands-on ones — adding livestock, deciding where a coral goes. So the app walks you through them, using what it already knows about your water and your layout.
Acclimation Assistant
New arrival · Acropora frag · started 12 min ago
Tell the app what you're adding and it builds the acclimation plan from live readings — how long the bag floats is decided by the actual temperature difference, not a guess, and the drip rate is set from the salinity gap between bag and tank.
- ✓ Lights dimmed to 20% · flow pumps paused near arrival zone done
-
2
Float bag — equalising temperature
finishes when bag ΔT < 0.2°C, not on a fixed timer 11:42 - 3 Drip mix — slow 1:1 water blend over ~40 min queued
- 4 Placement — recommended spot ready (see tank map) queued
Bag ΔT
0.4°C
Drip rate
3.2mL/m
Bag salinity
1.0242sg
app note: phone buzzes when each step is actually ready · no more standing over the bag with a kitchen timer · full log saved to the livestock record
Placement Advisor
Digital twin · flow & light map · concept render
The app builds a flow-and-light map of your tank from your wavemaker positions, light fixture, and camera view — then recommends where a new coral should go based on what that species actually wants.
AUpper rock shelf — recommended for this Acropora. ~250 PAR · high indirect flow · in the crossfire of both wavemakers without direct blast, close to the light.
BMid rockwork. ~140 PAR · moderate flow · suits most LPS — hammers, torches, favia.
CShaded sand bed. ~60 PAR · low flow · mushrooms, zoas, and anything that sulks in current.
app note: the map updates when you move a pump or change the light schedule · PAR figures are model estimates — calibrate with a one-off PAR meter session for precision
Where this can scale
Start with demanding reef keepers.
Build toward managed living systems.
The first users provide dense feedback and diverse tank histories. The same monitoring loop can then serve operators responsible for many systems and higher-value livestock.
BEACHHEAD · 01
Serious reef keepers
High-value, sensor-rich home systems where avoidable failures are painful and owners already invest in monitoring and automation.
EXPANSION · 02
Aquarium service businesses
A fleet view for teams maintaining tanks across customer sites, with earlier intervention and auditable maintenance workflows.
PLATFORM · 03
Coral aquaculture
Multi-system operations where water chemistry, animal health, equipment performance, and intervention history must be understood together.
Founder
Built from a reef keeper's
own operating problem.
Peter Skliros
Founder · ReeferVision
Peter is building ReeferVision around a live pilot on his own reef tank. The first objective is practical: create a dependable history of what the system measured, what the corals looked like, what changed, and what action was taken.
That founder-operated pilot is the proving ground for the edge hardware, capture routines, per-tank baselines, and alert experience before ReeferVision expands to external pilot systems.
Founding pilot · Expressions of interest
Help prove what actually prevents a reef failure.
ReeferVision is pre-launch. We are preparing a small founding pilot to validate the hardware, collect paired image and telemetry histories, and learn which alerts are genuinely useful. There is no paid subscription today and no model-performance claim hidden behind this form.
Delivered privately by emailApplications go directly to Peter and are not stored in the website database.
Collection notice: ReeferVision collects these details only to assess founding pilot interest. They are delivered to waitlist@reefervision.com.au through an email provider and retained in the receiving mailbox, not in a website database. Email that address to request access, correction, or deletion.
Or email waitlist@reefervision.com.au
Camera + hub module at our cost
Founding pricing when plans launch
Direct line to the people building it