Fish Farm Management Software | KAMAHU

A Practical Data Strategy for Safer Atlantic Salmon Crowding

KAMAHU — Sun, 06 Sep 2026 23:20:22 +0000

Crowding is necessary during transfer, treatment and harvest, but it compresses risk into a short operational window. The 2026 CrowdMonitor report shows that safer decisions depend on combining behaviour, water quality, time and fish condition—not relying on biomass density alone.

The practical takeaway: Treat crowding as a live, time-based operation. Track behaviour above and below the surface alongside water quality, fish condition and operator actions—and use those signals to intervene before welfare deteriorates.

Crowding Atlantic salmon is not simply a question of how many kilograms of fish occupy a cubic metre. It is a live operational process: water volume changes, pumping begins, fish behaviour evolves, oxygen conditions may vary and hazards can develop below the surface even when the water above looks calm.

That is the central lesson from Monitoring and optimising the crowding of Atlantic salmon using health and welfare indicators (CrowdMonitor), a Nofima-led project conducted with the Institute of Marine Research and commercial partners. Its findings point to a practical management principle for fish farmers: steer the operation using several synchronised welfare signals, not one number.

For farm-management systems, the implication is equally important. A crowding record should not be a single density field completed after the event. It should be a time-based operational log that helps staff see deterioration early, act consistently and learn from every crowd. This is where a configurable platform such as KAMAHU’s fish farm management software can provide the structure: linking stock and movement records with tracking sheets, mortality, treatments, sensor data, production reporting and advanced cameras capable of detecting signs of stress.

What the density figures tell us—and what they do not

In controlled tank trials, post-smolts of approximately 530 g were crowded for two hours at four densities corresponding to crowding intensity levels 1 to 4: approximately 100, 130, 180 and 255 kg/m³.

The fish did not show severe behavioural or welfare responses under these experimental conditions, but the data still revealed important changes:

heart rate increased to about 65 beats per minute during crowding;
cortisol and magnesium were elevated one hour after crowding, then returned to pre-crowding levels within 24 hours;
fish at level 1, around 100 kg/m³, grew marginally but significantly better after the event than fish at levels 2 to 4;
contact between fish was higher at level 4, while activity increased at levels 2 to 4;
alignment against the water flow became especially marked after 1 to 1.5 hours at levels 3 and 4;
minor skin changes were still observable 168 hours later.

A second tank trial compared approximately 160 and 320 kg/m³ over one and three hours. It found no major effect of duration or intensity on the measured welfare outcomes, and heart rate rose to about 60 beats per minute during crowding.

These figures need careful interpretation. The tanks were partially drained before fish were crowded sideways with a clam-shell grader, leaving room to move and avoiding forcing fish above the surface. Commercial tank operations often crowd by lowering the water level while pumping fish out. The report explicitly advises caution when generalising the experimental results.

In other words, 320 kg/m³ for three hours is not a general safe limit. The study shows that salmon can sometimes adapt to high density when the environment and method are favourable. It does not show that density or duration can be managed independently of fish condition, water quality, equipment and behaviour.

Crowded fish create intense surface activity, highlighting the importance of continuous welfare monitoring during handling operations.

Turn fish behaviour into a control signal

The established surface scale describes a progression from normal swimming to an emergency:

Level	Observable state	Operational interpretation
1	Slow, normal swimming; no dorsal fins or white sides at the surface	Target condition
2	Normal swimming near the suction point; a few dorsal fins; no white sides	Low stress, but monitor trends
3	Excited, disorganised swimming; more than 20 dorsal fins visible; some white sides continuously visible	Escalating welfare risk; intervene before conditions deteriorate further
4	Many fins and white sides; fish against the net; some lethargic fish; pumping rate cannot remain constant	High risk; conditions are unacceptable if they become more severe than level 3
5	The whole crowd is “boiling”	Emergency with potential for a large fish kill unless fish are rapidly released

The operational goal cited in the report is level 1, and crowding more severe than level 3 is considered unacceptable under the referenced welfare guidance. More importantly, the level is not merely something to record. It is a prompt to act.

During one commercial smolt transfer, the tank remained at level 1 for the first hour while water was drawn down. Intensity rose to level 2 when pumping began and to level 3 around 30 minutes later, as more fins became visible. Operators added water to the tank, reducing the observed intensity. This is monitoring closing the control loop: observe, intervene and verify the response.

The calm-surface problem

Surface observation remains valuable, but it can miss underwater hazards.

In a commercial net-pen crowd preceding delousing, the operation remained at level 2 for one hour and 20 minutes before rising to level 3. At times, visible activity at the surface was not matched by a dangerous underwater state. At other times, the surface appeared stable while fish below were touching the net and risked being pressed against it.

The project therefore recommends combining surface observations with underwater cameras or an ROV. Operators should look for:

fish touching or being pressed against the net;
folds or pockets that can trap fish;
crowding close to equipment or the pumping area;
gasping or other signs of respiratory distress;
burrowing behaviour;
loss of schooling structure, queueing or restricted movement;
insufficient space between the fish group, the net and the surface.

The project’s preliminary underwater risk scale extends from no apparent crowding risk to catastrophic risk. Whether a farm adopts that scale or its own validated protocol, the lesson is the same: surface and subsurface observations must share one timeline.

Stress can rise before injuries become visible

Visible injuries did not always track the stress response during the trials. In the commercial cases, cortisol, lactate and glucose rose progressively during crowding even when injury scores showed few clear changes.

Skin integrity also deserves special attention before another handling step. In the commercial delousing crowd, scale samples from fish exposed for only seven minutes at level 2 showed migration in more than 70% of cultures after 96 hours. For fish sampled after one hour and 40 minutes, including 30 minutes at level 3, the proportion was only around 30%. The report interprets this as a possible sign of micro-damage that may reduce the skin’s healing capacity.

This does not establish a universal time threshold, but it supports two precautions:

treat movement into level 3 as a meaningful escalation, not merely a change of label;
protect fish from additional stress and skin damage after an intensive crowding event, especially when further handling follows immediately.

What a useful digital crowding record should capture

The report recommends a toolbox rather than a single indicator. A useful workflow in farm-management software should connect five layers of information. KAMAHU supports essential records—including stock tracking, movements between ponds, tanks or cages, site-to-site transfers, mortality, tracking sheets and production reports—and has developed dedicated AI models trained to detect signs of stress in fish cohorts. When connected to webcams, these models can identify abnormal behaviour in real time, helping farms build a consistent crowding workflow around the five layers below.

1. Pre-operation readiness

Record fish group, estimated biomass, mean weight, recent mortality, appetite, relevant health issues, previous treatments and visible injury levels. KAMAHU’s stock, weighing, mortality and veterinary-prescription records can bring much of this context together before the operation begins. Add equipment checks and define who can pause, dilute or release the crowd.

2. Environmental conditions

Log oxygen and other relevant water-quality measurements with timestamp, position and depth. An isolated reading is less useful than a trend that can be compared with behaviour and operational actions. Where farms use connected monitoring equipment, KAMAHU can couple with sensors so environmental measurements sit alongside farm records rather than in a separate data silo.

3. A live event timeline

Timestamp the start of water drawdown, net movement, pumping, treatment batches, interruptions and the end of the operation. Add the estimated density where it is available, while recognising that density does not replace direct observation. A configurable KAMAHU tracking sheet can give operators one shared format across sites and crews.

4. Surface and underwater welfare observations

Use a consistent intensity scale and record where each observation was made. Attach camera or ROV evidence when practical. The system should highlight worsening level, repeated white sides, gasping, burrowing, fish-net contact, net pockets or impaired swimming.

5. Actions and outcomes

Connect each warning to an operator response—adding water, slowing or pausing pumping, changing the net configuration, adding oxygen or releasing the crowd—and document whether conditions improved. Follow the event with mortality, appetite and injury observations so the team can compare immediate signals with later outcomes. KAMAHU’s traceability and reporting functions can then help managers review events across fish groups, sites and time periods.

Together, these layers turn welfare documentation into operational intelligence. Instead of asking only, “What density did we reach?”, managers can ask better questions:

At what point did behaviour begin to deteriorate?
Did the deterioration coincide with pumping, falling oxygen or a particular pen zone?
Which intervention restored level 1 or level 2 conditions most quickly?
Do certain fish groups, seasons, crews or equipment configurations produce more warnings?
Did a high-risk observation predict later mortality, appetite loss or injury?

Because KAMAHU is customisable, farms can adapt the fields, reports and alerts to their own operating procedures. The aim is not to force every site into one rigid form; it is to give observations, decisions and outcomes a common structure that can be reviewed and improved.

Three rules for the next crowding operation

1. Keep the crowd steady, slow and controlled

The net-pen trials suggest that giving fish time to adapt, while monitoring the crowd continuously, can limit risk.

2. Treat intensity as dynamic

Density, duration, fish condition, water quality and equipment configuration interact. A fixed density limit cannot describe the whole risk.

3. Make every observation actionable

A welfare score that sits in a form after the event is documentation. A timestamped score linked to alerts, decisions and outcomes is management.

Crowding will always require experienced operators. Better data does not replace their judgement. It gives the team a shared picture, a common language and a record that can improve the next operation.

KAMAHU is designed to support that continuous-improvement loop through real-time monitoring, traceability, configurable reporting, alerts and data consolidation. Explore KAMAHU’s aquaculture management features or contact the team to discuss a crowding workflow tailored to your farm.

Paninnguaq Knudsen (September 2026)

Sources and editorial note

This article synthesises the April 2026 Nofima report Monitoring and optimising the crowding of Atlantic salmon using health and welfare indicators (CrowdMonitor) by Noble et al. The report describes both controlled experiments and a limited number of commercial observations. Figures should therefore be used as evidence from the reported conditions, not as universal operating limits. Farms should continue to follow applicable regulations, veterinary advice, welfare standards and site-specific procedures.

Further operational resources cited by the report:

Can Sea Cucumbers Turn Salmon-Farm Waste into a Resource?

Paninnguaq Knudsen — Fri, 07 Aug 2026 07:30:38 +0000

Sea cucumbers can consume and assimilate organic particles originating from salmon farms. The science behind that statement is credible. The harder question is whether they can intercept enough waste, reliably and economically, to become part of commercial salmon production.

The underlying idea is attractive: place an extractive species near a salmon farm, allow it to feed on material that would otherwise enter the surrounding environment, and produce an additional harvestable crop.

This approach is known as integrated multi-trophic aquaculture, or IMTA. Instead of treating each species as an isolated production unit, IMTA connects species occupying different nutritional levels. Wastes or by-products from one crop become potential inputs for another.

Sea cucumbers are particularly interesting because many species naturally consume suspended particles or organic material deposited on the seabed. Salmon farms release particulate matter in the form of faeces and uneaten feed, creating an apparent biological match.

But an apparent match is not yet an operating business model.

What did the 2012 study demonstrate?

In 2012, researchers E. J. Nelson, B. A. MacDonald and S. M. C. Robinson published a study on the
orange-footed sea cucumber, Cucumaria frondosa.

The researchers measured how efficiently the animals absorbed organic material from different food sources. When exposed to particles with high organic content—including salmon feed and faeces—the sea cucumbers achieved absorption efficiencies above 80%.

In other words, once suitable salmon-derived particles entered the animals’ digestive systems, they were able to extract a substantial proportion of the organic matter.

That is important evidence. It shows that salmon-farm particles are not merely ingested and passed through unchanged. They can serve as a usable food source.

However, absorption efficiency is not the same thing as farm-wide waste-removal efficiency.

An animal might digest more than 80% of the organic matter it captures while capturing only a small fraction of everything released by the farm. The first figure describes digestion. The second depends on currents, particle settlement, animal density, farm design and many other operational factors.

Source: Nelson, MacDonald and Robinson, 2012, Aquaculture.

More recent trials remain encouraging

The concept has continued to attract research interest.

A Scottish feasibility project tested the native sea cucumber Holothuria forskali using a mixture of salmon faeces, uneaten feed and marine sediment. The animals survived the 58-day laboratory experiment while consuming the mixture.

Preliminary project estimates suggested that sea cucumbers might remove as much as 70% of waste within specifically targeted areas below aquaculture pens.

The qualification matters. This was not a finding that 70% of all waste produced by a salmon farm would automatically be removed. It referred to potential removal in areas where waste and sea cucumbers could be brought together effectively.

The project nevertheless points towards an important design principle: success may depend less on simply releasing animals under a farm and more on engineering a system that reliably directs particles towards them.

Source: Sustainable Aquaculture Innovation Centre—sea cucumbers as bioremediators for salmon farms.

Other research has also found changes in the composition of sea cucumbers raised alongside salmon, providing further evidence that salmon-derived material enters their tissues and contributes to their nutrition.

So why has the Norwegian salmon industry not adopted the
concept?

The absence of widespread commercial adoption does not necessarily mean that the biology failed. It reflects the distance between demonstrating a biological process and operating it at industrial scale.

1. The animals can only process waste they intercept

Open-net salmon farms operate in dynamic marine environments. Currents transport faeces and uneaten feed away from the cages, while particles of different sizes settle at different speeds.

A sea cucumber located below or beside a farm cannot consume material that passes outside its feeding zone.

This creates a fundamental distinction:

Digestion efficiency: How much organic material is absorbed after a particle is eaten?
Capture efficiency: How much of the farm’s total waste reaches and is eaten by the sea cucumbers?
System efficiency: How much of the farm’s total environmental load is removed after accounting for the entire production system?

The 2012 study answered the first question positively. Commercial adoption requires convincing
answers to all three.

A later modelling and life-cycle study of an IMTA system found that sea cucumbers (Holothuria scabra) removed only around 0.73% of the fish farm’s solid waste under the stocking-density constraints examined. That study involved red drum (Sciaenops ocellatus) rather than Norwegian salmon, so the number should not be transferred directly to every salmon farm. It does, however, illustrate how a high ability to digest captured particles can coexist with low whole-system removal.

Source: Chary et al. (2020), “Integrated multi-trophic aquaculture of red drum (Sciaenops ocellatus) and sea cucumber (Holothuria scabra): Assessing bioremediation and life-cycle impacts”

2. Commercial farms produce waste at a very large scale

A laboratory tank can maintain close contact between animals and a controlled food source. A commercial farm releases particles across a much larger and less predictable area.

Meaningful remediation could require:

large populations of sea cucumbers;
extensive seabed or suspended cultivation structures;
systems for directing or collecting particles;
regular monitoring;
predator protection;
and equipment for harvesting the secondary crop.

Each addition increases capital requirements, operational complexity and maintenance costs.

The central question for a farmer is therefore not simply, “Will the sea cucumbers eat the waste?” It is, “How many animals and how much infrastructure are needed to remove one ton of it?”

That question does not yet have a universal commercial answer.

3. Stocking density has biological limits

It may appear that low removal could be solved by adding more animals. In practice, sea cucumbers
cannot necessarily be stocked at arbitrarily high densities.
At excessive densities, individuals may compete for food, experience reduced growth or alter sediment
conditions. The appropriate carrying capacity depends on species, temperature, water movement,
oxygen availability, substrate and the spatial distribution of waste.
A remediation system must therefore balance two competing objectives:

maintaining enough animals to process a meaningful quantity of material; and
giving each animal sufficient space and food to remain healthy and commercially productive.

4. A suitable cold-water species must also be a viable crop

The 2012 study used Cucumaria frondosa, a cold-water species found in the North Atlantic. Its
environmental suitability is an advantage for northern aquaculture, but ecological compatibility is only
one part of commercial species selection.
A candidate must also offer:

reliable hatchery reproduction;
predictable juvenile supply;
acceptable growth rates;
manageable mortality;
established processing methods;
regulatory approval;
and a market capable of paying for the final product.

Some of the world’s most valuable sea-cucumber species are associated with warmer waters. A species that performs well in Norwegian conditions may not command the same market price, while a high-value species may not be biologically appropriate for those waters.

Collecting large numbers of wild animals would not be (possible and) a satisfactory scaling strategy. Commercial adoption would require dependable hatchery production without creating additional pressure on natural populations.

5. The business case remains uncertain

IMTA is often described as turning waste into value, but the value does not appear automatically.

A sea-cucumber crop creates additional costs for juveniles, equipment, labour, monitoring, harvesting, processing, certification and sales. Those costs must be covered by some combination of:

sea-cucumber revenue,
improved farm performance,
reduced environmental-monitoring or remediation costs,
additional production permissions,
market premiums,
or regulatory incentives.

Without one or more of those benefits, the salmon producer bears the cost of the environmental service while its financial return remains uncertain.

European IMTA programmes have repeatedly identified economics, market development, regulation and operational complexity as major obstacles—not only the underlying biology.

Source: EU IDREEM project: Increasing Industrial Resource Efficiency in European Mariculture.

6. Existing farms were not designed as multi-species systems

Adding sea cucumbers is not as simple as attaching one more cage.

The system may need to accommodate different production cycles, husbandry protocols, equipment, veterinary considerations and harvesting procedures. The most suitable location for growing salmon may not be the best location for sea cucumbers.

Responsibility must also be clear. Who owns the secondary crop? Who monitors it? What happens if disease, mortality or an escape occurs? How should environmental performance be measured?

Aquaculture regulations and licences have traditionally been organised around individual species and defined production sites. A multi-species farm can therefore encounter administrative requirements that were not designed with nutrient recycling in mind.

A 2022 systematic review and industry survey found that commercial IMTA implementation on Atlantic salmon farms is limited by uncertain mitigation performance at scale, the cost and complexity of cultivating extractive species, insufficient commercial demonstration, and limited institutional support.

Source: Sickander, O. and Filgueira, R. (2022). “Factors affecting IMTA (integrated multi-trophic aquaculture) implementation on Atlantic Salmon (Salmo salar) farms.” Aquaculture, 561, 738716.

7. Sea cucumbers address only one part of salmon farming’s
footprint

Sea cucumbers could potentially intercept particulate organic material. They do not provide a complete environmental solution.

They do not directly prevent:

salmon lice;
fish escapes;
disease transmission;
fish mortality;
or all dissolved nutrient emissions.

Different extractive organisms perform different functions. Seaweeds, for example, can take up dissolved inorganic nutrients, while shellfish may capture suspended particles. Deposit-feeding sea cucumbers can act on material reaching the seabed, and suspension-feeding species can intercept particles in the water.

A serious IMTA strategy may therefore require several complementary species rather than treating sea cucumbers as a stand-alone remedy.

Norway’s Institute of Marine Research identifies salmon lice and escaped farmed fish among the major environmental challenges associated with salmon farming. It is understandable that considerable investment and regulatory attention have consequently gone towards lice control, containment, welfare and escape prevention.

Source: Norwegian Institute of Marine Research—Environmental impacts of aquaculture.

A promising organism in search of the right system

The evidence supports a balanced conclusion.

Sea cucumbers can consume salmon-derived organic matter. They may also convert part of that material into a saleable product while contributing to sediment processing and nutrient cycling.

What has not yet been demonstrated consistently is a commercially attractive method that:

intercepts a substantial share of farm waste;
maintains healthy sea cucumbers at appropriate densities;
works under variable farm and current conditions;
produces a marketable secondary crop;
satisfies regulatory requirements;
and delivers a measurable net environmental benefit.

This is not a reason to abandon the concept. It is a reason to focus research on system design and commercial validation rather than repeating proof that sea cucumbers can eat fish-farm particles.

What would make adoption more likely?

For aquafarmers, the most valuable next-stage trials would report results in operational terms:

kilograms of salmon waste removed per square meter;
percentage of total farm particulate output intercepted;
sea-cucumber growth and survival over complete production cycles;
labour and infrastructure costs;
harvest value;
performance under different current and seabed conditions;
and environmental outcomes compared with an equivalent salmon farm without sea cucumbers.

It would also be useful to compare several configurations: animals directly on the seabed, animals in trays or cages, and systems that first collect or concentrate solids.

The most compelling commercial model may eventually combine biological extraction with physical waste capture. Concentrating particles before feeding them to sea cucumbers could make the food supply more predictable and reduce the main limitation of open-water systems: contact between waste and the extractive crop.

From proof of concept to practical aquaculture

Sea cucumbers offer a powerful image of circular aquaculture: nutrients that would otherwise be dispersed are captured and transformed into biomass.

The image is supported by real biology—but commercial reality demands more.

The key question is no longer whether a sea cucumber can digest salmon waste. Research has shown that it can. The key question is whether farms can deliver that waste to enough sea cucumbers, at an acceptable cost, while producing measurable environmental benefits and a marketable crop.

That remains an open engineering, biological and economic challenge.

For the salmon industry, the appropriate position is neither uncritical enthusiasm nor dismissal. Sea-cucumber IMTA deserves continued testing, particularly in systems designed from the outset to collect and redirect solids. At the same time, claims about waste removal should always distinguish between what an individual animal digests and what an entire farm actually prevents from entering the environment.

Paninnguaq Knudsen (July 2026)

Turn Aquaculture Data into Better Decisions

Innovations such as Integrated Multi-Trophic Aquaculture show how better system design, monitoring and operational data can help fish farms improve resource efficiency and environmental performance. KAMAHU’s fish farm management software enables aquaculture producers to monitor production, feeding, biomass, mortality, traceability and farm performance in real time – helping teams develop more efficient, sustainable and profitable aquaculture operations. Discover KAMAHU’s aquaculture farm management system and request a demonstration to see how digital farm monitoring can support your business.

References and further reading

Proliferative Kidney Disease in Rainbow Trout: How One Breton Fish Farm Beat the Odds

KAMAHU — Tue, 07 Jul 2026 09:50:35 +0000

This case study demonstrates how alternativ agroecological principles transformed disease control at a commercial rainbow trout farm in Brittany, in the context of global warming.
The practices described were tracked using KAMAHU’s data-driven aquaculture management software which has been in place at the farm since 2016.

The original and official text can be found here : https://hal.inrae.fr/hal-05677497v1
Robert Le Coat, Christophe Jaeger. L’hépatonéphrite parasitaire (Tetracapsula bryosalmonae) : Témoignage d’un changement gagnant de pratiques en élevage de truite arc-en-ciel (Oncorhynchus mykiss). 9èmes Journées de la Recherche Filière Piscicole, Itavi, Jun 2026, Rennes, France. ⟨hal-05677497⟩

ABSTRACT

Proliferative Kidney disease (Tetracapsula bryosalmonae) is a disease that occurs when the water temperature exceeds 15°C and can cause losses of over 90%. There is no cure or preventive treatment, and the advice is to limit the effects of the disease in reducing food quantity delivered to a minimum.
Agroecology focuses on improving animal health by addressing the causes of the disease in order to adapt farming practices and reduce its effects. The case study presented illustrates such a change in rainbow trout (Oncorhynchus mykiss) farming practices. Fry are raised in recirculating water systems, fed with well water at a constant temperature of 12°C and free of the parasite. For fry from spring eggs, the strategy is to infect them while rearing them in water below 15°C, before transferring them, at the end of summer, to outdoor raceways supplied with water from river. For fry from autumn eggs, the individuals remain naive to the parasite until they are transferred to raceways in mid-summer. In this way, regardless of the batch, the young trout develops the disease under rearing conditions that do not allow it to progress to clinical cases. The trout thus acquire immunity that lasts until they reach commercial size. In this way, overall health standards have been improved up to a loss rate of around 5%, which in turn has improved growth rates.
This example sets out the strategies to be adopted to control this infection and adapt practices according to the configuration of each affected fish farm.

The Challenge: A Disease That Thrives in Warm Water

Proliferative Kidney Disease (PKD), caused by the parasite Tetracapsula bryosalmonae, represents one of the most significant threats to rainbow trout (Oncorhynchus mykiss) farming. The disease emerges when water temperatures exceed 15°C, and without intervention, it can cause mortality rates exceeding 90 percent.

Crucially, there are no curative or preventive treatments available. Traditional advice has been to minimize feed input during outbreaks, but this approach fails to address the root cause and results in significant production losses.

At Pisciculture du Dourduff in Plougoulm, Brittany—a farm producing approximately 200 tons of rainbow trout annually—PKD had been a persistent problem since at least the 1990s. After the 2003 ban on malachite green (previously used in combination with formalin), the farm needed a new strategy.

The Solution: Rethinking Farm Practices Through Agroecology

Rather than seeking technological or biochemical solutions, the farm embraced an agroecological approach: understanding the disease’s life cycle and adapting farming practices to disrupt it.

Understanding the Parasite’s Life Cycle

PKD has a complex lifecycle:

The parasite’s spores are released from its host—a freshwater bryozoan (Fredericella sultana)—when water temperatures rise above 9°C.
Free-swimming spores remain infectious for only 12–24 hours.
They enter fish through gills and skin.
Clinical disease manifests only when water exceeds 15°C in naïve (previously unexposed) fish.
Fish that survive initial exposure develop immunity specific to the local parasite strain.
The parasite cannot transmit directly from fish to fish; it must return to bryozoans to complete its cycle.

The Innovative Farming Strategy

The farm implemented two distinct rearing protocols based on spawning season:

1. Spring-Spawning Fry (Summer Alevins)

Raised in recirculating aquaculture systems (RAS) fed with parasite-free groundwater at a constant 12°C.
From July onward, controlled amounts of river water (containing the parasite) are gradually introduced.
Temperature is carefully managed to remain below 15°C through precise mixing of groundwater and river water.
Fish become infected but do not develop clinical disease due to the controlled temperature.
In September, after the critical high-temperature period, fish are transferred to outdoor raceways at ~15g.

2. Autumn-Spawning Fry (Winter Alevins)

Also raised in RAS with parasite-free groundwater.
Kept naïve to the parasite until mid-summer transfer to raceways.
First exposure occurs during the critical period (July-August) when fish weigh ~100g.
The late exposure means the infection develops after the peak temperature period.
More mature fish with stronger immune systems can fight the infection before it becomes clinical.

This approach ensures that all fish develop immunity under conditions that prevent the disease from reaching clinical stages, providing protection through to commercial size.

Building of the RAS in 2018

The Results: From 60% Losses to 95% Survival

The transformation in farming practices delivered dramatic improvements:

Batch	Initial Number	Mortalities	Survival Rate
1 (Old method)	80,000	36,667	54.2%
2 (Old method)	130,000	75,059	42.3%
3 (Old method)*	160,000	18,970	88.1%
4 (New method)	50,000	4,976	90.1%
5 (New method)	55,241	5,209	90.6%
6 (New method)	68,234	10,076	85.3%
7 (New method)	60,000	4,349	92.8%
8 (New method)	85,000	7,807	90.8%

*Batch 3 used groundwater at the start of grow-out, unlike other old-method batches

Key Improvements:

Survival rate from fry to market: Increased from ~42% to ~93%.
Growth performance: Autumn-spawned trout now reach 800g at 14 months (vs. 250g previously).
Production efficiency: Requires 55% fewer eggs to meet production targets (140,000 vs. 300,000 for spring batches).
Antibiotic use: Significantly reduced due to improved overall health.
Farmer well-being: Eliminates the stress of summer mortality events.

How Farm Software Enabled This Transformation

The success of this approach relied on precise data management—where specialized aquaculture software played a crucial role:

Temperature Monitoring & Control
- Daily water temperature tracking from river and groundwater sources.
- Historical data (available since 1992) enabled identification of the “critical period”.
- Near real-time water mixing to maintain optimal temperatures in RAS.
Production Tracking
- Monitoring fish growth rates across different batches and rearing systems.
- Tracking survival rates at each life stage.
- Managing the transition timing between RAS and raceways.
Water Quality Management
- Monitoring oxygen levels (with jet platform systems in all basins).
- Tracking water source usage (groundwater vs. river water ratios).
- Ensuring parasite-free water supply for vulnerable life stages.
inventory & Planning
- Managing egg arrivals (April and November deliveries).
- Planning production cycles to align with temperature patterns.
- Reducing egg purchases through improved survival rates.

Key Success Factors

The farm’s success depended on several critical elements:

Access to parasite-free groundwater – Essential for maintaining naïve fish and controlling exposure timing
Recirculating aquaculture systems – Enabled precise temperature control and efficient use of limited groundwater
Additional infrastructure – A new RAS building constructed in 2018 near a second groundwater source
Daily monitoring – Consistent temperature tracking was indispensable for timing transfers and water mixing

Conclusion: A Model for Climate-Resilient Aquaculture

This case study demonstrates that even without medical treatments, significant disease control is possible through adaptive farming practices. As climate change increases water temperatures, PKD and similar diseases will become more prevalent. The approach developed at Pisciculture du Dourduff provides a practical, cost-effective model that other farms can adapt to their specific configurations.

The key insight: By understanding the pathogen’s biology and leveraging available resources (groundwater, RAS technology), farms can turn a major production constraint into a manageable challenge. The use of farm management software to track temperatures, growth rates, and water quality parameters was instrumental in implementing and refining this approach.

While further research is needed to fully understand the immunization mechanisms, this case proves that agroecological principles combined with precise data management can deliver sustainable solutions in aquaculture.

The KAMAHU team visiting the Moulin du Dourduff trout farm in 2020 with its actual manager Amaury GUET (on the right)

Article from 12th August 2026 about this case published by Hatchery International : https://www.hatcheryinternational.com/how-one-french-farm-developed-pkd-resistance-in-its-rainbow-trout/

Mapping Waterways

KAMAHU — Wed, 07 Jan 2026 00:16:48 +0000

Like the rivers that shape landscapes, fish farms are part of a living, sustainable balance.
Happy New Year from the KAMAHU Team to all those who watch over aquaculture ecosystems every day.
May 2026 flow with the same continuity as our waterways, and may this new year bring stability to the ponds, serenity in monitoring, and success in your farming operations.

Here is the code we used to draw the map of waterways for America. It’s the same logic for Europe, Africa and Asia.
NB : We work on Linux. You’ll find below the command lines.

1) Download the last version from OSM for the continent :

wget -O north-america-latest.osm.pbf https://download.geofabrik.de/north-america-latest.osm.pbf
wget -O north-america-latest.osm.pbf.md5 https://download.geofabrik.de/north-america-latest.osm.pbf.md5
md5sum -c north-america-latest.osm.pbf.md5

wget -O south-america-latest.osm.pbf https://download.geofabrik.de/south-america-latest.osm.pbf
wget -O south-america-latest.osm.pbf.md5 https://download.geofabrik.de/south-america-latest.osm.pbf.md5
md5sum -c south-america-latest.osm.pbf.md5

NB : Files can be large, so we use –continue –no-cache in case of micro-interruptions.

Check integrity of the file :

md5sum -c africa-latest.osm.pbf.md5

You should get

africa-latest.osm.pbf: OK

If this not the case, just remove both files and re-download.

NB : Sometimes, you need to rename the .osm.pbf file to match the .md5 file.

2) Filter waterways :

cat > waterway-filter.txt << ‘EOF’
w/waterway=river
w/waterway=stream
w/waterway=canal
#w/waterway=drain
#w/waterway=ditch
EOF

NB : We comment drains and ditches; otherwise would the file much too big.

osmium tags-filter north-america-latest.osm.pbf -e waterway-filter.txt -o waterways_north_america.osm.pbf --overwrite
osmium tags-filter south-america-latest.osm.pbf -e waterway-filter.txt -o waterways_south_america.osm.pbf --overwrite

3) Export GeoJSONSeq

osmium export waterways_north_america.osm.pbf -f geojsonseq -o waterways_north_america.geojsons --overwrite
osmium export waterways_south_america.osm.pbf -f geojsonseq -o waterways_south_america.geojsons --overwrite

4) Concatenate (stream)

cat waterways_north_america.geojsons waterways_south_america.geojsons > waterways_america.geojsons

5) Render points Datashader (low RAM)

Since we built this map on a small PC, we had to minimize the size of the files and the resources that had to be mobilized.

Create a file render_america_points.py with

cat > render_america_points.py << 'EOF'
import json
import numpy as np
import pandas as pd
import datashader as ds
import datashader.transfer_functions as tf
from datashader.utils import lnglat_to_meters

INP = “waterways_america.geojsons”
OUT = “waterways_america.png”

minlon, minlat, maxlon, maxlat = -170.0, -60.0, -25.0, 83.0
x0, y0 = lnglat_to_meters(minlon, minlat)
x1, y1 = lnglat_to_meters(maxlon, maxlat)

W, H = 7000, 7000
cvs = ds.Canvas(plot_width=W, plot_height=H, x_range=(x0, x1), y_range=(y0, y1))

CHUNK_PTS = 3_000_000
xs = np.empty(CHUNK_PTS, dtype=”float64″)
ys = np.empty(CHUNK_PTS, dtype=”float64″)
n = 0

agg = None
STRIDE = 1

def flush():
global n, agg
if n == 0:
return
df = pd.DataFrame({“x”: xs[:n], “y”: ys[:n]})
a = cvs.points(df, “x”, “y”, agg=ds.count())
agg = a if agg is None else (agg + a)
n = 0

def add_coords(coords):
global n
if not coords:
return
for i in range(0, len(coords), STRIDE):
pt = coords[i]
if not pt or len(pt) < 2:
continue
X, Y = lnglat_to_meters(pt[0], pt[1])
xs[n] = X
ys[n] = Y
n += 1
if n >= CHUNK_PTS:
flush()

with open(INP, “r”, encoding=”utf-8″, errors=”ignore”) as f:
for line in f:
line = line.strip()
if not line:
continue
try:
feat = json.loads(line)
except json.JSONDecodeError:
continue
geom = feat.get(“geometry”)
if not geom:
continue
t = geom.get(“type”)
if t == “LineString”:
add_coords(geom.get(“coordinates”))
elif t == “MultiLineString”:
for coords in geom.get(“coordinates”) or []:
add_coords(coords)

flush()

img = tf.shade(agg, how=”eq_hist”)
img.to_pil().save(OUT)
print(“OK ->”, OUT)
EOF

6) Launch

export PYTHONNOUSERSITE=1
source .venv/bin/activate
python render_america_points.py

7) Cleaning

Don’t forget to remove the files in order to free space (several tens of gigabytes)

rm -f north-america-latest.osm.pbf* south-america-latest.osm.pbf*
rm -f waterways_north_america.osm.pbf waterways_south_america.osm.pbf
rm -f waterways_north_america.geojsons waterways_south_america.geojsons

Here is the result with some tiles that seem to be uncompleted :

It is interesting to observe that North America appears here as a set of discontinuous “tiles.”
In reality, this stems from the origin of the OSM data, which has heterogeneous coverage.
Some areas (the United States, southern Canada) are extremely well mapped,
while others (northern Canada, Alaska, boreal regions) are very incomplete.
Contributors often import data in blocks (basins, provinces, local projects), which results in dense areas and nearly empty ones, with rectangular or polygonal outlines.

The initial files used, which come from Geofabrik, are themselves aggregated from regional sub-extracts. The discontinuity is therefore already present in the PBF, and the effect is amplified by the Datashader rendering.

In Europe, OSM coverage is very homogeneous. In Africa, it is patchy but more “organic.” In the Americas, the contrasts are stark and produce this mosaic effect. The resulting map therefore shows the geography of human contribution to OSM. It is more a map of the density of hydrological mapping than a map solely of rivers.

If you’re interested in our skills in map design or python coding, get in touch with us.

All the best from the KAMAHU Team !

KAMAHU — Mon, 05 Jan 2026 14:37:06 +0000

In 2025, 82 versions of the service were delivered on each of the continental servers!
In 2026, it will be the same pricing for the 9th consecutive year, along with more versions featuring new and major functionalities!
For the one who would be interested, you’ll find HERE the code we used to produce this map of the European rivers. Otherwise, just get in touch with us.

Press book

KAMAHU — Sun, 31 Aug 2025 19:52:07 +0000

Various articles published in recent years about KAMAHU (page in construction)

Sonar, La revue du Campus mondial de la mer (2025.06) : Observer les fermes aquacoles depuis l’espace
Produits de la Mer (2024.11) : L’IA au service de la filière des produits aquatiques
Fish Farmer Magazine (October-November 2018) : KAMAHU offer a SAASy solution

KAMAHU and ESA BIC: Satellite Imagery for Aquaculture

KAMAHU — Sun, 29 Jun 2025 11:37:41 +0000

🚀 Extract of SONAR #12 (June 2025),
the news magazine of Campus Mondial de la Mer (Brest, BZH)
that spreads about our incubation into
the European Space Agency (ESA)
Business Incubation Center (BIC) ⬇️

HOW MUCH does a Machine Learning model cost ?

KAMAHU — Thu, 01 Aug 2024 06:00:08 +0000

AI solutions are becoming increasingly accessible to businesses. Harnessing the power of artificial intelligence, neural networks have the ability to analyze vast amounts of data, identify complex patterns, and make accurate predictions, enabling businesses to unlock new opportunities and drive growth.

At KAMAHU, we specialize in providing comprehensive neural network services that can revolutionize your business. Whether you’re looking to enhance your data analysis capabilities, automate repetitive tasks, or optimize operational processes, our team of experts is here to help you leverage the full potential of neural networks.
Data lies at the heart of neural networks, and our services start with understanding your unique data landscape. We work closely with you to identify and collect relevant data sources, ensuring that your neural network models are built on a solid foundation. We employ cutting-edge techniques to preprocess and clean the data, making it ready for training the neural network models.

Data collection and preparation are key and may cost a lot, or nothing, depending on what you already store.

Model design would cost much less than the cost of your ultrasound scanner for instance : a few hundreds or thousands Dollars.

The development of neural networks is a specialized task that requires expertise and experience. KAMAHU excels in designing and implementing neural network architectures tailored to your specific business needs. Get in touch with us

Revolutionizing Aquaculture with AI and Machine Learning: real-world applications and success stories

KAMAHU — Wed, 03 Jul 2024 17:00:49 +0000

Article by Mikael Dautrey (ISITIX) and Kilian Delorme (KAMAHU) – July 2024

Machine learning is transforming aquaculture with groundbreaking applications in image classification, image segmentation, video analysis, and object detection.

In this post, we explore four innovative projects that demonstrate real results in the field:

Image classification using ultrasound – to detect frog maturity, essential for breeding programs, improving breeding cycles and increasing yield.
Image segmentation – to identify malformations in fish, aiding in early health interventions.
Video analysis and scene understanding – to provide continuous monitoring of fish farms, detecting anomalies in behavior and environmental conditions.
Object detection algorithms – to identify fish cages from satellite images, optimizing farm management and resource allocation.

Image classification : detecting frog maturity using ultrasound

In a frog hatchery, to optimize tadpoles production, it is necessary to estimate frog maturity in order to separate the spawning females. To do this, the breeder performs ultrasound scans on the frogs. Initially, this work requires a highly qualified biologist to decide on frog maturity. Agnes Joly who runs the AQUAPRIMEUR hatchery wanted anyone on her farm to be able to carry out the operation, through the use of an automatic classification system.

Designing a device to automatically classify ultrasound scans in an industrial environment is quite a challenge.

Key challenges and solutions:

Image collection and validation: we validated the feasibility of using machine learning to classify ultrasound images, despite having only a few hundred classified scans initially.
Ultrasound scanner interface: we interfaced with the ultrasound scanner to automate the task, using auxiliary electronics to read and process the video signal.
Ergonomic solutions: in the environment of an aquaculture farm, we implemented an audio interface, enabling hands-free operation, and complemented it by a touch screen.
Reliability and performance: we tackled issues like peripheral interfacing, noise reduction, and power supply.

Collecting images and designing a ML model, the easy part of the project

When we began this project in 2020, we faced significant challenges. Traditional models were hard to optimize, and deep learning required thousands of images, while we had only a few hundred classified ultrasound scans. Today, advances in ML tools and our growing expertise have made this task routine. It remains an important part of the project, especially in collaborating with experts, whose maturity classifications can vary with their subjective judgment.

Interfacing with the ultrasound scanner, a matter of electronics and DIY

We’ve only done this for one model today, but we’re confident in our ability to interface with any ultrasound scanner on the market. After testing several methods, we decided to read the video signal directly and process it via the auxiliary electronics box. There’s still plenty of room for improvement, but it works.

Finding ergonomic solutions to facilitate the operator’s work, still a work in progress

In an aquaculture farm, the environment is obviously challenging; workers often need both hands to carry loads or handle animals. Solutions that work in an office, like a mouse and keyboard, are no longer suitable. We opted for an audio interface complemented by a touch screen.

The audio interface works both ways, allowing for speaking and listening, with the user wearing a headset with a microphone and earphones.

The touch screen provides visual feedback to validate commands sent to the system, read information, or perform certain complex actions via audio. This was one of the most difficult parts of the project, and we are still working to improve the solution.

Addressing various reliability and performance issues, 80/20 law

A complex project like this brings its share of time-consuming little problems, such as headset peripheral interfacing, noise reduction, power supply, shock and humidity protection, model and response time optimization, and application architecture. This has a direct impact on development costs, and at some point you have to ask yourself whether it’s worth it.

A long-term investment, beyond bottom-line improvement

Automation and work simplification were the primary drivers for this project. The system will eliminate the access barrier to using the ultrasound scanner, ensuring consistent use and standardized results, regardless of who performs the operations.

Image segmentation : detecting malformations

A tedious but essential work

Research laboratories studying fish deformities need to measure various dimensions of fingerlings, such as head size, body size, camber, yolk sac appearance and eye shape. The specific measurements often depend on the research focus or the requirements of a particular publication. Traditionally, this involves taking photos and measuring dimensions in pixels using a scale shown in the photo. This method is slow, time-consuming, and prone to inaccuracies.

A model for this task

A research laboratory which had supervised a doctoral thesis about the direct and transgenerational ecotoxicity of glyphosate on the health of rainbow trout approached us to test the feasibility of using machine learning for measuring fish deformities. Using a sample of around 100 measured images, we developed a model tailored to this task.

Annotations reloaded

The images had been annotated by drawing lines with an image editor and then recording the values in an Excel file. Although the information was available, it couldn’t be easily integrated into a machine learning pipeline. Therefore, we had to redo all the annotations using a dedicated tool. For this project, we used VGG VIA, a lightweight image annotation software developed by the Visual Geometry Group (VGG) at the University of Oxford.

From pixels to geometry

We then trained a segmentation model that allowed us to easily measure the main characteristics monitored by the researchers. Next, we had to convert the pixel measurements into units of measurement (mm). This task was complicated by the absence of documentation or traces of the device used to take the photos, including camera optics and mounting, making it difficult to accurately estimate the geometric deformations of the images.

A well-functioning model, but with a limited scope

The model worked well, but it was limited by the specific research topic for which it had been designed. Each research topic would require a different model. We don’t see a cost-effective opportunity to create customized Deep Learning models for biology researchers, as each research topic comes with its own set of measurements and therefore a dedicated model that will serve only once and for a few thousand images.

It would be more advantageous to develop a software environment dedicated to customizing ML models for researchers. This environment would provide a standardized photography tool, standardize the image annotation process and automatically produce customized models tailored to their specific research topics.

Video analysis and scene understanding : monitoring fish farms

Many aquaculture start-up projects use underwater cameras to monitor fish, providing information on fish quantity, size, and health status. While this idea is excellent in theory, operating underwater cameras is difficult due to water turbidity, the need for frequent glass cleaning, and the high cost of watertight housing. To address these issues, we tested a different solution by positioning aerial cameras above the farm’s tanks. Since birds excel at spotting fish from above, we thought, why not us?

Positioning cameras

A fish farm with a small but efficient facility on the banks of a river in Brittany wanted to monitor its tanks more effectively. Our test site breeds trout with moderately sized raceways, approximately 50 meters by 5 meters, and uses a RAS system located under cover. We strategically positioned cameras around the tank, taking into account the constraints of the location, available height, power supply, and network. This setup allowed us to collect data on a NAS, which we then processed.

Processing videos, more data, but not significantly more information, except time

Processing videos brought more data, but information varies slowly from image to image. When we started this project in 2021, we had primarily been working with still images. Initially, we were overwhelmed by the volume of data produced by just a few cameras. Gradually, we developed our tools and methods to better handle the specifics of video data: a large quantity of similar images with different temporalities, ranging from seconds to minutes, hours, days, and months.

Going further: a territory to explore

Guided by Robert Le Coat and Amaury Guet, we have today a solid understanding of the production process. We can detect simple activities such as movement around the tanks, feeding, and aerator activation. However, there is still much work to be done in optimizing camera positions, selecting the right optics, and defining what truly constitutes valuable information in images of an aquaculture farm. This ongoing exploration promises to refine our approach and enhance the effectiveness of our monitoring solutions.

Object detection : detecting cages from satellite images

Satellite imagery offers a vast potential for monitoring aquaculture installations globally.

The globe at your fingertips

We were put in touch with a satellite data operator who was looking for new fields of application and new opportunities to resell its data. Satellites enable us to work on an unimaginable scale, covering the surface of the globe in just a few clicks.

A very simple challenge : detecting fish cages

To test the potential of satellite data, we started with a very simple problem: detecting fish cages installed by offshore fish farmers around the world. This initial challenge allowed us to explore the capabilities of satellite imagery in identifying and monitoring aquaculture installations on a global scale.

Satellite Data Sets: a complex field

Each satellite operator manages its own constellations, comprising specific types of satellites equipped with sensors that have distinct capabilities, measured wavelengths, measurement precision, and spatial resolution. Additionally, the route taken by a constellation is well-defined depending on its orbit, and the resulting covered area of the globe. These routes and coverage areas can also vary with the seasons. Furthermore, some measurements may or may not be available, depending on the sun’s position and the cloudy weather when the satellite passes over the area.

Starting up with products of level 3 or higher

The raw data thus produced, representing thousands of small squares of data covering the surface of the globe at close but different times, are then reprocessed to produce the satellite images we consult, such as Google maps, which are in fact assemblies of images to reconstruct a global view of the earth.

There are five levels of products sold by satellite operators.

We’ve started our development work with products of level 3 or higher.

Level	Description
0	Raw telemetry data; includes received signals without any correction
1	Data corrected for instrumental errors
1A	Radiometrically corrected data
1B	Georeferenced and calibrated data
2	Data derived from Level 1 with specific products
3A	Data synthesized on regular grids (mosaics); used for global or regional analyses
4	Modeled or assimilated data; combination of observational data and numerical models

Geojson and image annotation

We first used geojson data from farms we wanted to track. It turned out that reconciling geojson and satellite data was complex.

Reconciling GeoJSON data with satellite imagery presented challenges, particularly due to differences in projections and coordinate systems. GeoJSON typically uses the WGS 84 coordinate reference system (CRS) with geographic coordinates (latitude and longitude). Satellite imagery might use different projections (e.g., UTM, Mercator) or datums, leading to discrepancies.

As we didn’t have much time, we reverted to the classic image annotation that we had mastered.

AI in Aquaculture – Conclusion: model training

Training a model is also a real challenge. Imagine that, to cover a coastal region such as Brittany, several tens of thousands of 240×240 images are required. Approximately 1/10000th of these images will include an aquaculture farm. The model must therefore be adapted to this situation.

We are still fine-tuning the model and hope to produce other significant results soon.

For more insights and updates on our innovative projects, connect with us on LinkedIn:
Mikael Dautrey, Kilian Delorme

The AQUASCAN project led by Isitix and KAMAHU initially received part funding from the Brittany Region. KAMAHU received part funding from the European Space Agency BIC Nord France for a project using satellite imagery in her farm management software.

Is Machine Learning in aquaculture THE RIGHT CHOICE ?

KAMAHU — Thu, 19 Oct 2023 16:18:53 +0000

In today’s fast-paced and data-driven world, businesses are constantly seeking innovative ways to gain a competitive edge, make smarter decisions, and deliver exceptional customer experiences. One technology that is transforming industries across the globe is neural networks. Harnessing the power of artificial intelligence, neural networks are used for machine and deep learning, and have the ability to analyze vast amounts of data, identify complex patterns, and make accurate predictions, enabling businesses to unlock new opportunities and drive growth. To determine whether the use of machine learning, in aquaculture or whatever industry, is the right choice, you need to consider these 4 key points :

VOLUME : there are a lot of repetitive counting or analysis to be done

CONSISTENCY and REPRODUCIBILITY : the actual human process is boring, biased and error prone.

SHORTAGE OF SKILLED WORKERS : the process requires skills that few of your employees have or that cost too much.

DECISION SUPPORT : the process is easier when additional information is provided to assist the operator.

The development of neural networks is a specialized task that requires expertise and experience. Our KAMAHU team excels in designing and implementing neural network architectures tailored to your specific business needs. From traditional feedforward networks to advanced convolutional and recurrent networks, we have the knowledge and skills to build models that deliver superior performance and accuracy.