algaeScan

Algae scan tracks and predicts algae blooms to reduce fish mortalities and increase the reliability of profits for salmon fisheries. Algae blooms affect coastal and ocean ecosystems and cost Europe an estimated €850 million/year in ecosystem damage affecting tourism and the seafood industry. Specifically algae blooms cost €177 million/year to fisheries directly.

Specifically, Algae scan uses a customized satellite index using Copernicus Sentinel-2 L2A data to track algae blooms in areas surrounding offshore fisheries using open source API points of registered fisheries. Our product is a software as a service (SaaS) that conveys algae bloom risk and algae bloom concentration in an easily accessible dashboard. We aim to develop a product that can:

• detect algae blooms before the visible detection from the human eye.
• warn fisheries during algae bloom events to prevent catastrophic fish mortality and profit revenue loss. This is done through a prediction model of the likelihood of algae bloom events.
• Improve offshore fishery locations to have reduced risk from algae blooms.

We address challenge #2: tracking and preventing pollution. This product aims to track and prevent the occurrence of algae blooms and their impacts on offshore fisheries.

To achieve this, AlgaeScan combines two complementary data sources into a single hybrid detection system. The first layer is Copernicus Sentinel-2 L2A satellite imagery, which provides 10-metre resolution surface mapping of chlorophyll-a concentration, turbidity, where the correlation between them can asess if there is algae bloomin in a specific area where the fisheries are. The second layer is in-situ IoT sensor, that measure dissolved oxygen, pH, water temperature at depth. By fusing satellite surface signals with real-time subsurface sensor data, AlgaeScan detects bloom precursors that neither source could identify alone, extending the early warning before a bloom becomes visible or causes fish mortality.

The platform delivers bloom scores through an accessible web dashboard, with automated alerts sent directly to farm managers when risk thresholds are exceeded. The dashboard consists of a map with all fish farms based on an API. 

AlgaeScan is built entirely on free and open European space infrastructure. Sentinel-2 and Sentinel-3 data are accessed through the Copernicus Data Space Ecosystem. Galileo GNSS positioning underpins the precise geolocation of registered farm sites and SmartOcean buoy tracking. This means the core data input costs nothing, AlgaeScan's value lies in the intelligence layer built on top of it.

Norwegian salmon farms are legally required to report water quality and environmental impact under ESRS E2 and E3 standards, which entered into force in Norwegian law in November 2024. AlgaeScan automatically generates compliance-ready environmental documentation from satellite and sensor data, reducing the administrative burden on farm operators while providing regulators and retailers with independent, tamper-proof verification of water conditions.

Team Members:

Marsel Safin – Team Lead, Product Lead, CEO

Erza Malici - IT & Informationssystem & COO

Olivier Herlin - International Ecosystem Advisor, Relations Lead & CFO

Feodor Svetlanov Konomaev - Phd Physicist, Research & Data Analyst

Business viability:

Capturing just 1-3% of the market will provide a viable revenue for the business, since in Norway alone has a 140 billion NOK in revenue and we have the potential to reduce the loss of fisheries with a market estimate of 177million euros annually in Europe. 

Costs of Saas is estimated around 72k Euros to maintain provide software access to customers. This is a low cost for fisheries with high profit rewards for fisheries.

Estimated profit in three years if we get 30 customers. We have the potential to scale to other countries and water bodies specifically to expand our services to Chile.

Source for customised indices:

• https://custom-scripts.sentinel-hub.com/custom-scripts/sentinel-2/ulyssys_water_quality_viewer/
• Sachidananda Mishra and Deepak R. Mishra, Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters, Remote Sensing of Environment 117, 394-406 (2012), doi.org/10.1016/j.rse.2011.10.016
  
  Github repo: https://github.com/marcelsafin/algaeScan