The AGRI-SATT programme grows food in the desert using seawater, satellite data, and wind energy. It combines high-resolution satellite imagery with real-time data from algae ponds to turn barren coastal land into productive farms for protein and Omega-3-rich feed. This matters because conventional aquaculture feed—fishmeal and soy protein concentrate—is environmentally costly and often unsustainably sourced. The programme addresses a gap in scalable, low-impact food production by exploiting natural seawater and deep-ocean nutrients, while deacidifying 99.98% of the water it uses. This benefits local marine ecosystems and boosts carbon sequestration. If successful, the approach could transform global supply chains for fish and livestock feed, making them cheaper and more sustainable. UK food producers would gain access to large volumes of critical feed ingredients, increasing their competitiveness. The cloud-based AI and IoT-controlled pond systems are designed to be globally applicable, not just to algae farming but to any agricultural system aiming to increase net primary productivity. The project is applied and commercially focused, with a patented, scaled growth methodology already tested.
View original technical description
The AGRI-SATT programme combines newly available, high-resolution spatial and temporal satellite data with key environmental and algal productivity data to create an effective, scalable, protein and food production method on desert land. The objective of this growth methodology is to produce food and aquaculture feed with widely available natural nutrients, in locations where nothing grew before. By extracting CO2 from seawater and underutilized nutrients from the deep ocean, this highly sustainable project 'deacidifies' enormous quantities of seawater, returning 99.98% of the seawater used during the process. This is very beneficial to the local ecosystem and aids coastal primary producers to sequester more carbon from the environment further amplifying the benefits of this growth methodology. What distinguishes the AGRI-SATT programme is that it exploits abundantly available natural seawater to produce food in non-arable deserts using wind-energy. The tested, scaled and patented growth methodology will be applied globally. With ground-based operational data, production operations will be forecast and automatically adjusted to dramatically increase the impact of this highly sustainable food production method. The AGRI-SATT programme, for the first time, combines daily, high-resolution, hyperspectral satellite data with detailed in-pond photo-physiological data to determine the quality and productivity of natural algae for the production of high value food and feed ingredients. Marine microalgae create the plant-based Omega-3 fatty acids, protein, and even the colour and taste of seafood that accumulate in high-value mollusks, crustaceans and fish or alternatively could be used for vegetarian food. Combining these data in an AI-enabled computational 'Digital Twin', automates and increases production and the nutritional quality (protein, pigments) of food. Furthermore, with IoT-enabled, SCADA-controlled pond machinery, sustainable food and feed production will be maximised. By controlling the production ponds with IoT-informed operational equipment and 'weather-responsive nutrient supply', this growth methodology recreates the ideal growth conditions for microalgae. Also, reproducing ideal growth conditions year-round means our highly sustainable and scalable production method is cost-competitive with less sustainable commodities like fishmeal or soy protein concentrate. UK PLC benefits directly by receiving large volumes of critical feed as well as highly valuable organic food. This sustainable food fundamentally and significantly increases the competitiveness of UK food production. The data integration software is applicable globally to all agricultural schemes that aim to increase Net Primary Productivity. The cloud-based AI applies to any agricultural production system.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know