The award will support a collaboration between Food System Innovations’ sensory program, NECTAR, and computer scientists at Stanford University to develop an open-source AI model that accelerates the global shift…

The award will support a collaboration between Food System Innovations’ sensory program, NECTAR, and computer scientists at Stanford University to develop an open-source AI model that accelerates the global shift to sustainable proteins

Food System Innovations, a philanthropic impact platform investing in a more humane and sustainable future of food, has been awarded $2 million from the Bezos Earth Fund’s AI for Climate and Nature Grand Challenge. Food System Innovations (FSI) is among fifteen global teams chosen to scale artificial intelligence solutions that address the world’s most pressing environmental challenges – from biodiversity loss and to climate change.

Livestock farming is responsible for ~18 per cent of global greenhouse gas emissions, ~27 per cent of global freshwater use, and ~41 per cent of tropical deforestation. Sustainable proteins are one of the most impactful carbon mitigation interventions in food (second only to reforestation) and have the highest CO2e savings per dollar than any other decarbonization lever across all sectors. Improving the quality, taste, and cost of sustainable proteins is therefore an urgent and critical climate and biodiversity imperative.

FSI’s mission is to accelerate this necessary transition by uniting science, markets, and society to create better food choices for everyone. FSI advances this mission through a diversity of programs, including NECTAR, which has built the world’s largest publicly available database on the sensory performance of plant-based meats and balanced protein products.

“Taste is the gateway to consumer adoption. NECTAR’s data helps the sustainable protein industry refine formulations and enhance flavour, making climate-friendly foods truly irresistible,” said Caroline Cotto, Director of NECTAR and co-Principal Investigator of the grant. “Partnering with the Bezos Earth Fund allows us to translate AI innovation into real-world climate and conservation impact, one bite at a time.”

The team is developing algorithms that predict sensory attributes and optimise ingredient formulations for sustainable proteins. Using a combination of NECTAR’s sensory data and molecular flavour databases, the team will build an AI model that connects molecular structure, flavour, texture, and consumer preference, accelerating sustainable protein product development and, ultimately, market penetration.

“I’m excited to partner with NECTAR, the Bezos Earth Fund, and other incredible collaborators on developing AI tools for sustainable protein design, a critical step for human and planetary health,” shared Anna Thomas, the project’s Technical Lead and co-Principal Investigator, and a computer science PhD candidate at Stanford. “Our early research shows that large language models can help revise formulations based on sensory feedback. With this grant, we can deliver actionable insights that improve taste and speed the protein transition.”