STARGATE · Project

Sensor and Data Tools to Grow Better Crops and Safer Food

foodIdeaTRL 2Thin data (2/5)

Imagine you could scan a plant the way a doctor scans a patient — checking its health, nutrition, and stress levels without cutting it open. That's what STARGATE built capacity for: using sensors, genetic analysis, and machine learning to understand exactly what makes crops perform best. The goal is to pick the right plant varieties that need fewer pesticides, last longer on shelves, and deliver more nutrition. A Portuguese university teamed up with leading research labs in Germany, France, and the Netherlands to learn and deploy these techniques.

By the numbers

consortium partners across 4 countries

research pillars at UCP (Environment & Resources, Food & Nutrition, Biobased & Biomedical Products)

total project deliverables produced

demo deliverables including open dataset and information system

The business problem

What needed solving

Food and agriculture companies face a costly guessing game when selecting crop varieties — choosing plants that resist disease, need fewer chemicals, deliver better nutrition, and last longer on store shelves. Traditional breeding and quality control methods are slow, expensive, and often miss the molecular-level traits that determine real-world performance.

The solution

What was built

The project produced 16 deliverables including an open dataset for agri-food sensor research and an information system deployed at CBQF (UCP's research center). The core output is institutional capacity: trained researchers and established methods for sensor-based phenotyping, metabolomics analysis, and machine learning-driven crop quality prediction.

Audience

Who needs this

Seed companies looking to accelerate crop variety selection using sensor dataFood processors seeking to improve raw material quality and extend shelf-lifeAgTech startups building IoT sensor platforms for precision farmingAgricultural cooperatives wanting data-driven crop management adviceNutraceutical companies needing crops with specific nutritional profiles

Business applications

Who can put this to work

Seed & Crop Breeding

mid-size

Target: Seed companies and plant breeding firms looking to accelerate variety selection

If you are a seed company spending years on trial-and-error crop selection — this project built sensor-based phenotyping and data analysis capabilities that can screen plant traits faster. The consortium developed expertise in combining sensor data with machine learning to predict which crop varieties will perform best, potentially cutting breeding cycles. Their open dataset and deployed information system at CBQF offer a starting point for collaborative R&D.

Fresh Produce & Food Processing

any

Target: Food producers and processors focused on shelf-life extension and nutritional quality

If you are a food company struggling with product spoilage and inconsistent raw material quality — this project developed multi-omics and sensor approaches to select crops that naturally last longer and deliver higher nutritional value. The consortium of 4 partners across 4 countries built predictive models for crop quality scenarios. Their work on reducing losses and improving shelf-life through better raw material selection addresses a core cost driver in food processing.

Precision Agriculture Technology

SME

Target: AgTech companies developing IoT sensor platforms for farming

If you are an AgTech company building sensor solutions for farmers — this project created an information system integrating phenotyping data, metabolomics, and IoT sensor inputs with machine learning models. The consortium combined expertise from 3 leading European research organizations (INRAE, IPK, Wageningen Research) to bridge the gap between raw sensor data and actionable crop management decisions. Their open dataset could serve as training data for your own agricultural AI tools.

Frequently asked

Quick answers

What would it cost to access STARGATE's tools or data?

STARGATE was a Coordination and Support Action (CSA) focused on building research capacity rather than developing commercial products. Their open dataset is publicly available. Access to the information system deployed at CBQF or collaborative R&D would need to be negotiated directly with Universidade Católica Portuguesa.

Can these sensor and data analysis methods work at industrial scale?

The project focused on building institutional expertise and deploying an information system at one research center (CBQF). Scaling to industrial agricultural operations would require further development and integration work. The predictive models and sensor methods were validated in a research context across 4 partner institutions.

What about intellectual property and licensing?

As a publicly funded CSA project, the open dataset is freely available. The information system and predictive models developed may be subject to institutional IP policies at UCP and the 3 research partners. Licensing terms would need to be discussed with the coordinator.

How mature is this technology for real-world farming use?

This was primarily a capacity-building project — training researchers and transferring knowledge from established labs (INRAE, IPK, Wageningen) to UCP. The deployed information system and open dataset are concrete outputs, but the focus was on research excellence rather than market-ready products. Based on available project data, practical farming deployment would require additional development phases.

Can these methods integrate with existing farm management systems?

The project built expertise in IoT sensors, phenotyping, and machine learning for agri-food applications. While the information system was deployed at CBQF, integration with commercial farm management platforms was not a stated objective. The sensor and data analysis methods could potentially feed into existing precision agriculture platforms with additional engineering work.

Is there regulatory alignment for food safety applications?

The project addressed crop resistance to stresses and nutritional quality improvement through better variety selection — areas that align with EU food safety and sustainability regulations. However, specific regulatory validation or certification was not part of this capacity-building project's scope.

Consortium

Who built it

The STARGATE consortium is entirely academic and research-driven: 1 university (UCP, Portugal) and 3 research organizations (INRAE in France, IPK in Germany, Wageningen Research in the Netherlands), with zero industrial partners and zero SMEs across 4 countries. This is a capacity-building project where established research leaders transferred sensor, phenotyping, and data analysis expertise to UCP. For a business looking to collaborate, you would be dealing exclusively with research institutions — which means strong scientific depth but no existing commercial pathway or industry validation. Any commercialization would require bringing in industry partners not currently in the consortium.

UNIVERSIDADE CATOLICA PORTUGUESACoordinator · PT
LEIBNIZ - INSTITUT FUER PFLANZENGENETIK UND KULTURPFLANZENFORSCHUNGparticipant · DE
INSTITUT NATIONAL DE RECHERCHE POUR L'AGRICULTURE, L'ALIMENTATION ET L'ENVIRONNEMENTparticipant · FR
STICHTING WAGENINGEN RESEARCHparticipant · NL

How to reach the team

Contact the coordinator at Universidade Católica Portuguesa (Portugal) through SciTransfer for a facilitated introduction.

Order a report on this consortium See UNIVERSIDADE CATOLICA PORTUGUESA profile →

Next steps

Talk to the team behind this work.

SciTransfer can help you evaluate whether STARGATE's sensor-based crop analysis methods and open dataset are relevant to your agri-food business challenge. We connect companies with the right research teams.

Order a report on this topic More in Food & Agriculture