Research

DiAGRI supports interdisciplinary research at the intersection of plant science, computer science, and food innovation. Our infrastructure enables six core research themes, each contributing to the development of smart, sustainable controlled environment agriculture.
Research Highlights
  • CEA Optimisation Investigating genotype × environment interactions and abiotic stress responses to maximise crop yield and quality under controlled conditions.
  • AI-Driven Phenotyping Deploying multi-modal imaging (3D scanning, hyperspectral, thermal, fluorescence) with edge AI for automated, real-time plant trait analysis.
  • Digital Twins Building virtual models of crop production systems that integrate real-time sensor data with AI predictions, enabling in-silico experimentation and optimisation.
  • Urban Farming Innovation Developing scalable business models and decentralised food systems for sustainable urban agriculture in collaboration with industry partners.
Theme 1: Plant Growth and Development

Understanding how plants respond to controlled environments is fundamental to CEA optimisation. DiAGRI researchers study genotype × environment (GxE) interactions, abiotic stress responses (temperature, light, drought), and yield optimisation across a range of crop species. The precision control of our growth chambers enables factorial experiments that isolate specific environmental variables.

Theme 2: Crop Breeding for CEA

Developing plant varieties specifically optimised for controlled environments — with traits such as compact architecture, efficient light use, rapid growth cycles, and enhanced nutritional profiles. DiAGRI leverages genome editing technologies (e.g., CRISPR) to accelerate the development of CEA-adapted cultivars, with strawberry as a primary model crop.

Theme 3: Smart Sensing and Automation

Integrating IoT sensor networks with intelligent automation to create responsive growing environments. Research focuses on developing closed-loop control systems where environmental parameters (temperature, humidity, light spectrum, CO₂, nutrients) are dynamically adjusted based on real-time plant status data from imaging and sensor feedback.

Theme 4: AI and Multimodal Data Fusion

Developing AI methods that combine data from multiple sensing modalities — 3D geometry, hyperspectral reflectance, thermal signatures, fluorescence, and environmental sensors — into unified models for plant phenotyping, growth prediction, and stress detection. Research explores CLIP-based multi-modal alignment, edge AI deployment, and predictive analytics.

Theme 5: Digital Twins

Building virtual replicas of physical growth environments that integrate real-time sensor data with AI-driven predictive models. Digital twins enable in-silico experimentation — testing hypothetical growing conditions, optimising resource allocation, and accelerating experimental design without occupying physical infrastructure.

Theme 6: Food Science and Urban Farming Innovation

Investigating the food science dimensions of CEA — including nutritional quality, sensory attributes, and post-harvest handling of controlled-environment crops. Also exploring scalable business models, decentralised food systems, and food design approaches for urban food production in collaboration with the Viikki Food Design Factory.

AI and Edge Computing

DiAGRI deploys artificial intelligence at the edge — processing imaging and sensor data directly within the growth chamber facility for real-time insights and automated control. Our AI research spans multi-modal data fusion, predictive analytics, and embedded model deployment.

Digital Twins

Digital twins are virtual replicas of physical systems, continuously updated with real-time data. In DiAGRI, we develop digital twins of our growth chamber environments — enabling researchers and growers to simulate, predict, and optimise crop production without the constraints of physical experimentation.