Projects

Functional foods for gastrointestinal health represent a rapidly evolving field in food and health sciences.The aim of this project is to develop novel health-promoting food solutions using postbiotics, i.e. bioactive compounds produced by bacteria. Unlike probiotics, postbiotics do not contain live microorganisms, making them safer and easier to use in food processing. The project focuses on a Ligilactobacillus salivarius strain that has demonstrated anti-inflammatory effects, the ability to inhibit epithelial-mesenchymal transition in gastric epithelial cells and to reduce cancer cell self-renewal in live bacterial cultures and in cell-free supernatants. The project will identify the compounds responsible for these effects and evaluate their stability during food processing and their impact on product shelf life. The results will be validated in food matrices and production processes, including fermentation. The project will lead to the development of new functional food solutions.

Estonian aquaculture faces hidden biological losses that reduce production predictability and added value. Early decisions on stock origin and feed are made under uncertainty, while consequences emerge only later under fast growth or stress. The heart is a key mechanistic bottleneck: cardiac abnormalities are common in farmed salmonids, and reduced cardiac reserve may remain silent until fish encounter warming, hypoxia, or handling. This project determines how genotype, feed, and age shape cardiac development and robustness in farmed rainbow trout, identifies early warning signs of hidden vulnerability, and develops the Trout Robustness Assessment Protocol (TRAP) — a standardised, farm-linked decision-support tool. Controlled genotype-by-feed experiments combined with farm cohort validation connect cardiac physiology to real production outcomes. The project builds applied competence, trains doctoral researchers, and targets uptake in Estonian and Nordic trout farming.

In this project, TalTech, NICBP, Estonian Academy of Security Sciences, together with Neo Performance Materials Silmet and TSR Innovation and will address three challenges set by the companies. First, the development of more sustainable mechanochemical technologies for the production of rare earth element compounds from secondary resources, such as REE oxides, carbonates, or chlorides. Second, the development of mechanochemically enhanced solid–liquid and liquid–liquid extraction and separation processes using supramolecular chemistry, including extraction process modelling. Third, the assessment of technological risks and the development of emergency response protocols for chemical rescue units in order to reduce the risk of accidents and improve safety in the rare earth element processing chemical industry. As a result, best performing chemical technologies can be applyed by industry, helping to increase the impact potential of Estonia’s chemical industry in Europe and worldwide.

Companies in the food and health sector continually launch novel, healthier, and more affordable products, driven by consumer demand. This innovation often relies on engineering microbial cells (e.g., bacteria or yeast) that either produce these compounds directly or accelerate key steps in production. The microbial products market is expected to reach $346.3 billion by 2027. High‑throughput screening (HTS) remains a major bottleneck in microbial strain development: current workflows are manual, poorly automated, and lack scalable, data‑rich environments. Existing tools cannot keep pace with rapidly expanding metabolic libraries containing millions of variants, slowing progress from research to industrial deployment. DropletFactory addresses this by developing droplet‑based HTS platforms available via service (CORE) or licensing (MOBILE), enabling local and international companies to innovate faster and bring new food and health products to market.

Although several solutions have been developed for the processing of cereal byproducts, these have generally not been applied in food production. By-products are nutrient dense and food-grade products, hence, composting, burning, or using them as animal feed is not economically viable. Biotechnological processing, including hydrolysis technologies, enable to produce alternatives to bread and dairy products from bran. Rye consumption has been steadily decreasing in Estonia. The goal is to bring this high-bioactive food back into daily diets. We will develop a technology that can be implemented in development of various food products in different companies. We plan to demonstrate that modern hydrolysis technologies can be used to create fiber-rich and tasty products, thereby solving a fundamental dietary problem —the lack of dietary fibre in the diet, which is the root cause of most chronic diseases.

The project aims to develop a bio-based UV protection material from lignin for use in polyurethane construction foams and as a UV filter in cosmetic products such as sunscreens. UV radiation degrades foam surfaces, reducing insulation and sealing performance, while the cosmetics industry seeks safer, more sustainable UV filters. The research focuses on chemical modification of lignin, a by-product of the wood and peat industries, to create an effective UV-absorbing additive or coating. Its performance in construction materials and cosmetic formulations, including durability and safety, will be evaluated. The expected result is a sustainable UV additive that extends product lifetime, reduces reliance on synthetic stabilizers, and increases the value of local bioresources, supporting circular economy and greener production.

The ReDESign project focuses on the production of high-purity lignin and on developing a technology for recovering the green solvent needed for this process. Lignin is generated in large amounts as a by-product of the pulp industry, but it is mostly used as a low-value fuel. At the same time, purified lignin could serve as a raw material for higher value products such as composite materials, carbon materials, and other advanced bio-based products. The aim of the project is to develop a method that enables efficient regeneration and recycling of the deep eutectic solvent (DES) used in lignin purification. The expected results include a workable solvent reuse concept, improved understanding of the process chemistry, and a basis for creating an industrially applicable technology. In Estonia, this can support smarter use of biomass, promote the circular economy, and create new opportunities for developing high-value materials and technologies.

The central problem of the research topic is that there is no comprehensive methodology and technological systemic approach that would allow companies to assess the feasibility of digitalization and robotization of production systems before making investments and to propose needs-based solutions for automated workplaces, taking into account the actual functioning of production processes and the impact of various technological solutions on the entire production system. The aim of the research topic is to develop and validate an artificial intelligence-based decision support system and methodological framework that allows industrial companies to analyze production processes, model a virtual factory, create a digital twin of it, and assess the performance, profitability, and implementation capability of various automation solutions (including robotized workplaces, digital devices, and integrated work operations) in the company's production system before making physical investments.

AIM-Labs addresses educational gap by creating a new generation of AI-Driven Smart Manufacturing Learning Labs that blend data, simulation, and extended reality (XR). The project introduces AI SPRINTS—structured, challenge-based learning pathways in which students collaboratively design, prototype, and evaluate AI-enabled solutions for realistic manufacturing scenarios. These sprints integrate multiple technological layers, from data preparation and machine learning to discrete-event simulation, optimisation, digital twins, and XR-based interaction. The project is driven by the conviction that engineering students learn best when they can manipulate real or realistic data, test alternatives in simulation, and visualise system behaviour through immersive and interactive environments. By embedding AI SPRINTS into higher-education curricula, AIM-Labs will empower learners to develop the competencies required in the emerging AI-enhanced manufacturing workplace: data literacy, model development and validation, human-in-the-loop decision-making, explain-ability awareness, and the ability to evaluate trade-offs in complex production systems. The project aims to: - Deliver and validate AI-driven learning SPRINTS in higher education programs in industrial and manufacturing engineering. - Establish AI SPRINT co-design labs where students apply and evaluate AI solutions in data analytics, simulation, and XR. - Foster collaborative, challenge-based learning through immersive workshops integrating AI, digital manufacturing, and XR technologies. - Enhance students’ problem-solving skills, practical competencies, and innovation readiness.

The overall aim of the Thematic R&D Programme project SPARK-CHIP is to strengthen the R&D capacity, training and cooperation in TalTech and TKK School of Applied Sciences and to foster business-oriented R&D collaboration with Electronics Industry Association and Metrosert Chip Centre in the field of AI chip design. The scientific scope of the project is defined in close cooperation with two innovative Estonian technology companies: Skeleton and Imaginal Microsystems that will monitor the progress of R&D within the project. The project aims at development of a novel platform for cost-effective parametrizable and reliable system-on-chip cores for AI accelerators, supporting emerging AI models and validating it in real silicon. The research builds on TalTech’s previous results in the area of reliable AI chips design and it contributes to advancing the Estonian ICT hardware ecosystem by gaining strategic knowledge on AI deployment on hardware as well as on chip design and production.

Mental health disorders are widespread, and their impact on individual functioning, work ability, and the healthcare system is substantial. At present, the effects of interventions delivered as part of mental health support or treatment are assessed mainly through clinical interviews and self-reports, usually during infrequent visits. The project adds a regular data-driven measurement layer to this process and develops an interpretable individualized model and a standardized workflow to help detect clinically meaningful changes earlier, more consistently, and more objectively. In this way, the project lays the foundation for a new data-driven service layer in occupational health and mental health services, as well as for the further development of well-being digital solutions based on neurophysiological input.

Kidney failure and the need for dialysis are rising, increasing pressure on healthcare systems and expectations for treatment quality. This project addresses a critical gap by developing an optical sensor for real-time assessment of dialysis quality, enabling continuous monitoring of under-monitored uremic toxin removal. Moving beyond single-point measurements, the approach supports data-driven and patient-centred treatment optimization. The project combines technology development with clinical validation and practical implementation, involving a leading industrial partner, a clinical centre, a professional network, and a university of applied sciences. This ensures both relevance and a clear pathway to real-world use. The expected outcome is a clinically validated sensor prototype with strong potential for further development into a market-ready solution, contributing to improved treatment outcomes, innovation in health technologies, and academic workforce development.

The present project aims to develop novel and enhance existing methods of explainable artificial intelligence for the analysis of human motor functions. Pilot studies have demonstrated promising results to support the diagnosis of neurodegenerative diseases. In addition, we plan to extend the area of application from medicine to cognitive development and cognitive fatigue analysis. The integration of the explainer component will provide medical professionals with the necessary transparency of the decisions made by AI. Application in the area of cognitive development to support the school education process. Cognitive fatigue is known to cause severe injuries and serious financial losses. In-depth understanding of this phenomenon and ability to recognise mental fatigue targets to make the work environment safer and reduce monetary and non-monetary losses in the process of work.

In traditional food systems, additives derived from petrochemicals and animal products are widely used. While these compounds may possess desired techno-functional properties, they come with environmental, ethical, health, and sustainability issues. The goal of this project is to develop alternative protein-based food additives, such as colorants and sweeteners, that meet the needs of the food industry while addressing the concerns. Rational design, structural biology, and AI methods are utilized for protein development. In collaboration with TFTAK, a precision fermentation platform is developed to produce proteins in microorganisms. Protein samples are tested in model foods. Successful prototypes are commercialized through partnerships with the local food industry and startup accelerators. The gathered experimental data is used to model relationships between protein structure and techno-functional properties, facilitating the design of novel food proteins in the future.