New funding for interdisciplinary research

Quantum computing promises a new computational paradigm with the potential to solve certain information-processing tasks beyond the reach of conventional computers, with impact on materials science, drug discovery, and secure communication. However, to realize this advantage, quantum processors must be operated in a regime where their behavior can no longer be efficiently tested or simulated on conventional computers. This creates a fundamental challenge: how can we trust and improve devices that we cannot fully verify? This project tackles this challenge by creating a tight synergy between data-science-driven learning theory and quantum information experiments to learn, certify, and control quantum dynamics directly from measurement data. By tightly integrating theory, algorithms, and experiments, we aim to uncover the limits of reliable quantum computation and translate these insights into practical methods that accelerate the development of trustworthy quantum technologies.

Associate Professor Albert H. Werner, Department of Mathematical Sciences, University of Copenhagen and Associate Professor Morten Kjaergaard, Niels Bohr Institute, University of Copenhagen

DKK 14 million.

Cyber attackers are no longer a single “type”: intrusions may be driven by automated malware, human adversaries, or emerging AI agents; still most cyber-security methods still treat them alike. PSYFIND will build personalised cyber defense by combining cyber-deception engineering with personality psychology to infer attacker type from interaction traces and adapt deception in real time. We will learn “psychological fingerprints” from behavior in deceptive environments using both large-scale honeypot deployments and controlled, ethically run ground-truth sessions. We will experimentally validate psychological mechanisms that reliably degrade human attacker performance and translate them into deployable, attacker-specific deception modules. PSYFIND delivers an integrated attacker-typing framework, open evaluation protocols, reusable software, and a curated benchmark dataset for next-generation security research.

Associate Professor Emmanouil Vasilomanolakis, DTU Compute, Technical University of Denmark and Professor Ingo Zettler, Department of Psychology, University of Copenhagen

DKK 4.5 million.

Satellite networks are the only technology capable of providing global connectivity but face severe scalability issues as the number of users increases and are still vulnerable to unexpected and targeted disruptions. Despite these critical challenges, existing works have focused on maximizing the performance and efficiency of the satellite network operation in a centralized manner, with a reduced number of users and under ideal operating conditions, leading to vulnerable satellite networks with a single point of failure on ground and no mechanisms to recover from critical failures. Hence, we aim to develop a flexible, decentralized, and data-driven framework for resilient and scalable satellite networks. Our methods will provide provable uncertainty guarantees for the predictions of AI algorithms on satellite network graphs using a conformal prediction approach to achieve the continuous network operation in strategic areas such as Greenland, even in catastrophic scenarios.Satellite networks are the only technology capable of providing global connectivity but face severe scalability issues as the number of users increases and are still vulnerable to unexpected and targeted disruptions. Despite these critical challenges, existing works have focused on maximizing the performance and efficiency of the satellite network operation in a centralized manner, with a reduced number of users and under ideal operating conditions, leading to vulnerable satellite networks with a single point of failure on ground and no mechanisms to recover from critical failures. Hence, we aim to develop a flexible, decentralized, and data-driven framework for resilient and scalable satellite networks. Our methods will provide provable uncertainty guarantees for the predictions of AI algorithms on satellite network graphs using a conformal prediction approach to achieve the continuous network operation in strategic areas such as Greenland, even in catastrophic scenarios.

Associate Professor Christophe Biscio, Department of Mathematical Sciences, Aalborg University and Associate Professor Israel Leyva-Mayorga, Department of Electronic Systems, Aalborg University

DKK 4,5 million.

1.5 mio. EVs and 35 GW solar power in the DK grid by 2035 will challenge grid stability and increase blackout hours by up to 100 times. This challenge cannot be solved with the current technology: better and larger power system models are needed for real-time control, but current data science methods are too slow. DLPower remedies these challenges. DLPower will develop physics-informed AI models to learn both from real data and physics, ensuring realistic grid stability predictions. Novel methods for training and inference of AI model directly on compressed data without decompression are developed, speeding calculations dramatically to support real-time control. The resulting system processes massive data, analyzes grid conditions in real-time and instantly controls PV panels + EV chargers to prevent grid failures before they happen, revolutionizing management of renewable and EV charger dominated power grids, as well as general-purpose AI on massive data. 

Professor Torben Bach Pedersen, Department of Computer Science, Aalborg University and Professor Remus Teodorescu, AAU Energy, Aalborg University

DKK 4.5 million.

The project develops a novel approach to physics-informed machine learning to build a framework for automized data acquisition and selection of maximally informative parameter sweeps in quantum electronics. This allows us to leverage recent developments in the project group of integrated cryogenic circuits capable of massive upscaling experimental quantum electronics. Together, this enables us to perform the first systematic experimental investigation of the role of length-scales for the phase diagram of quantum circuits and materials based on nanoscale superconducting geometries. Such experiments have previously been unfeasible due to hardware limitations and methods for dealing with the massive parameter space and data volumes. The synergy of data science methods and experimental quantum physics is essential, and a successful outcome would constitute a very significant contribution to both fundamental quantum physics and machine learning methodologies.

Associate Professor Oswin Krause, Department of Computer Science, University of Copenhagen and Professor Thomas Jespersen, DTU Energy, Technical University of Denmark

DKK 4.5 million.

Crystallization is a key process in the chemical, pharmaceutical, and food industries. To meet future needs — including in relation to developing new materials — it is important to be able to steer crystal formation toward desired properties. This is difficult because crystallization is hard to predict and manage. This project focuses on membrane crystallization (MCr), an advanced technique. Achieving desired crystal properties depends on appropriate operation design; yet, current practices still rely largely on repeated trial-and-error experiments, which is costly and leads to undesirable outcomes. We will develop a first-of-its-kind machine learning-based framework: learning dynamic characteristics of MCr and generating time-adaptive operation designs to produce targeted crystals. The project will enable the transition to generalizable and resource-efficient crystal manufacturing.

Associate Professor Tianyi Li, Department of Computer Science, Aalborg University and Associate Professor Cejna Anna Quist-Jensen, Department of Chemistry and Bioscience, Aalborg University

DKK 4.5 million.

The rapidly increasing energy density in AI industries is pushing for a major paradigm shift in cooling solutions from traditional air cooling to direct-to-chip liquid cooling. Two-phase immersion cooling (IMC) can capture all the waste heat efficiently with a supreme heat transfer coefficient. However, the phase change process is associated with stochastic dynamics of microscale bubbles and a critical point for maximal heat flux. SmartCool is aiming for controllable and predictable operations of IMC processes by establishing a framework connecting fundamental multiphysics models, advanced microfabrication of boiling surfaces, and stochastic greybox modeling. The greybox models will improve our understanding of physical mechanisms of microscale heat transfer, at the same time, a squeeze-shift-adapt principle will be established for robust industrial implementation of IMC processes. The outcome of the project will pave the way for a broad spectrum of two-phase cooling solutions.  

Professor Henrik Madsen, DTU Compute, Technical University of Denmark and Professor Jesper Hattel, DTU Construct, Technical University of Denmark.

DKK 4.5 million.

The WRITE-MODE project will develop much-needed robust knowledge about students’ writing development in Grades 4-6, under-researched due to challenges in tracking and quantifying progress over time. We will integrate expert educational knowledge and advanced data science to capture how linguistic features – ranging from grammar to coherence and voice – emerge and evolve in student texts. As part of this, we will develop new probabilistic and uncertainty-aware models and extend the statistical Rasch framework to account for uncertainty, temporal dynamics, and writing context, pushing beyond limitations of current methods. The project unites school writing research, educational linguistics, probabilistic modelling, and uncertainty quantification, and hereby we aim to create a strong interdisciplinary synergy capable of providing new evidence-based insights and advancing student writing research and robust and reliable machine learning.

Associate Professor Michael Riis Andersen, DTU Compute, Technical University of Denmark and Associate Professor Kristine Kabel, The Danish School of Education (DPU), Aarhus University

DKK 4.5 million.

Preparing society for climate change requires much better tools for understanding extreme rainfall than today’s methods, which cannot fully use the rapidly growing mix of historical gauges, modern weather stations, and private sensor networks. We aim here to establish a new interdisciplinary research direction that positions Denmark at the forefront of next‑generation climate services. By merging advanced statistical modelling with hydrology and atmospheric science, we aim to create a scalable framework that can inform both national and international planning. We will (1) integrate heterogeneous data in a consistent way, (2) capture changing storm behavior, (3) connect large‑scale weather patterns to local extremes, (4) distinguish physical processes from hidden spatial effects, and (5) extend the framework across Northern Europe. The complementary strengths of the two PIs provide a strong foundation for building a long‑term research platform and strengthening future climate services.

Associate Professor Anders Stockmarr, DTU Compute, Technical University of Denmark and Professor Peter Steen Mikkelsen, DTU Sustain, Technical University of Denmark.

DKK 4.4 million.

Greenland holds major potential for critical minerals vital to modern industry, European security, and the green transition. Exploration, however, is difficult because key information is vast, fragmented, and often locked in decades-old handwritten reports, maps, and field photographs. Sustainable development requires smarter, data-driven methods to balance economic growth, environmental protection, and benefits to Greenlandic communities, while avoiding inefficient, brute-force prospecting. This project combines geological expertise at GEUS with advanced artificial intelligence at the University of Copenhagen to develop new mineral-targeting tools. We will digitize and structure historical materials, align legacy maps and images with modern geospatial data, and train AI models to identify patterns linked to mineralization. The synergy between the PIs, who have geological domain leadership and multimodal AI expertise, ensures both scientific depth and practical impact of this project.

Associate Professor Bulat Ibragimov, Department of Computer Science (DIKU), University of Copenhagen and Senior Researcher Pierpaolo Guarnieri, Department of Mapping and Mineral Resources, GEUS

DKK 4.4 million.

Accurate ocean-wave data are essential for weather forecasting, climate research, and safe, fuel-efficient shipping, yet conventional wave buoys provide sparse coverage. In principal, this project transforms the global merchant fleet into a distributed wave-observing system using ship motion measurements (MRU data) already collected onboard. Moving beyond single-vessel studies, we analyse MRU data from about 150 container ships in worldwide service and treat wave estimation as a fleet-scale inference problem. By combining hydrodynamic transfer functions with physics-informed neural networks, transfer learning, and uncertainty quantification, the framework embeds physical constraints while leveraging large-scale data. Aggregating diverse vessel responses reduces bias and uncertainty without new hardware. The project establishes scalable, self-validating wave estimation with impact on maritime safety, operational efficiency, and improved ocean observations for weather and climate models.

Associate Professor Allan Engsig-Karup, DTU Compute, Technical University of Denmark and Associate Professor Ulrik Dam Nielsen, DTU Construct, Technical University of Denmark

DKK 4.4 million. 

To make solar energy more practical for everyday life, we need to move beyond large solar farms and also start powering indoor electronics, reducing our reliance on disposable batteries. New materials like antimony sulfide show great promise for capturing indoor light, but they are currently difficult to perfect because even tiny mistakes during manufacturing can ruin their performance. Instead of optimizing the design by old-fashioned trial and error, this project uses a smart "closed-loop" system that combines hands-on lab work at DTU Electro with advanced AI from DTU Compute. By letting the AI learn from every experiment and suggest the best next steps, we can quickly discover how to build high-efficiency solar cells for indoor use and beyond.

Associate Professor Mikkel Schmidt, DTU Compute, Technical University of Denmark and Senior Researcher Stela Canulescu, DTU Electro, Technical University of Denmark

DKK 4 million.