Machine Learning-Assisted Design of Biopolymer-Based Hybrid Materials
Discovering optimal composition of bio-based compounds and process conditions to achieve specific properties is a complex, multifaceted problem that requires extensive domain knowledge and intuitive insights. It can be effectively addressed by combining experimental design, optimization techniques and machine learning. The project will be carried out in the Cellulose & Wood Materials Laboratory under supervision of Dr. Gustav Nyström and Dr. Mark Schubert at Empa Dübendorf and is aimed at exploring the material design space more effectively by leveraging advanced machine learning algorithms.
Master thesis: Designing a fishnet harvesting buoy to find and tag ghost nets at the ocean surface in a nature-driven way for ocean cleanup and marine plastic mining
Designing a fishnet harvesting buoy to find and tag ghost nets at the ocean surface in a nature-driven way for ocean cleanup and marine plastic mining
Living materials as an alternative to antibiotics to fight against pathogen infections.
Wound infections present a significant challenge in healthcare, and traditional treatments involving antibiotics can lead to the emergence of antibiotic-resistant bacteria. Probiotics (i.e. the "good bacteria") have been studied widely for their potential antimicrobial effects and use in wound treatment as an alternative to antibi-otics. They have been reported to enhance wound healing, produce antimicrobial substances, disrupt biofilm, and restore the microbial balance in wounds. In this project, we aim to combine the benefits of probiotics and hydrogels to form a so-called "living hydrogel": i.e. a hydrogel with organisms inside. The living hydrogel can not only fulfill the function of a normal wound patch but also deliver the therapeutic factors secreted by the encapsulated probiotics to fight against pathogen infection and also promote wound healing.
Machine Learning-Assisted Design of Biopolymer-Based Hybrid Materials
Discovering optimal composition of bio-based compounds and process conditions to achieve specific properties is a complex, multifaceted problem that requires extensive domain knowledge and intuitive insights. It can be effectively addressed by combining experimental design, optimization techniques and machine learning. The project will be carried out in the Cellulose & Wood Materials Laboratory under supervision of Dr. Gustav Nyström and Dr. Mark Schubert at Empa Dübendorf and is aimed at exploring the material design space more effectively by leveraging advanced machine learning algorithms.
Techno-economic assessment of community energy storage options for a residential district in St. Gallen
We offer an exciting master thesis opportunity at Urban Energy Systems Lab, Empa, in collaboration with a Living lab of Stadtwerke St. Gallen focused on flexibility management and grid optimization in a residential district in St.Gallen. The district is characterized by a mix of building stock with individual and institutional ownership, providing a unique context for exploring integrated energy solutions. This project aims to support the energy transformation of the area by developing and evaluating the potential of electricity storage options.
Raman Spectroscopy of Atomic Quantum Defects
Master's Project in Raman spectroscopy of atomic quantum defects. We are looking for a highly motivated candidate with an experimental background and interest in solid state physics, nanoscience and Raman spectroscopy who wants to pursue cutting-edge research at a world-class level.
High-Fidelity Modeling of Boreholes Thermal Energy Storage Systems for Effective Integration in District Heating and Cooling Networks
Integrating renewable energy sources with energy storage solutions is essential to advancing sustainable energy infrastructures. Borehole Thermal Energy Storage (BTES) is a cost-effective solution to address the seasonal mismatch between energy supply and demand, in which excess heat during summer is stored under the ground at a temperature below 30 °C to be reused in winter. At the Empa campus in Dübendorf, an innovative high-temperature (up to 50 °C) BTES system was constructed and ready to be operated. Storing energy at higher temperatures allows for the use of the accumulated heat for a larger number of applications, for example, to directly serve the district heating network of the Empa campus. However, using such temperature levels poses challenges in the correct design and operation of the system, especially in relation to other key components of the campus district heating and cooling networks, such as heat pumps and chillers. This results in highly nonlinear behaviors, which require detailed modeling to be anticipated. This project leverages existing object-oriented models in the Modelica language to develop high-fidelity models of the high-temperature borehole thermal energy storage system integrated into the district heating and cooling network of the Empa campus.
Machine Learning-Assisted Design of Biopolymer-Based Hybrid Materials
Discovering optimal composition of bio-based compounds and process conditions to achieve specific properties is a complex, multifaceted problem that requires extensive domain knowledge and intuitive insights. It can be effectively addressed by combining experimental design, optimization techniques and machine learning. The project will be carried out in the Cellulose & Wood Materials Laboratory at Empa Dübendorf and is aimed at exploring the material design space more effectively by leveraging advanced machine learning algorithms.
Optimal design of hydrogen systems integrated in small-scale districts
As Switzerland advances towards achieving the Swiss Energy Strategy 2050, decarbonization efforts are gaining momentum, especially for small-scale districts and energy communities. In this context, hydrogen technologies, alongside waste heat recovery, represent promising solutions to decarbonize and enhance the flexibility of energy systems. These technologies offer potential benefits in improving energy efficiency and reducing emissions, particularly when integrated into multi-energy networks that enable efficient energy sharing within prosumer communities. Optimizing the integration and operation of hydrogen systems, along with recovering waste heat, is crucial to maximizing both economic and ecological benefits. This project will investigate the optimal integration of hydrogen technologies and waste heat recovery in small-scale districts and energy communities, focusing on maximizing decarbonization while maintaining economic viability. One key outcome of the project is the identification of scenarios where these technologies offer the most significant benefits and explore how to best integrate them within energy-sharing communities.
Contextual Bayesian Optimization of Heating Curves
Buildings in Switzerland account for 42% of total energy use and 26% of CO2 emissions, with heating making up 68% of this consumption. Our semester thesis focuses on reducing heating energy while maintaining tenant comfort by optimizing heating curves using Contextual Bayesian Optimization. Heating curves define the relationship between outdoor temperature and heating power, and we adjust these parameters to minimize energy use while ensuring comfort. We optimize a 2-point linear heating curve, incorporating contextual information like temperature, and iteratively refine parameters through simulation. Our approach emphasizes simplicity and accessibility, but the complexity of adaptive systems can hinder transparency, which we address by developing an interactive interface. This interface visualizes comfort and energy trade-offs, highlights "safe" parameter regions, and allows users to adjust heating curves interactively. Our research explores the most effective heating curve parameterizations, enhancing system transparency and usability to promote broader adoption of energy-efficient heating solutions.
Flexibility Potential Quantification of Prosumers: How to integrate Users’ Behavior?
In recent years, the penetration of renewable energy resources in distribution grids has been steadily increasing, raising new issues such as voltage violations or line congestions. Due to their large thermal inertia, individual buildings can regulate their heating system to support distribution system operation. In our previous work, we proposed a quantification of the flexibility potential of an electric heating system, using the concept of energy flexibility envelopes, and accounting for the impact of various uncertainties: the weather forecast, the building thermal model inaccuracy, and the uncertain inhabitants’ behavior. However, we considered that uncertainties are independent of the requested flexibility. Yet, in practice, the inhabitants’ behavior is correlated to flexibility requests as optimal control strategies. For example, a request to shift the consumption may increase the room temperature, which in turn impacts the inhabitant behaviors, possibly reducing energy efficiency.
Finite Element Modeling (FEM) of thermoplastic elastomer based sensors and actuators for soft robotics
Soft robotics leverages compliant, elastomeric materials for enhanced interaction and adaptability in various applications. While silicone compounds are commonly used, their slow casting process hinders large-scale production. Thermoplastic elastomers (TPEs) offer a promising alternative due to their ease of fabrication through thermoplastic techniques, allowing for faster production scaling. However, TPEs are not yet widely adopted in soft robotics, with limited research available. Finite Element Method (FEM) analysis can play a crucial role in evaluating TPE properties, streamlining their application in sensing and actuation devices.
Categorization of the extreme events affecting demand side flexibility provision of smart energy system
Flexibility provision is crucial for Switzerland's electricity grid due to its high reliance on hydroelectric power. Switzerland intends to increase other renewable sources, which require balance with variable energy supply. Seasonal energy fluctuations and peak demand periods also necessitate adaptable consumption practices. Flexibility helps Switzerland in maintaining energy independence, integrating with the European electricity market, and supporting its decarbonization efforts. In this rapidly evolving landscape of smart energy systems, resilience has emerged as a critical area of study. In the context of this project, it highlights the importance of understanding how extreme social events can affect the demand side flexibility provision of smart energy systems. Such events may include natural disasters, widespread technological failures, or significant social unrest. Each of the above-mentioned events have the potential to destabilize energy consumption patterns and challenge the reliability of energy infrastructure. For instance, (i) during a heatwave, the effectiveness of demand response programs incentivizing consumers to reduce their electricity consumption might be lower due to increased reliance on air conditioning or, (ii) during a pandemic, changes in energy consumption patterns, such as increased residential use due to lockdowns, could alter the effectiveness of demand response programs.
Development of an ML-driven Mobile App for Quality and Species Analysis of Roundwood
Roundwood is sorted by quality and species in the forestry (and in sawmills). Based on the dataset with images of roundwood (from partner sawmill³) containing quality and species labels, a classification model has been developed for predicting the species and the quality of a stem based on the image of its cross-section. The detailed description of the model architecture and the results can be found in the paper: https://www.sciencedirect.com/science/article/pii/S0957417423036217. The task of the project is to develop an iOS or Android App that based on the model results.
Postdoc in Chirped Pulse Amplification Laser
The laboratory is looking for a postdoctoral candidate to carry out experimental research in non-linear optics lab. The research focuses on chirped pulse amplification (CPA) laser development and implementation for X-ray laser spectroscopy. We offer an excellent infrastructure in an in-terdisciplinary group. You will gain a large and diversified expertise in spectroscopy. The lab will encourage your scientific career with application to grants and submission of papers. The project is part of the EuPRAXIA consortium (https://www.eupraxia-project.eu/ )
PhD in X-ray Laser
X-ray Laser are huge machines attached to particle accelerators. Our group built a compact X-ray Laser that can be operated in the lab. In this PhD the existing setup is utilized for application in spectroscopy. Further you will work to further miniaturize X-ray lasers down to a chip.
Laser Ablation Spectroscopy
Focused laser destroy materials. Laser ablation permits to inspect the composition in a depth-resolved way. The ablation process produces X-rays that have a fingerprint of the target material.
Plasma Ion Trap Mass Spectroscopy
Ion Traps are used in chemistry as high resolution analyzers. Their hyphenation to a plasma source offer much more flexibility of ionization. This new platform needs to be investigated.
Innovative Urban Planning for Sustainable Development in Low- and Middle-Income Countries: An Agent-Based Modeling Approach
Urban development in low- and middle-income countries (LMICs) presents unique challenges and opportunities in the global effort to reduce greenhouse gas emissions and energy demand. While much focus is placed on renewable energy technologies and efficiency solutions in the global transition to sustainability, significant gains can also be made through intelligent urban design. One promising concept is the "15-minute city," where residents can meet most of their needs within a 15-minute walk or bike ride from their homes. This approach contrasts sharply with conventional urban development strategies, which often result in sprawling cities with high reliance on automobile transportation. This project aims to explore how innovative urban planning strategies like the 15-minute city can contribute to emissions reduction and energy demand mitigation in an LMIC case study area. By developing an agent-based model (ABM), the student will simulate agents and their movement/transportation behaviour under different urban development strategies, impacting energy demand and emissions. The findings will identify design opportunities to curb base energy demand and emissions while supporting human well-being; well-designed urban environments can enhance well-being by reducing commute times, improving access to essential services, and alleviating mobility poverty. This project presents a unique opportunity, as it will be jointly supervised by the Urban Energy Systems Laboratory at Empa, the Urban Energy Systems Group at Imperial College London, and Climate Compatible Growth (CCG). This collaboration will provide access to cutting-edge international research, expertise, and resources across these teams.
Safe reinforcement learning-based V2X operation of EV fleets for demand-side flexibility
The global electric vehicle (EV) fleet is projected to reach 145 million units by 2030, posing new threats to the reliability of the power system. However, EVs can also play a key role as a source of demand-side flexibility to support the system in managing uncertainty resulting from the integration of renewable energy resources. The onsite coupling of photovoltaics (PVs), battery energy storage systems (BESS) and EV fleets with vehicle-to-grid (V2G) technology has shown promising performance in terms of demand-side flexibility provision.
Safe deep reinforcement learning for building control
Buildings are significant energy consumers, primarily due to the operation of heating, ventilation, and air conditioning (HVAC) systems. Effective control of such systems is crucial for enhancing overall energy efficiency. Typically, traditional rule-based controllers are used due to their affordability and interpretability. However, as complexity increases, these controllers suffer from non-optimal performance and limited scalability. Recent advancements in Deep Reinforcement Learning (DRL) provide a data-driven alternative, demonstrating promising control performance without the need for explicit system modeling. Despite these advantages, conventional DRL approaches often fail to account for specific operational constraints present in HVAC systems. One critical constraint is the requirement for smooth control actions with a limited number of on-off switches, as frequent switching can lead to faster deterioration of the controlled systems. Therefore, it is imperative to develop data-driven control strategies that not only optimize energy consumption but also adhere to these operational constraints. This study, part of the Euthermo Project, aims to develop safe reinforcement learning algorithms for building climate control.
Multi Agent Deep Reinforcement Learning for Building Control
Energy consumption in buildings is a critical concern, primarily driven by the operation of heating, ventilation, and air conditioning (HVAC) systems, lighting, and other appliances. Efficient control of these systems is paramount for achieving significant energy savings and reducing environmental impact. Traditional rulebased controllers, while cost-effective and easy to implement, often fail to provide optimal performance and lack scalability as system complexity grows. Recent advancements in Deep Reinforcement Learning (DRL) offer a powerful, data-driven alternative. DRL has shown promising results in optimizing control performance without the need for explicit system modeling. However, the complexity of managing multiple interdependent control variables within a building remains a challenge. For instance, the heating control of individual rooms can influence each other, and shading controls can affect both heating and cooling demands.

Powered by  SiROP - the academic career network