Opportunities for Master's theses at D-MTEC
Explore opportunities to write your Master's thesis at a research group at D-MTEC or an associated lab. The feed is based on SiROP placements.
Scaling Expert Assessments Through AI and LLM-Based Reasoning: A Real-World Heat Pump Performance Assessment
system is configured correctly and running efficiently. This manual evaluation requires specialized knowledge, does not scale well, and can delay the detection of installation issues. With the rapid advancement of large language models and autonomous agent systems, there is a promising opportunity to automate parts of this expert reasoning process. In this thesis, you will investigate whether LLM-based agents can understand and interpret heat pump performance data in a way that mirrors human expert evaluations. You will study how experts identify typical installation problems, derive the key features and patterns from time-series data that are necessary for assessment, and design an AI workflow capable of generating explanations and recommendations. The work includes preparing data, experimenting with different model architectures and representations, and building a prototype system that evaluates performance and flags potential issues. The goal is to deliver a validated proof-of-concept that demonstrates how AI can support or partially automate expert feedback, ultimately enabling scalable, consistent, and timely assessments for large fleets of connected heat pumps. This project combines applied machine learning, energy systems knowledge, and agentic AI design, in collaboration with the ETH Agentic Systems Lab and the Bosch Lab.
Keywords
LLMs, Agentic AI, Time-Series, Applied Machine Learning, Energy Tech Innovation, Automated Diagnostics, Heat Pump
Labels
Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)
Goal
Contact Details
More information
Published since: 2025-11-18 , Earliest start: 2025-12-01
Organization Bosch IoT Lab
Hosts Potthoff Ugne
Topics Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology , Earth Sciences
AI for Supporting a Scalable Transition to Sustainable Heating in Residential Buildings
Heating systems in European homes were rarely designed with modern heat pumps in mind. When upgrading such buildings, one of the most important questions is whether the existing radiators can deliver enough heat to keep rooms warm under winter design conditions. Knowing the heating power of each radiator is essential for correctly sizing a heat pump, ensuring comfort, and avoiding costly mistakes. Yet most homeowners and many installers do not know which radiators are installed, how large they are, or what their thermal output is. Traditional assessments require manual measurements, catalog lookup, or accessing technical data that may be unavailable or difficult to interpret. With advances in artificial intelligence - especially computer vision and reasoning models - we now have the opportunity to automate this entire process. Instead of manual work, a homeowner or installer could simply take a few photos of each radiator. An AI system could then recognize the radiator type, estimate its dimensions, and calculate its expected heating power at typical operating conditions. Such a tool would significantly simplify and speed up heat load calculations, which form the foundation for designing efficient, reliable heat pump systems in existing homes. This research aims to explore how AI can bridge this gap by interpreting real-world images and transforming them into actionable engineering information.
Keywords
Computer Vision, AI, Automated Assessment, Heat Pump, Reliability Analysis
Labels
Collaboration , Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)
Description
Goal
More information
Published since: 2025-11-18 , Earliest start: 2025-12-01
Organization Bosch IoT Lab
Hosts Potthoff Ugne
Topics Mathematical Sciences , Information, Computing and Communication Sciences , Engineering and Technology , Earth Sciences , Physics
Master Thesis Economics of spatial and temporal information for improving nitrogen efficiency in agriculture.
Background Switzerland has ambitious goals to reduce nitrogen surpluses in agriculture. An important mechanism in this context is to improve nitrogen efficiency. In this context, new technologies such as precision farming, and remote sensing and new sensors can provide better information on nutrient availability in the field. In the past, these efforts were mainly focused on improving spatial application patterns. This thesis aims to also include the temporal application pattern, i.e. when to apply fertilizer. Such spatial and temporal information can help farmers avoid nitrogen losses by applying the right amount of fertilizer at the right time and place to meet crop needs. Soil health sensors (such as those developed by Digit Soil) can provide additional information about the timing of fertilizer application. Combining spatial and temporal information about fertilizer application could improve nitrogen efficiency in crop production and contribute to a more sustainable agricultural sector. Research questions ● What are the economic costs and benefits of knowing when to fertilize? ● How big is the potential to reduce fertilizing by using temporal information? ● What is the potential of spatial and temporal information for achieving nitrogen efficiency goals in Swiss agriculture?
Labels
Master Thesis , ETH Zurich (ETHZ)
Description
Goal
Contact Details
More information
Published since: 2025-11-10 , Earliest start: 2025-09-01 , Latest end: 2026-12-31
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Finger Robert, Dr.
Topics Agricultural, Veterinary and Environmental Sciences , Economics
Analysing the potential of multi-yield index insurance to cope with heat and/or drought risks
The agricultural sector is exposed to yield risks, such as weather anomalies (e.g. Beillouin et al., 2020; Schmitt et al., 2022). Farmers can implement on-farm and off-farm risk management strategies to mitigate these risks (Bardaji, 2016; OECD, 2021). On-farm strategies include crop diversification, while off-farm strategies include insurance. Farmers often combine these strategies. However, crop insurance across Europe currently does not take crop diversification opportunities into account in the insurance design. This master's thesis will evaluate the potential of multi-yield index insurance as an option to help farmers cope with weather risks such as heat and/or drought.
Keywords
Risk Management; Index Insurance; Diversification
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-10-16 , Earliest start: 2025-11-01 , Latest end: 2026-06-30
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Schmitt Jonas
Topics Agricultural, Veterinary and Environmental Sciences
Climate change adaptation of cash crop farming in Germany
Climate change is having a significant impact on agriculture around the world (Ortiz-Bobea et al., 2021). Consequently, farmers must adapt to more frequent and severe extreme weather events. They can implement short-term measures, such as irrigation, or long-term measures, such as soil protection. However, the extent to which these adaptations take place is usually unknown. This master's thesis aims to examine the short- and long-term adaptation of cash crop farming in Germany between 1979 and 2021. Quantifying the extent and effect of adaptation in these areas in the past will be crucial in determining the potential for future adaptation. The analysis could inform policymakers, farmers, industry, breeders, and other stakeholders.
Keywords
Climate change adaptation; long-difference approach; cash crop farming.
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-10-14 , Earliest start: 2025-11-01 , Latest end: 2026-06-30
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Schmitt Jonas
Topics Agricultural, Veterinary and Environmental Sciences
Bachelor/Master Thesis on Agentic AI in Education: Agents for Oral Student Examinations (ETH Zurich – Agentic Systems Lab, Lab Track)
This thesis project explores the use of Agentic AI systems in education, focusing on conducting oral student examinations with agentic AI. Students will work on an examination platform developed at ETH Zurich’s Agentic Systems Lab, which allows professors to upload course materials and automatically generate oral exam questions. The AI agent conducts examinations, asks follow-up questions, and evaluates responses in real-time. The thesis offers opportunities to contribute to the next generation of intelligent assessment systems by improving question generation, interactive reasoning, and evaluation accuracy, while investigating pedagogical and technological implications for higher education.
Keywords
Agentic AI, Oral Examinations, AI in Education, Large Language Models, Automated Assessment, Conversational AI, Human-AI Interaction, Pedagogy, Evaluation Systems, ETH Zurich, Educational Technology, Natural Language Processing, Generative AI, Adaptive Learning, Interactive Agents
Labels
Semester Project , Bachelor Thesis , Master Thesis , ETH Zurich (ETHZ)
Description
Goal
More information
More information
Published since: 2025-09-11 , Earliest start: 2025-10-01 , Latest end: 2026-07-01
Organization Agentic Systems Lab
Hosts Bertrand Pascal
Topics Information, Computing and Communication Sciences
Master thesis: Crop protection in organic and non-organic pesticide-free arable farming
Pesticide-free (non-organic) crop production is currently gaining ground in European agriculture as a new alternative pathway between conventional and organic farming. To successfully produce crops without using pesticides, farmers must adopt sustainable crop protection measures, e.g., following the principles of integrated crop protection (IPM) or agroecological crop protection (ACP). Even though both production systems, i.e., pesticide-free non-organic and organic, work without pesticides, the alternative crop protection measures used may differ between organic and non-organic farms. To date, little is known about potential differences between farming systems without pesticides regarding the adoption of alternative crop protection strategies.
Keywords
crop protection, pesticide-free, organic, integrated pest management (IPM), wheat, maize, Switzerland
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-09-11 , Earliest start: 2025-02-02 , Latest end: 2026-01-22
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Akter Sharmin
Topics Agricultural, Veterinary and Environmental Sciences
Labour and the transition to sustainable production in Swiss viticulture
This thesis examines the current state of labour in Swiss viticulture, and how this state could influence winemaker’s decision-making ability, using survey data from 489 producers across all major wine regions. Given viticulture’s labour intensity and Swiss viticulture facing a mix of high labour costs and poor mechanisability offers outlook into the economic and environmental sustainability.
Keywords
Labour, Data analysis, Viticulture, Pest Management
Labels
Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2025-08-04 , Earliest start: 2025-08-04 , Latest end: 2026-08-03
Applications limited to ETH Zurich
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Höper Philipp
Topics Economics
A Spatiotemporal Analysis of the Uptake of Fungus-Resistant Grapes
This thesis investigates the spatial and temporal patterns in the adoption of fungus-resistant grapevine varieties (also known as PiWi) in the Canton of Zurich. Using rich plot-level panel data (N=36,270), it explores how replanting decisions are shaped by spatial and temporal factors, contributing to a better understanding of pesticide risk reduction in viticulture.
Keywords
GIS, Data analysis, Viticulture, Pest Management
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-07-15 , Earliest start: 2025-07-15 , Latest end: 2026-07-15
Applications limited to ETH Zurich
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Zachmann Lucca
Topics Economics
Ex-ante assessment of merged biodiversity and landscape quality payments in Swiss agricultural policy
This thesis uses an ex-ante simulation to evaluate the effects of merging agglomeration bonuses and landscape quality payments in Swiss agricultural policy. Using a budget allocation model applied to the canton of Grisons, the study assesses the influence of varying cantonal co-financing levels on farm participation, income, and potential biodiversity outcomes.
Keywords
Biodiversity, collective agri-environmental schemes, budget allocation, co-finance mechanism
Labels
Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2025-07-14 , Earliest start: 2025-08-01 , Latest end: 2026-08-01
Organization Chair of Agricultural Economics and Policy D-USYS
Hosts Finger Robert, Dr.
Topics Economics
Marginal costs of biodiversity provision in Swiss agriculture
This thesis uses the bio-economic model FarmDyn to quantify the opportunity costs of biodiversity-friendly practices on Swiss dairy and beef farms, based on data from the canton of Grisons. The thesis evaluates the cost-efficiency of various agri-environmental scheme designs to inform biodiversity policy in Swiss mountain agriculture.
Keywords
Biodiversity, agriculture, agri-environmental schemes, opportunity costs, mountain farming
Labels
Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2025-07-14 , Earliest start: 2025-08-01 , Latest end: 2026-08-01
Organization Chair of Agricultural Economics and Policy D-USYS
Hosts Huber Robert , Finger Robert, Dr.
Topics Economics
Falling Through the Cracks: Understanding Non-Participation in Direct Payment Schemes among Swiss Grape Growers
This thesis examines factors behind non-participation in direct payment schemes by grape growers in Swiss viticulture using survey data from 489 producers across all major wine regions. Given viticulture’s high pesticide use and economic importance, the thesis offers policy-relevant insights into the effectiveness of agri-environmental programs.
Keywords
Agricultural Policy, Data analysis, Viticulture, Pest Management
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2025-07-07 , Earliest start: 2025-07-07 , Latest end: 2026-07-06
Applications limited to ETH Zurich
Organization Chair of Agricultural Economics and Policy D-MTEC
Hosts Zachmann Lucca
Topics Economics