Student Assistant / Master Thesis - Deep Learning for Urban Climate Emulation

Fraunhofer Karriere; Arkansas; On-site; USD 11,160 - 22,320; Part time

Benefits offered by this job

Master's thesis

GPU resources

Mentorship

International collaboration

Job summary

Fraunhofer IBP offers a Master’s thesis opportunity at the intersection of AI and urban physics. You will work on neural operators, SDFs for geometry, and DL models to predict 3D wind and temperature fields in urban districts.

The role includes access to high-performance workstations and GPU resources, with mentorship from atmospheric modeling, meteorology and ML experts, and a collaboration with Concordia University in Canada.

Qualifications

• Enrollment in a relevant scientific computing or AI program.
• Strong Python and DL framework skills, or willingness to learn.
• Interest in geometric DL and fluid dynamics; willing to learn SDFs.

Responsibilities

• Assist with generating synthetic urban datasets using LES for training/validation.
• Implement Signed Distance Functions and gradients for building geometries as NN inputs.
• Develop and train DL models to approximate 3D wind and temperature fields in urban districts.
• Evaluate generalization capabilities of the model.
• Compare accuracy and inference speed against CFD results.

Skills

Python

Deep learning

PyTorch

TensorFlow

Geometric deep learning

PDEs

Fourier analysis

Education

Master's student in Scientific Computing/CS/Physics/Geoinformatics/Meteorology

Tools

PyTorch

TensorFlow

Job description

Traditional CFD solvers are too slow for iterative design applications, requiring days to evaluate a single urban design variant. Fraunhofer IBP is pioneering the use of Deep Learning emulators to provide high-fidelity microclimate predictions at speeds that are much higher than physics-based numerical solvers. We are seeking a Master’s student with a background in Scientific Computing or AI to develop neural operators that utilize Signed Distance Functions for geometry-resolving urban physics.

Be part of change

• Assist with the generation of synthetic urban datasets using large-eddy simulations (LES) to serve as training and validation data.
• Implement Signed Distance Functions (SDF) and their gradients to represent complex building geometries as inputs to the neural network.
• Develop and train Deep Learning (DL) models to approximate 3D wind and temperature fields in urban districts.
• Evaluate the model’s generalization capabilities.
• Compare the accuracy and inference speed of the DL emulator against traditional CFD results.

What You Contribute

• Enrollment in Scientific Computing, Computer Science, Physics, Geoinformatics, Meteorology, or a related computational field.
• Strong programming skills in Python and deep learning frameworks (PyTorch or TensorFlow), or a strong willingness to learn.
• Interest in geometric deep learning and the physics of fluid dynamics, or a strong willingness to learn.
• Familiarity with 3D data representations (voxels, point clouds, or SDFs), or a strong willingness to learn.
• Strong mathematical foundation in Partial Differential Equations (PDEs) and Fourier analysis.

What We Offer

• A Master’s thesis opportunity (6-12 months, or longer) at the intersection of AI and urban physics.
• Access to high-performance workstations and GPU resources for training large-scale models.
• Mentorship from experts in both atmospheric modeling, meteorology and machine learning.
• Access to a collaborative platform linking Fraunhofer IBP in Germany and Concordia University in Canada.

The weekly working time is at least 5 hours. This position is limited, an extension possible. We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities. Remuneration according to the general works agreement for employing assistant staff.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

If you have any questions, you may contact:

Dr. Afshin Afshari

Phone: [phone]

Fraunhofer Institute for Building Physics IBP

www.ibp.fraunhofer.de

Requisition Number: 85181 Application Deadline: