zur Hauptnavigation springen zum Inhaltsbereich springen

BayWISS-Kolleg Life Sciences and Green Technologies www.baywiss.de

Research Projects Life Sciences and Green Technologies

© chuttersnap / Unsplash'

PhD Projects

Towards data efficient and robust weed detection leveraging foundational models.

Accurate weed detection plays a crucial role in sustainable crop management, enabling targeted interventions that reduce chemical use and improve yield. Deep learning-based weed detection and targeted, site-specific weed management offer significant opportunities for resource and environmental conservation in agriculture. However, current state-of-the-art (SOTA) deep learning models are typically trained on narrow, task-specific datasets and perform poorly when exposed to new, unseen field conditions. This is due to the inherently heterogeneous nature of weed detection data, which for instance varies across crop types, growth stages, soil conditions, imaging modalities, and environmental factors. These models also often suffer from being highly data-hungry, requiring large volumes of labeled data to function effectively. Collecting such data in agriculture is costly and time-consuming. Therefore, there is a pressing need for more data-efficient and generalizable approaches.
In this regard, we aim to explore and validate the hypothesis that pretrained foundation models, which have learned general visual features from large and diverse datasets, can be fine-tuned for weed detection with significantly less labeled data, while maintaining or improving performance compared to traditional SOTA models. These models are hypothesized to be less sensitive to data heterogeneity and capable of generalizing well, thereby enabling broader applicability in real-world agricultural conditions.

MEMBER IN THE JOINT ACADEMIC PARTNERSHIP

since

Joint Academic Partnership Life Sciences and Green Technologies

Supervisor Technical University of Munich:

Prof. Dr. agr. Heinz Bernhardt

Stable 4.0 (Integrated Dairy Farming)

Current research projects

  • Animal-Machine Interaction
  • Influencing Factors Analysis on Infield Logistics
  • Precision Grassland Farming
  • Automatic Feeding Systems for Cattle
  • Modeling agricultural transport logistics
  • Simulation agricultural crop chains

Projects:

Supervisor Weihenstephan-Triesdorf University of Applied Sciences:

Prof. Dr. Florian Haselbeck

The Professorship of Smart Farming at Weihenstephan-Triesdorf University of Applied Sciences, headed by Florian Haselbeck, conducts research on AI-based methods for various applications in a sustainability context. The team's main focus is on developing computer vision and time series forecasting methods as well as multimodal machine learning approaches to create practical and scientifically sound solutions in close collaboration with domain experts. 

Project:

Harshavardhan Subramanian

Harshavardhan Subramanian

Weihenstephan-Triesdorf University of Applied Sciences

Master: Statistics and Machine Learning, Linköping University, Sweden

Bachelor: Industrial Engineering and Management, Visvesvaraya Technological University, India

Publication: Bukas, Christina, Harshavardhan Subramanian, Fenja See, Carina Steinchen, Ivan Ezhov, Gowtham Boosarpu, Sara
Asgharpour et al. ”MultiOrg: A Multi-rater Organoid-detection Dataset.” Advances in Neural Information Processing
Systems 37 (2024): 95808-95839.

Coordination

Get in touch. We look forward to your questions and ideas for our Joint Academic Partnership Life Sciences and Green Technologies

Dr. Michaela Stegmann

Dr. Michaela Stegmann

Koordinatorin BayWISS-Verbundkolleg Life Sciences und Grüne Technologien

Hochschule für angewandte Wissenschaften Weihenstephan-Triesdorf
Zentrum für Forschung und Wissenstransfer
Am Staudengarten 12
85354 Freising

Telephone: +49 816171 6358
life-sciences.vk [ at ] baywiss.de