Agriculture and Environment Natural Resources

Area/s: Agriculture and Environment | Natural Resources

Organization: Universitat Autònoma de Barcelona

Research theme code : RLA-UAB-06

UAB invites applications for a postdoctoral fellowship focused on machine learning based data compression. Fellows will work on developing AI models for compressing data coming from different sources (e.g., synchrotron data, remote sensing, astronomy, …), for different scenarios (long-term archiving, on-the-fly compression, on-the-ground compression, on-board satellites compression), and contemplating lossy, lossless and near-lossless compression. Ideal candidates will have a background in AI and be eager to drive innovations with real-world industrial and scientific applications.

Minimum Requirements:

  • At least two years of postdoctoral research experience after completion of the PhD.
  • Proven expertise in data compression, including advanced techniques and practical implementations.
  • Priority will be given to candidates with experience in synchrotron data compression, due to the complexity and scale of these datasets. Synchrotron data typically involve extremely high-resolution imaging and continuous data streams, which demand sophisticated compression strategies to reduce size without compromising scientific integrity.
    Illustrative examples: compression of 3D image stacks from X-ray diffraction experiments, or efficient handling of massive data flows in high-speed computed tomography.

Key Responsibilities:

  • Design and develop AI models for data compression.
  • Research, design and implement algorithms for real-world applications.
  • Supervise PhD students within the research group.

Qualifications:

  • PhD in Computer Science, Data Science, Mathematics or related fields.
  • Strong knowledge of AI techniques, including deep learning and image processing.
  • Interest in interdisciplinary collaboration at the intersection of technology and real-world applications.
  • Excellent collaborative and communication skills.

Career Development Plan

The detailed Career Development Plan will be finalized after the selection of the candidate and will be adjusted according to the research group’s needs and the fellow’s profile. This process will take place once the call is resolved, ensuring optimal alignment between project objectives and the fellow’s expertise.

Scientific Context and Impact

Our work aims to address the challenges posed by the ever-growing volume of data generated daily. Here are some illustrative examples:

  • Synchrotron Data: Experiments at synchrotron facilities produce extremely large datasets, including high-resolution diffraction patterns and tomographic sequences, which require advanced compression techniques to enable efficient storage and transmission.
  • Hyperspectral Coding: Multispectral and hyperspectral images contain numerous spectral bands, each selectively detecting different frequencies of light. These bands provide valuable information for Earth and space observation tasks. However, their high dimensionality presents compression challenges.
  • Satellite Constellations: With the rise of smaller, more affordable satellites, constellations are becoming common, but data transmission from satellites to Earth has restricted band-with capabilities.

Benefits of Machine Learning based approaches include:

  • Improved Compression Ratios: Machine learning algorithms can exploit redundancy across spectral bands, leading to more compact representations.
  • Energy Efficiency: ML-based approaches can reduce energy consumption during compression, and lightweight approaches can be devised for resource-constrained environments.
  • Guaranteed Data Quality: By optimizing for specific purposes (e.g., land cover classification, synchrotron data exploitation), ML models can maintain desired image quality.

Integration and Collaborations

The selected fellow will join the Department of Information and Communications Engineering at UAB, within the Interactive Coding of Images (GICI) research group. The fellow will collaborate with several international partners, including synchrotron facilities, space agencies, private companies, ….

Principal Investigator: