Principal Investigator: Daniel Ponsa
Email: daniel.ponsa@cvc.uab.cat
Web: https://www.cvc.uab.es/research-lines/multispectral/
Brief Theme Description
Continuous Earth monitoring is essential to face some of today’s most important challenges: preserving the environment, maximizing agricultural production, and optimizing water use. This growing need has led to the proliferation of services dedicated to terrestrial remote sensing, primarily based on satellites.
Although existing systems provide images for developing certain solutions, they also impose limitations. These limitations are due to insufficient spatial, spectral, and temporal resolution, which restricts the range of problems that can be addressed. Resensoring current systems is not feasible, and acquiring alternative images with better resolution can be very expensive.
Considering these challenges, our group focuses on enhancing the spatial, spectral, and temporal resolution of satellite imagery through the application of super-resolution and fusion techniques. We design systems that optimally combine satellite imagery with minimal high-resolution observations, generating reliable data. This data can then be used to build impactful solutions in agriculture and Earth observation activities.
Key Responsibilities
- Develop models for digital image restoration and enhancement in Earth monitoring contexts.
- Apply AI techniques to improve Earth observation systems for sustainable resource management.
- Research, design and implement the integration of Foundation Models in common Earth observation downstream tasks (semantic segmentation, detection, …).
Qualifications
- PhD in Computer Science, Artificial Intelligence, Environmental Science, or related fields.
- Strong knowledge of AI techniques, including deep learning, image processing, and multimodal data integration.
- Excellent collaborative skills and an interest in sustainability and preservation applications.
Available Infrastructures: GPU-based computer servers.
Keywords: Super-Resolution; Fusion; Deep Learning; Precision Agriculture; Earth Observation.
