PILA: Physics-Informed Low Rank Augmentation for Interpretable Earth Observation

Add to your list(s) Download to your calendar using vCal

• Yihang She, University of Cambridge
• Friday 13 March 2026, 13:00-14:00
• Room GS15 at the William Gates Building and on Zoom: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon .

If you have a question about this talk, please contact lyr24.

Abstract

Physically meaningful representations are essential for Earth Observation (EO), yet existing physical models are often simplified and incomplete. This leads to discrepancies between simulation and observations that hinder reliable forward model inversion. Common approaches to EO inversion either ignored this incompleteness or relied on case-specific pre-processing. More recent methods use physics-informed autoencoders but depend on auxiliary variables that are difficult to interpret and multiple regularizers that are difficult to balance. We propose Physics-Informed Low-Rank Augmentation (PILA), a framework that augments incomplete physical models using a learnable low-rank residual to improve flexibility, while remaining close to the governing physics. We evaluate PILA on two EO inverse problems involving diverse physical processes: forest radiative transfer inversion from optical remote sensing; and volcanic deformation inversion from Global Navigation Satellite Systems (GNSS) displacement data. Across different domains, PILA yields more accurate and interpretable physical variables. For forest spectral inversion, it improves the separation of tree species and, compared to ground measurements, reduces prediction errors by 40-71\% relative to the state-of-the-art. For volcanic deformation, PILA ’s recovery of variables captures a major inflation event at the Akutan volcano in 2008, and estimates source depth, volume change, and displacement patterns that are consistent with prior studies that however required substantial additional pre-processing. Finally, we analyse the effects of model rank, observability, and physical priors, and suggest that PILA may offer an effective general pathway for inverting incomplete physical models even beyond the domain of Earth Observation. The code is available at https://github.com/yihshe/PILA.git.

Bio

Yihang She is a third-year PhD student in Computer Science at the University of Cambridge, supervised by Prof. Srinivasan Keshav and Prof. Andrew Blake. His research focuses on computer vision for forest monitoring and interpretable Earth observation.

This talk is part of the Energy and Environment Group, Department of CST series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Department of Computer Science and Technology talks and seminars
• Energy and Environment Group, Department of CST
• Interested Talks
• Room GS15 at the William Gates Building and on Zoom: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• yk449

Note that ex-directory lists are not shown.