arXiv subjects

Debora Keller

Publications and source records attributed to Debora Keller.

3 recordsLinked to original sources

arXiv2026

Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy

The transmission electron microscope facilitates the highest-resolution imaging of any instrument ever created, and its limiting factor is no longer spatial resolution but dose efficiency. Low electron doses avoid sample damage but produce noisy images for which, unlike in classical computer vision, there is no ground truth. Autonomous materials experimentation poses a related problem, since closed-loop instruments need representations grounded in the microscope state at acquisition. Both demand representations grounded in how an image was acquired. We release 7,330 paired high-angle annular dark-field scanning-TEM (HAADF-STEM) images and their seven-dimensional acquisition metadata, and propose Contrastive Image-Metadata Pre-training (CIMP), a CLIP-style encoder that aligns the two modalities and reaches 84.4% Top-1 cross-modal retrieval on a held-out split. All seven parameters are individually recoverable from the frozen visual embedding through a linear probe, and we use the embedding to condition a metadata-conditioned style-transfer model that re-renders experimental images under different acquisition parameters. Virtually scaling dwell time and beam current of low-dose images turns this model into a physics-informed denoiser; in a blind user study, experimental microscopists prefer it over the current state-of-the-art denoiser for STEM imagery on 70.2% of trials.

cs.LG↗

arXiv2023

Net electrophilicity as computational route for the choice of favorable ionic liquids in nanoparticle production

In the last years, the potential of using ionic liquids (IL)s as an environment for nanoparticle (NP) synthesis has been demonstrated and in particular, triggering NP formation in ILs by electron irradiation has been reported as a very simple and clean route for NP production. Starting from the recent evidence for a correlation between an IL's capability to support NP production and the radiochemical instability of the IL's cation, we used conceptual Density Functional Theory (DFT) to provide a pre-screening of a set of different IL cations. The screened quantity is the net electrophilicity which we suggest as possible measure of this instability. Therefore, our work not only gives a measure for the likelihood of NP generation in different ILs, but it also provides a model which can further be extended and applied to obtain information about any other IL of interest. Moreover, our theoretical approach outlines a strategy which may reduce a lengthy experimental investigation for the identification of the most suitable IL for a particular reaction.

physics.chem-ph↗

arXiv2021

Self-supervised denoising for massive noisy images

We propose an effective deep learning model for signal reconstruction, which requires no signal prior, no noise model calibration, and no clean samples. This model only assumes that the noise is independent of the measurement and that the true signals share the same structured information. We demonstrate its performance on a variety of real-world applications, from sub-Ångström resolution atomic images to sub-arcsecond resolution astronomy images.

cs.CV↗