English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Deep learning models have provided huge interpretation power for image-likedata. Specifically, convolutional neural networks (CNNs) have demonstratedincredible acuity for tasks such as feature extraction or parameter estimation.Here we test CNNs on strong-field ionization photoelectron spectra, training ontheoretical data sets to `invert' experimental data. Pulse characterization isused as a `testing ground', specifically we retrieve the laser intensity, where`traditional' measurements typically lead to 20% uncertainty. We report oncrucial data augmentation techniques required to successfully train ontheoretical data and return consistent results from experiments, includingaccounting for detector saturation. The same procedure can be repeated to applyCNNs in a range of scenarios for strong-field ionization. Using a predictiveuncertainty estimation, reliable laser intensity uncertainties of a few percentcan be extracted, which are consistently lower than those given by traditionaltechniques. Using interpretability methods can reveal parts of the distributionthat are most sensitive to laser intensity, which can be directly associatedwith holographic interferences. The CNNs employed provide an accurate andconvenient ways to extract parameters, and represent a novel interpretationaltool for strong-field ionization spectra.

Femtosecond pulse parameter estimation from photoelectron momenta using machine learning