Femtosecond pulse parameter estimation from photoelectron momenta using machine learning

Abstract

Deep learning models have provided huge interpretation power for image-like data. Specifically, convolutional neural networks (CNNs) have demonstrated incredible acuity for tasks such as feature extraction or parameter estimation. Here we test CNNs on strong-field ionization photoelectron spectra, training on theoretical data sets to `invert' experimental data. Pulse characterization is used as a `testing ground', specifically we retrieve the laser intensity, where `traditional' measurements typically lead to 20% uncertainty. We report on crucial data augmentation techniques required to successfully train on theoretical data and return consistent results from experiments, including accounting for detector saturation. The same procedure can be repeated to apply CNNs in a range of scenarios for strong-field ionization. Using a predictive uncertainty estimation, reliable laser intensity uncertainties of a few percent can be extracted, which are consistently lower than those given by traditional techniques. Using interpretability methods can reveal parts of the distribution that are most sensitive to laser intensity, which can be directly associated with holographic interferences. The CNNs employed provide an accurate and convenient ways to extract parameters, and represent a novel interpretational tool for strong-field ionization spectra.

arXiv comment13 pages, 5 figures

References in corpus (30)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Striving for Simplicity: The All Convolutional Net
• Machine learning and the physical sciences
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• EfficientNetV2: Smaller Models and Faster Training
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Attosecond physics at the nanoscale
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Symphony on Strong Field Approximation
• Paradigm shift in electron-based crystallography via machine learning
• Symbolic Discovery of Optimization Algorithms
• High-order above-threshold ionization: the uniform approximation and the effect of the binding potential
• It is all about phases: ultrafast holographic photoelectron imaging
• Deep Learning for Feynman's Path Integral in Strong-Field Time-Dependent Dynamics
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Coulomb-corrected quantum interference in above-threshold ionization: Working towards multi-trajectory electron holography
• QPROP with faster calculation of photoelectron spectra
• Coulomb-free and Coulomb-distorted recolliding quantum orbits in photoelectron holography
• Deep transfer learning for image classification: a survey
• Deep neural networks for classifying complex features in diffraction images
• Analytic quantum-interference conditions in Coulomb corrected photoelectron holography
• Spiral-like Holographic Structures: Unwinding Interference Carpets of Coulomb-Distorted Orbits in Strong-Field Ionization
• Holographic detection of parity in atomic and molecular orbitals
• Deep learning for retrieval of the internuclear distance in a molecule from interference patterns in photoelectron momentum distributions
• Deep learning and high harmonic generation
• Neural-network-powered pulse reconstruction from one-dimensional interferometric cross-correlation traces
• Transfer learning, alternative approaches, and visualization of a convolutional neural network for retrieval of the internuclear distance in a molecule from photoelectron momentum distributions
• Quantum Estimation in Strong Fields: in situ ponderomotive sensing