The development of an open and free RISC-V architecture is of great interest for a wide range of areas, including high-performance computing and numerical simulation in mathematics, physics, chemistry and other problem domains. In this paper, we discuss the possibilities of accelerating computations on available RISC-V processors by improving the vectorization of several computer vision and machine learning algorithms in the widely used OpenCV library. It is shown that improved vectorization speeds up computations on existing prototypes of RISC-V devices by tens of percent.

The power of machine learning (ML) in feature identification can be harnessed for determining quantities in experiments that are difficult to measure directly. However, if an ML model is trained on simulated data, rather than experimental results, the differences between the two can pose an obstacle to reliable data extraction. Here we report on the development of ML-based diagnostics for experiments on high-intensity laser–matter interactions. With the intention to accentuate robust, physics-governed features, the presence of which is tolerant to such differences, we test the application of principal component analysis, data augmentation and training with data that has superimposed noise of gradually increasing amplitude. Using synthetic data of simulated experiments, we identify that the approach based on the noise of increasing amplitude yields the most accurate ML models and thus is likely to be useful in similar projects on ML-based diagnostics.

When entering the phase of big data processing and statistical inferences in experimental physics, the efficient use of machine learning methods may require optimal data preprocessing methods and, in particular, optimal balance between details and noise. In experimental studies of strong-field quantum electrodynamics with intense lasers, this balance concerns data binning for the observed distributions of particles and photons. Here we analyze the aspect of binning with respect to different machine learning methods (Support Vector Machine (SVM), Gradient Boosting Trees (GBT), Fully-Connected Neural Network (FCNN), Convolutional Neural Network (CNN)) using numerical simulations that mimic expected properties of upcoming experiments. We see that binning can crucially affect the performance of SVM and GBT, and, to a less extent, FCNN and CNN. This can be interpreted as the latter methods being able to effectively learn the optimal binning, discarding unnecessary information. Nevertheless, given limited training sets, the results indicate that the efficiency can be increased by optimizing the binning scale along with other hyperparameters. We present specific measurements of accuracy that can be useful for planning of experiments in the specified research area.

Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of real experimental data, ML-models can be pre-trained on synthetic data simulated based on the analytical theory and then fine-tuned using real experimental data. A limitation of this approach is the presence of the latent parameters of the analytical model, which values are difficult or impossible to estimate. Setting these parameters incorrectly may induce a dataset shift even when applied to synthetic data. To overcome this problem, we train the ML-model on a dataset with randomly varied latent parameters of the analythical model to force the ML-model to concentrate on more general patterns that depend weakly on the latent parameters. We applied this approach to the problem of tight focusing of a laser pulse with the complex structure of the wavefront. We observed good accuracy of reconstructing of the tilt parameters when training and testing the ML-model on datasets generated for different values of the latent parameters. This confirms that the ML-model was able to select relevant information without over-fitting for specific features inherent in certain values of the latent parameters. We believe that this approach will enrich possible applications of ML-methods to an experimental diagnostics of laser pulses.

Diagnostic methods play a critical role in understanding the properties of fast particle beams, which is essential for experimentally validating theoretical studies in laser–plasma interactions. Two-screen magnetic spectrometers are commonly used to simultaneously measure both the energy and angular electron distributions. In a magnetic field, electrons are deflected according to their energy, resulting in light signals detected by a scintillator. However, the analysis of the obtained data often involves solving complex multi-parameter problems, which typically require heuristic approaches and manual intervention. In this work, we propose a method for reconstructing the electron distribution using a deep neural network. Unlike existing methods, the proposed approach enables the automatic and simultaneous reconstruction of both the energy and angular electron distribution. Since the labeled experimental data are unavailable, synthetic data generated through numerical simulations, combined with data augmentation techniques, are used for training the neural network. The neural network achieved a cosine similarity of 0.79 between experimental data and data obtained through numerical simulation based on the predicted distribution.