The interaction of ultrashort and intense laser pulses with solid targets and dense plasmas is a rapidly developing area of physics, this being mostly due to the significant advancements in laser technology. There is, thus, a growing interest in diagnosing as accurately as possible the numerous phenomena related to the absorption and reflection of laser radiation. At the same time, envisaged experiments are in high demand of increased accuracy simulation software. As laser-plasma interaction modelings are experiencing a transition from computationally-intensive to data-intensive problems, traditional codes employed so far are starting to show their limitations. It is in this context that predictive modelings of laser-plasma interaction experiments are bound to reshape the definition of simulation software. This chapter focuses an entire class of predictive systems incorporating big data, advanced machine learning algorithms and deep learning, with improved accuracy and speed. Making use of terabytes of already available information (literature as well as simulation and experimental data) these systems enable the discovery and understanding of various physical phenomena occurring during interaction, hence allowing researchers to set up controlled experiments at optimal parameters. A comparative discussion in terms of challenges, advantages, bottlenecks, performances and suitability of laser-plasma interaction predictive systems is ultimately provided.
Part of the book: Machine Learning