Related papers: PaMMA-Net: Plasmas magnetic measurement evolution …

The convergence of statistical learning and molecular physics is transforming our approach to modeling biomolecular systems. Physics-informed machine learning (PIML) offers a systematic framework that integrates data-driven inference with…

Geophysical inversion attempts to estimate the distribution of physical properties in the Earth's interior from observations collected at or above the surface. Inverse problems are commonly posed as least-squares optimization problems in…

Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in…

A deep neural network is developed and trained on magnetic measurements (input) and EFIT poloidal magnetic flux (output) on the EAST tokamak. In optimizing the network architecture, we use automatic optimization in searching for the best…

In a typical fusion experiment, the plasma can have several possible confinement modes. At the TCV tokamak, aside from the Low (L) and High (H) confinement modes, an additional mode, dithering (D), is frequently observed. Developing methods…

Time series change detection is a critical task for exploring ecosystem dynamics using time series remote sensing images, because it can simultaneously indicate where and when change occur. While deep learning has shown excellent…

The proper classification of plasma regions in near-Earth space is crucial to perform unambiguous statistical studies of fundamental plasma processes such as shocks, magnetic reconnection, waves and turbulence, jets and their combinations.…

The understanding of the mechanisms responsible for particle transport is of the utmost importance for magnetized fusion plasmas. A peaked density profile is attractive to improve the fusion rate, which is proportional to the square of the…

Understanding how protein mutations affect protein-nucleic acid binding is critical for unraveling disease mechanisms and advancing therapies. Current experimental approaches are laborious, and computational methods remain limited in…

We use a Convolutional Recurrent Neural Network approach to learn morphological evolution driven by surface diffusion. To this aim we first produce a training set using phase field simulations. Intentionally, we insert in such a set only…

Plasma systems exhibit complex multiscale dynamics, resolving which poses significant challenges for conventional numerical simulations. Machine learning (ML) offers an alternative by learning data-driven representations of these dynamics.…

Data-driven machine learning models often require extensive datasets, which can be costly or inaccessible, and their predictions may fail to comply with established physical laws. Current approaches for incorporating physical priors…

The limits of molecular dynamics (MD) simulations of macromolecules are steadily pushed forward by the relentless developments of computer architectures and algorithms. This explosion in the number and extent (in size and time) of MD…

Dusty plasmas are ubiquitous throughout the universe, spanning laboratory and industrial plasmas, fusion devices, planetary environments, cometary comae, and interstellar media. Despite decades of research, many aspects of their behavior…

This work describes a laboratory plasma experiment and initial results which should give insight into the magnetic dynamics of accretion discs and jets. A high-speed multiple-frame CCD camera reveals images of the formation and helical…

The analysis of tabular data has traditionally been dominated by gradient-boosted decision trees (GBDTs), known for their proficiency with mixed categorical and numerical features. However, recent deep learning innovations are challenging…

We develop a self-consistent analytical two-fluid framework for plasma evolution in the short-time regime, elucidating the fundamental mechanism underlying the coupled generation of flow and magnetic fields. We show that consistency between…

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes. Recently, geometric deep learning, especially Graph Neural Networks, has shown promising performance in molecular…