Search

Low-temperature plasmas are partially ionized gases, where ions and neutrals coexist in a highly reactive environment. This creates a rich chemistry, which is often difficult to understand in its full complexity. In this work, we develop a machine learning model to identify the most important reactions in a given chemical scheme. The training data are an initial distribution of species and a final distribution of species, which can be obtained from either experiments or simulations. The model is trained to provide a set of reaction weights, which become the basis for reducing the chemical scheme. The approach is applied to N$_2$-H$_2$ plasmas, created by an electric discharge at low pressure, where the main goal is to produce NH$_3$. The interplay of multiple species, as well as of volume and surface reactions, make this chemistry especially challenging to understand. Reducing the chemical scheme via the proposed model helps identify the main chemical pathways.

The proliferation of wireless devices requires flexible network infrastructures to meet the increasing Quality of Service (QoS) requirements. Mobile Robotic Platforms (MRPs) acting as mobile communications cells are a promising solution to provide on-demand wireless connectivity in dynamic networking scenarios. However, the energy consumption of MRPs is a challenge that must be considered to maximize the availability of the wireless networks created. The main contribution of this paper is the experimental evaluation of the energy consumption of an MRP acting as a mobile communications cell. The evaluation considers different actions performed by a real MRP, demonstrating that energy consumption varies significantly with the type of action performed. The results obtained pave the way for optimizing MRP movement in dynamic networking scenarios, maximizing wireless network's availability while minimizing the MRP energy consumption.

We explore the possibility of fully replacing a plasma physics kinetic simulator with a graph neural network-based simulator. We focus on this class of surrogate models given the similarity between their message-passing update mechanism and the traditional physics solver update, and the possibility of enforcing known physical priors into the graph construction and update. We show that our model learns the kinetic plasma dynamics of the one-dimensional plasma model, a predecessor of contemporary kinetic plasma simulation codes, and recovers a wide range of well-known kinetic plasma processes, including plasma thermalization, electrostatic fluctuations about thermal equilibrium, and the drag on a fast sheet and Landau damping. We compare the performance against the original plasma model in terms of run-time, conservation laws, and temporal evolution of key physical quantities. The limitations of the model are presented and possible directions for higher-dimensional surrogate models for kinetic plasmas are discussed., Comment: title changed, accepted for publication in Machine Learning: Science and Technology, code available at https://github.com/diogodcarvalho/gns-sheet-model

This paper proposes a generative approach for the automatic typesetting of books in desktop publishing. The presented system consists in a computer script that operates inside a widely used design software tool and implements a generative process based on several typographic rules, styles and principles which have been identified in the literature. The performance of the proposed system is tested through an experiment which included the evaluation of its outputs with people. The results reveal the ability of the system to consistently create varied book designs from the same input content as well as visually coherent book designs with different contents while complying with fundamental typographic principles., Comment: 26 pages, 5 figures. Revised version published at Visual Informatics, 7(2), pp. 1\textendash{}12

In the fusion community, the use of high performance computing (HPC) has been mostly dominated by heavy-duty plasma simulations, such as those based on particle-in-cell and gyrokinetic codes. However, there has been a growing interest in applying machine learning for knowledge discovery on top of large amounts of experimental data collected from fusion devices. In particular, deep learning models are especially hungry for accelerated hardware, such as graphics processing units (GPUs), and it is becoming more common to find those models competing for the same resources that are used by simulation codes, which can be either CPU- or GPU-bound. In this paper, we give examples of deep learning models -- such as convolutional neural networks, recurrent neural networks, and variational autoencoders -- that can be used for a variety of tasks, including image processing, disruption prediction, and anomaly detection on diagnostics data. In this context, we discuss how deep learning can go from using a single GPU on a single node to using multiple GPUs across multiple nodes in a large-scale HPC infrastructure., Comment: (to appear)

Assessing the technical efficiency of a set of observations requires that the associated data composed of inputs and outputs are perfectly known. If this is not the case, then biased estimates will likely be obtained. Data Envelopment Analysis (DEA) is one of the most extensively used mathematical models to estimate efficiency. It constructs a piecewise linear frontier against which all observations are compared. Since the frontier is empirically defined, any deviation resulting from low data quality (imperfect knowledge of data or IKD) may lead to efficiency under/overestimation. In this study, we model IKD and, then, apply the so-called Hit \& Run procedure to randomly generate admissible observations, following some prespecified probability density functions. Sets used to model IKD limit the domain of data associated with each observation. Any point belonging to that domain is a candidate to figure out as the observation for efficiency assessment. Hence, this sampling procedure must run a sizable number of times (infinite, in theory) in such a way that it populates the whole sets. The DEA technique is used during the execution of each iteration to estimate bootstrapped efficiency scores for each observation. We use some scenarios to show that the proposed routine can outperform some of the available alternatives. We also explain how efficiency estimations can be used for statistical inference. An empirical case study based on the Portuguese public hospitals database (2013-2016) was addressed using the proposed method.

The JET baseline scenario is being developed to achieve high fusion performance and sustained fusion power. However, with higher plasma current and higher input power, an increase in pulse disruptivity is being observed. Although there is a wide range of possible disruption causes, the present disruptions seem to be closely related to radiative phenomena such as impurity accumulation, core radiation, and radiative collapse. In this work, we focus on bolometer tomography to reconstruct the plasma radiation profile and, on top of it, we apply anomaly detection to identify the radiation patterns that precede major disruptions. The approach makes extensive use of machine learning. First, we train a surrogate model for plasma tomography based on matrix multiplication, which provides a fast method to compute the plasma radiation profiles across the full extent of any given pulse. Then, we train a variational autoencoder to reproduce the radiation profiles by encoding them into a latent distribution and subsequently decoding them. As an anomaly detector, the variational autoencoder struggles to reproduce unusual behaviors, which includes not only the actual disruptions but their precursors as well. These precursors are identified based on an analysis of the anomaly score across all baseline pulses in two recent campaigns at JET., Comment: (to appear)

The use of deep learning is facilitating a wide range of data processing tasks in many areas. The analysis of fusion data is no exception, since there is a need to process large amounts of data collected from the diagnostic systems attached to a fusion device. Fusion data involves images and time series, and are a natural candidate for the use of convolutional and recurrent neural networks. In this work, we describe how CNNs can be used to reconstruct the plasma radiation profile, and we discuss the potential of using RNNs for disruption prediction based on the same input data. Both approaches have been applied at JET using data from a multi-channel diagnostic system. Similar approaches can be applied to other fusion devices and diagnostics., Comment: arXiv admin note: substantial text overlap with arXiv:1811.00333

This paper reports the results of an experiment in high energy physics: using the power of the "crowd" to solve difficult experimental problems linked to tracking accurately the trajectory of particles in the Large Hadron Collider (LHC). This experiment took the form of a machine learning challenge organized in 2018: the Tracking Machine Learning Challenge (TrackML). Its results were discussed at the competition session at the Neural Information Processing Systems conference (NeurIPS 2018). Given 100.000 points, the participants had to connect them into about 10.000 arcs of circles, following the trajectory of particles issued from very high energy proton collisions. The competition was difficult with a dozen front-runners well ahead of a pack. The single competition score is shown to be accurate and effective in selecting the best algorithms from the domain point of view. The competition has exposed a diversity of approaches, with various roles for Machine Learning, a number of which are discussed in the document, Comment: 36 pages, 22 figures

Nuclear fusion is the process that powers the sun, and it is one of the best hopes to achieve a virtually unlimited energy source for the future of humanity. However, reproducing sustainable nuclear fusion reactions here on Earth is a tremendous scientific and technical challenge. Special devices -- called tokamaks -- have been built around the world, with JET (Joint European Torus, in the UK) being the largest tokamak currently in operation. Such devices confine matter and heat it up to extremely high temperatures, creating a plasma where fusion reactions begin to occur. JET has over one hundred diagnostic systems to monitor what happens inside the plasma, and each 30-second experiment (or pulse) generates about 50 GB of data. In this work, we show how convolutional neural networks (CNNs) can be used to reconstruct the 2D plasma profile inside the device based on data coming from those diagnostics. We also discuss how recurrent neural networks (RNNs) can be used to predict plasma disruptions, which are one of the major problems affecting tokamaks today. Training of such networks is done on NVIDIA GPUs., Comment: This paper is based on a talk presented at NVIDIA's GPU Technology Conference, which took place at the International Congress Center in Munich, Germany, October 9--11, 2018 (GTC Europe 2018)

Plasma tomography consists in reconstructing the 2D radiation profile in a poloidal cross-section of a fusion device, based on line-integrated measurements along several lines of sight. The reconstruction process is computationally intensive and, in practice, only a few reconstructions are usually computed per pulse. In this work, we trained a deep neural network based on a large collection of sample tomograms that have been produced at JET over several years. Once trained, the network is able to reproduce those results with high accuracy. More importantly, it can compute all the tomographic reconstructions for a given pulse in just a few seconds. This makes it possible to visualize several phenomena -- such as plasma heating, disruptions and impurity transport -- over the course of a discharge.