University of Luxembourg

About: University of Luxembourg is a education organization based out in Luxembourg, Luxembourg. It is known for research contribution in the topics: Population & European union. The organization has 4744 authors who have published 22175 publications receiving 381824 citations.

Improving Traffic Flow Prediction with Weather Information in Connected Cars: A Deep Learning Approach

Abstract: Transportation systems might be heavily affected by factors such as accidents and weather. Specifically, inclement weather conditions may have a drastic impact on travel time and traffic flow. This study has two objectives: first, to investigate a correlation between weather parameters and traffic flow and, second, to improve traffic flow prediction by proposing a novel holistic architecture. It incorporates deep belief networks for traffic and weather prediction and decision-level data fusion scheme to enhance prediction accuracy using weather conditions. The experimental results, using traffic and weather data originated from the San Francisco Bay Area of California, corroborate the effectiveness of the proposed approach compared with the state of the art.

Is the Cu/Zn disorder the main culprit for the voltage deficit in kesterite solar cells?

Abstract: Photovoltaic thin film solar cells based on kesterite Cu2ZnSn(Sx,Se1–x)4 compounds (CZTSSe) have reached >12% sunlight-to-electricity conversion efficiency. This is still far from the >20% record devices known in Cu(In1–y,Gay)Se2 and CdTe parent technologies. A selection of >9% CZTSSe devices reported in the literature is examined to review the progress achieved over the past few years. These devices suffer from a low open-circuit voltage (Voc) never better than 60% of the Voc max, which is expected from the Shockley-Queisser radiative limit (S-Q limit). The possible role of anionic (S/Se) distribution and of cationic (Cu/Zn) disorder on the Voc deficit and on the ultimate photovoltaic performance of kesterite devices, are clarified here. While the S/Se anionic distribution is expected to be homogeneous for any ratio x, some grain-to-grain and other non-uniformity over larger area can be found, as quantified on our CZTSSe films. Nevertheless, these anionic distributions can be considered to have a negligible impact on the Voc deficit. On the Cu/Zn order side, even though significant bandgap changes (>10%) can be observed, a similar conclusion is brought from experimental devices and from calculations, still within the radiative S-Q limit. The implications and future ways for improvement are discussed.

NLRP3 Inflammasome Is Expressed and Functional in Mouse Brain Microglia but Not in Astrocytes

Abstract: Neuroinflammation is the local reaction of the brain to infection, trauma, toxic molecules or protein aggregates. The brain resident macrophages, microglia, are able to trigger an appropriate response involving secretion of cytokines and chemokines, resulting in the activation of astrocytes and recruitment of peripheral immune cells. IL-1β plays an important role in this response; yet its production and mode of action in the brain are not fully understood and its precise implication in neurodegenerative diseases needs further characterization. Our results indicate that the capacity to form a functional NLRP3 inflammasome and secretion of IL-1β is limited to the microglial compartment in the mouse brain. We were not able to observe IL-1β secretion from astrocytes, nor do they express all NLRP3 inflammasome components. Microglia were able to produce IL-1β in response to different classical inflammasome activators, such as ATP, Nigericin or Alum. Similarly, microglia secreted IL-18 and IL-1α, two other inflammasome-linked pro-inflammatory factors. Cell stimulation with α-synuclein, a neurodegenerative disease-related peptide, did not result in the release of active IL-1β by microglia, despite a weak pro-inflammatory effect. Amyloid-β peptides were able to activate the NLRP3 inflammasome in microglia and IL-1β secretion occurred in a P2X7 receptor-independent manner. Thus microglia-dependent inflammasome activation can play an important role in the brain and especially in neuroinflammatory conditions.

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Abstract: Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not restricted to a grid. Instead, their precise locations contain essential physical information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles. Our architecture achieves state-of-the-art performance for benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally, we introduce a more challenging benchmark with chemical and structural variations that suggests the path for further work.

Machine Learning Force Fields

Abstract: In recent years, the use of Machine Learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.