Search

Increasing HPC cluster sizes and large-scale simulations that produce petabytes of data per run, create massive IO and storage challenges for analysis. Deep learning-based techniques, in particular, make use of these amounts of domain data to extract patterns that help build scientific understanding. Here, we demonstrate a streaming workflow in which simulation data is streamed directly to a machine-learning (ML) framework, circumventing the file system bottleneck. Data is transformed in transit, asynchronously to the simulation and the training of the model. With the presented workflow, data operations can be performed in common and easy-to-use programming languages, freeing the application user from adapting the application output routines. As a proof-of-concept we consider a GPU accelerated particle-in-cell (PIConGPU) simulation of the Kelvin- Helmholtz instability (KHI). We employ experience replay to avoid catastrophic forgetting in learning from this non-steady process in a continual manner. We detail challenges addressed while porting and scaling to Frontier exascale system., Comment: 12 pages, 9 figures

The mathematical consistency of the BMHV scheme of dimensional regularisation (DReg) comes at the cost of requiring symmetry-restoring counterterms to cancel the regularisation-induced breaking of gauge and BRST invariance. There is no unique way to extend a 4-dimensional theory to $D$ dimensions, and different choices can be made for the dimensionally regularised fermions, evanescent parts of their kinetic terms and evanescent gauge interactions. Here we present a detailed study of the impact of changing such evanescent details. We leverage this freedom to identify a particularly convenient formulation that simplifies practical calculations. In order to thoroughly study the available options, we focus on a general abelian chiral gauge theory including scalar fields and adopt a general approach to the BMHV implementation. This allows for specialisation to various models and different approaches, including those from the literature. Importantly, our model can be specialised to the abelian sector of the Standard Model (SM). Consequently, this article also serves as a roadmap for upcoming applications to the full SM.

Banded energy distributions of H$^{+}$, O$^{++}$, S$^{+++}$, and O$^+$ or S$^{++}$ ions between 100 eV to ~20 keV are consistently observed in Jupiter's magnetosphere mapping to M-shells between M=10-20. The bands correspond to flux enhancements at similar speeds for different ion species, providing the first evidence of simultaneous bounce-resonant acceleration of multiple ion species in Jupiter's magnetosphere. Ion enhancements occur for energies at which the bounce frequencies of the trapped ions matched integer harmonics of the System-III corotation frequency. The observations highlight a previously unknown interaction between corotation and bounce motion of <10 keV energy ions that is a fundamental and persistent process occurring in Jupiter's magnetosphere.

Recent advancements in diffusion models have enabled a wide range of works exploiting their ability to generate high-volume, high-quality data for use in various downstream tasks. One subclass of such models, dubbed Layout-to-Image Synthesis (LIS), learns to generate images conditioned on a spatial layout (bounding boxes, masks, poses, etc.) and has shown a promising ability to generate realistic images, albeit with limited layout-adherence. Moreover, the question of how to effectively transfer those models for scalable augmentation of few-shot detection data remains unanswered. Thus, we propose a collaborative framework employing a Large Language Model (LLM) and an LIS model for enhancing few-shot detection beyond state-of-the-art generative augmentation approaches. We leverage LLM's reasoning ability to extrapolate the spatial prior of the annotation space by generating new bounding boxes given only a few example annotations. Additionally, we introduce our novel layout-aware CLIP score for sample ranking, enabling tight coupling between generated layouts and images. Significant improvements on COCO few-shot benchmarks are observed. With our approach, a YOLOX-S baseline is boosted by more than 140%, 50%, 35% in mAP on the COCO 5-,10-, and 30-shot settings, respectively., Comment: This paper has been accepted at the Asian Conference on Computer Vision (ACCV), 2024

We live in a world that is experiencing an unprecedented boom of AI applications that increasingly penetrate and enhance all sectors of private and public life, from education, media, medicine, and mobility to the industrial and professional workspace, and -- potentially particularly consequentially -- robotics. As this world is simultaneously grappling with climate change, the climate and environmental implications of the development and use of AI have become an important subject of public and academic debate. In this paper, we aim to provide guidance on the climate-related regulation for data centers and AI specifically, and discuss how to operationalize these requirements. We also highlight challenges and room for improvement, and make a number of policy proposals to this end. In particular, we propose a specific interpretation of the AI Act to bring reporting on the previously unadressed energy consumption from AI inferences back into the scope. We also find that the AI Act fails to address indirect greenhouse gas emissions from AI applications. Furthermore, for the purpose of energy consumption reporting, we compare levels of measurement within data centers and recommend measurement at the cumulative server level. We also argue for an interpretation of the AI Act that includes environmental concerns in the mandatory risk assessment (sustainability risk assessment, SIA), and provide guidance on its operationalization. The EU data center regulation proves to be a good first step but requires further development by including binding renewable energy and efficiency targets for data centers. Overall, we make twelve concrete policy proposals, in four main areas: Energy and Environmental Reporting Obligations; Legal and Regulatory Clarifications; Transparency and Accountability Mechanisms; and Future Far-Reaching Measures beyond Transparency., Comment: 18 pages, 1 figure, preprint

One of the main challenges in optimal scaling of large language models (LLMs) is the prohibitive cost of hyperparameter tuning, particularly learning rate $\eta$ and batch size $B$. While techniques like $\mu$P (Yang et al., 2022) provide scaling rules for optimal $\eta$ transfer in the infinite model size limit, the optimal scaling behavior in the infinite data size limit remains unknown. We fill in this gap by observing for the first time an intricate dependence of optimal $\eta$ scaling on the pretraining token budget $T$, $B$ and its relation to the critical batch size $B_\mathrm{crit}$, which we measure to evolve as $B_\mathrm{crit} \propto T$. Furthermore, we show that the optimal batch size is positively correlated with $B_\mathrm{crit}$: keeping it fixed becomes suboptimal over time even if learning rate is scaled optimally. Surprisingly, our results demonstrate that the observed optimal $\eta$ and $B$ dynamics are preserved with $\mu$P model scaling, challenging the conventional view of $B_\mathrm{crit}$ dependence solely on loss value. Complementing optimality, we examine the sensitivity of loss to changes in learning rate, where we find the sensitivity to decrease with increase of $T$ and to remain constant with $\mu$P model scaling. We hope our results make the first step towards a unified picture of the joint optimal data and model scaling.

Although the magnetic fields in the quiet Sun account for the majority of the magnetic energy in the solar photosphere, inferring their exact spatial distribution, origin, and evolution poses an important challenge because the signals lie at the limit of todays instrumental precision. This severely hinders and biases our interpretations, which are mostly made through nonlinear model-fitting approaches. Our goal is to directly compare simulated and observed polarization signals in the FeI 630.1 nm and 630.2 nm spectral lines in the solar internetwork. This way, we aim to constrain the mechanism responsible for the generation of the quiet Sun magnetism while avoiding the biases that plague other diagnostic methods. We used three different three-dimensional radiative magneto-hydrodynamic simulations representing different scenarios of magnetic field generation in the internetwork: small-scale dynamo, decay of active regions, and horizontal flux emergence. We synthesized Stokes profiles at different viewing angles and degraded them according to the instrumental specifications of the spectro-polarimeter on the Hinode satellite. Finally, we statistically compared the simulated spectra to the observations at the appropriate viewing angles. The small-scale dynamo simulation reproduced best the statistical properties of the observed polarization signals. This is especially prominent for the disk center viewing geometry, where the agreement is excellent. Moving toward more inclined lines of sight, the agreement worsens slightly. The agreement between the small-scale dynamo simulation and observations at the disk center suggests that small-scale dynamo action plays an important role in the generation of quiet Sun magnetism. However, the magnetic field around 50 km above the photosphere in this simulation does not reproduce observations as well as at the very base of the photosphere.

We present two multilingual LLMs designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate competitive performance across multilingual benchmarks, as evidenced by their performance on European versions of ARC, HellaSwag, MMLU, and TruthfulQA.

Determining the location of a tropical cyclone's (TC) surface circulation center -- "center-fixing" -- is a critical first step in the TC-forecasting process, affecting current and future estimates of track, intensity, and structure. Despite a recent increase in the number of automated center-fixing methods, only one such method (ARCHER-2) is operational, and its best performance is achieved when using microwave or scatterometer data, which are not available at every forecast cycle. We develop a deep-learning algorithm called GeoCenter; it relies only on geostationary IR satellite imagery, which is available for all TC basins at high frequency (10-15 min) and low latency (< 10 min) during both day and night. GeoCenter ingests an animation (time series) of IR images, including 10 channels at lag times up to 3 hours. The animation is centered at a "first guess" location, offset from the true TC-center location by 48 km on average and sometimes > 100 km; GeoCenter is tasked with correcting this offset. On an independent testing dataset, GeoCenter achieves a mean/median/RMS (root mean square) error of 26.9/23.3/32.0 km for all systems, 25.7/22.3/30.5 km for tropical systems, and 15.7/13.6/18.6 km for category-2--5 hurricanes. These values are similar to ARCHER-2 errors when microwave or scatterometer data are available, and better than ARCHER-2 errors when only IR data are available. GeoCenter also performs skillful uncertainty quantification (UQ), producing a well calibrated ensemble of 200 TC-center locations. Furthermore, all predictors used by GeoCenter are available in real time, which would make GeoCenter easy to implement operationally every 10-15 min., Comment: Submitted to AMS journal Weather and Forecasting. Main body is 52 pages and 14 figures; supplement is another 33 pages and 28 figures

We study a generalised version of Gross-Neveu model in 2+1 dimensions. The model is inspired from graphene which shows a linear dispersion relation near the Dirac points. The phase structure and the thermodynamic properties in the mean field approximation have been studied before. Here we go beyond the mean field level by deriving a Beth-Uhlenbeck equation for Gaussian fluctuations, solutions of which we explore numerically, for the first time including their momentum dependence. We discuss the excitonic mass, fluctuation pressure and phase shifts. We also perform a comparison with the NJL model in 3+1 dimension and discuss its implication for graphene., Comment: 11 pages, 7 figures

In just the past few years multiple data-driven Artificial Intelligence Weather Prediction (AIWP) models have been developed, with new versions appearing almost monthly. Given this rapid development, the applicability of these models to operational forecasting has yet to be adequately explored and documented. To assess their utility for operational tropical cyclone (TC) forecasting, the NHC verification procedure is used to evaluate seven-day track and intensity predictions for northern hemisphere TCs from May-November 2023. Four open-source AIWP models are considered (FourCastNetv1, FourCastNetv2-small, GraphCast-operational and Pangu-Weather). The AIWP track forecast errors and detection rates are comparable to those from the best-performing operational forecast models. However, the AIWP intensity forecast errors are larger than those of even the simplest intensity forecasts based on climatology and persistence. The AIWP models almost always reduce the TC intensity, especially within the first 24 h of the forecast, resulting in a substantial low bias. The contribution of the AIWP models to the NHC model consensus was also evaluated. The consensus track errors are reduced by up to 11% at the longer time periods. The five-day NHC official track forecasts have improved by about 2% per year since 2001, so this represents more than a five-year gain in accuracy. Despite substantial negative intensity biases, the AIWP models have a neutral impact on the intensity consensus. These results show that the current formulation of the AIWP models have promise for operational TC track forecasts, but improved bias corrections or model reformulations will be needed for accurate intensity forecasts., Comment: 33 pages. 9 figures, 3 tables

The growth of streamer discharges is determined at their heads, for individual streamers as well as in collective phenomena, such as streamer trees or coronas or streamer bursts ahead of lighting leaders. Some properties of the streamer heads, such as velocity $v$ and radius $R$ now can be measured quite well, but this is very challenging for others such as the maximal electric field, the charge content of the streamer head and the degree of chemical excitation and ionization in the streamer channel. Here we develop, test and evaluate a macroscopic approximation for positive streamer heads in air that relates macroscopic streamer head properties to each other. In particular, we find that velocity $v$, radius $R$ and background field $E_{\rm bg}$ determine the complete profile of streamer heads with photoionization, if they propagate steadily. We also review Naidis' approximate relation between $v$, $R$ and the maximal field $E_{\rm max}$. The approximate head model developed in the present paper consists of three first-order ordinary differential equations along the streamer axis. It is derived from the classical fluid model for streamer discharges by assuming axisymmetry, steady streamer propagation (i.e. with constant velocity and shape), and a spherical shape of the charge layer around the streamer head. The new reduced model agrees well with full solutions of the classical fluid model, even when it is applied to accelerating streamers. Therefore the model can be used for evaluations of experiments, like for the determination of the maximal electric field from radius and velocity of the streamer, and it is a step towards constructing reduced models for the collective dynamics of multi-streamer discharges.

This paper critically examines the AI Act's provisions on climate-related transparency, highlighting significant gaps and challenges in its implementation. We identify key shortcomings, including the exclusion of energy consumption during AI inference, the lack of coverage for indirect greenhouse gas emissions from AI applications, and the lack of standard reporting methodology. The paper proposes a novel interpretation to bring inference-related energy use back within the Act's scope and advocates for public access to climate-related disclosures to foster market accountability and public scrutiny. Cumulative server level energy reporting is recommended as the most suitable method. We also suggests broader policy changes, including sustainability risk assessments and renewable energy targets, to better address AI's environmental impact., Comment: 5 pages, 1 table, preprint

Recent studies showcase the competitive accuracy of Vision Transformers (ViTs) in relation to Convolutional Neural Networks (CNNs), along with their remarkable robustness. However, ViTs demand a large amount of data to achieve adequate performance, which makes their application to small datasets challenging, falling behind CNNs. To overcome this, we propose GenFormer, a data augmentation strategy utilizing generated images, thereby improving transformer accuracy and robustness on small-scale image classification tasks. In our comprehensive evaluation we propose Tiny ImageNetV2, -R, and -A as new test set variants of Tiny ImageNet by transferring established ImageNet generalization and robustness benchmarks to the small-scale data domain. Similarly, we introduce MedMNIST-C and EuroSAT-C as corrupted test set variants of established fine-grained datasets in the medical and aerial domain. Through a series of experiments conducted on small datasets of various domains, including Tiny ImageNet, CIFAR, EuroSAT and MedMNIST datasets, we demonstrate the synergistic power of our method, in particular when combined with common train and test time augmentations, knowledge distillation, and architectural design choices. Additionally, we prove the effectiveness of our approach under challenging conditions with limited training data, demonstrating significant improvements in both accuracy and robustness, bridging the gap between CNNs and ViTs in the small-scale dataset domain., Comment: This paper has been accepted at International Conference on Pattern Recognition (ICPR), 2024

Protein dynamics play a crucial role in many biological processes and drug interactions. However, measuring, and simulating protein dynamics is challenging and time-consuming. While machine learning holds promise in deciphering the determinants of protein dynamics from structural information, most existing methods for protein representation learning operate at the residue level, ignoring the finer details of atomic interactions. In this work, we propose for the first time to use graph neural networks (GNNs) to learn protein representations at the atomic level and predict B-factors from protein 3D structures. The B-factor reflects the atomic displacement of atoms in proteins, and can serve as a surrogate for protein flexibility. We compared different GNN architectures to assess their performance. The Meta-GNN model achieves a correlation coefficient of 0.71 on a large and diverse test set of over 4k proteins (17M atoms) from the Protein Data Bank (PDB), outperforming previous methods by a large margin. Our work demonstrates the potential of representations learned by GNNs for protein flexibility prediction and other related tasks.

This article introduces a novel non-orthogonal multiple access (NOMA) scheme for coordinated uplink channels. The scheme builds on the recently proposed sparse-regression low-density parity-check (SR-LDPC) code, and extends the underlying notions to scenarios with many concurrent users. The resulting scheme, called Multi-User SR-LDPC (MU-SR-LDPC) coding, consists of each user transmitting its own SR-LDPC codeword using a unique sensing matrix in conjunction with a characteristic outer LDPC code. To recover the sent information, the decoder jointly processes the received signals using a low-complexity and highly-parallelizable AMP-BP algorithm. At finite blocklengths (FBL), MU-SR-LDPC codes are shown to achieve a target BER at a higher spectral efficiency than baseline orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) schemes with similar computational complexity. Furthermore, MU-SR-LDPC codes are shown to match the performance of maximum a posteriori (MAP) decoding in certain regimes. For certain blocklengths and a sufficiently high number of users, MU-SR-LDPC codes may achieve a higher spectral efficiency than the approximate FBL capacity of the effective single-user Gaussian channel seen by each user in a comparable OMA scheme. Results are supported by numerical simulations., Comment: This work has been submitted to the IEEE for possible publication

Kubo's linear response formalism has been used to calculate the orbital Hall conductivity (OHC) for non-magnetic undoped and doped transition metal systems, focusing on the impact of different types of disorder and the role of vertex corrections for the OHC. The doping- and temperature-dependence of the OH conductivity have been investigated and compared with corresponding results for the spin Hall conductivity (SHC). A strong difference has been found between the results for undoped and doped metallic systems. For elemental systems at finite temperature a dominating role of the intrinsic contribution to the temperature-dependent OH and SH conductivities is found. Moreover, the different temperature dependent behavior of the intrinsic SOC-independent OHC and SOC-driven SCH indicates a non-trivial relationship between these quantities. It is shown, that in contrast to the intrinsic part of the OH and SH conductivities, the extrinsic contributions in doped systems are determined by spin-orbit coupling for both of them. It is dominating at low temperature, strongly decreasing at higher temperatures due to the increasing impact of the electron-phonon scattering., Comment: 12 pages, 12 figures

This paper focuses on hyperparameter optimization for autonomous driving strategies based on Reinforcement Learning. We provide a detailed description of training the RL agent in a simulation environment. Subsequently, we employ Efficient Global Optimization algorithm that uses Gaussian Process fitting for hyperparameter optimization in RL. Before this optimization phase, Gaussian process interpolation is applied to fit the surrogate model, for which the hyperparameter set is generated using Latin hypercube sampling. To accelerate the evaluation, parallelization techniques are employed. Following the hyperparameter optimization procedure, a set of hyperparameters is identified, resulting in a noteworthy enhancement in overall driving performance. There is a substantial increase of 4\% when compared to existing manually tuned parameters and the hyperparameters discovered during the initialization process using Latin hypercube sampling. After the optimization, we analyze the obtained results thoroughly and conduct a sensitivity analysis to assess the robustness and generalization capabilities of the learned autonomous driving strategies. The findings from this study contribute to the advancement of Gaussian process based Bayesian optimization to optimize the hyperparameters for autonomous driving in RL, providing valuable insights for the development of efficient and reliable autonomous driving systems., Comment: Submitted and accepted by LOD24 conference https://lod2024.icas.events/

In this paper, we study the Cauchy problem for the linear plate equation with mass term and its applications to semilinear models. For the linear problem we obtain $L^p-L^q$ estimates for the solutions in the full range $1\leq p\leq q\leq \infty$, and we show that such estimates are optimal. In the sequel, we discuss the global in time existence of solutions to the associated semilinear problem with power nonlinearity $|u|^\alpha$. For low dimension space $n\leq 4$, and assuming $L^1$ regularity on the second datum, we were able to prove global existence for $\alpha> \max\{\alpha_c(n), \tilde\alpha_c(n)\}$ where $\alpha_c = 1+4/n$ and $\tilde \alpha_c = 2+2/n$. However, assuming initial data in $H^2(\mathbb{R}^n)\times L^2(\mathbb{R}^n)$, the presence of the mass term allows us to obtain global in time existence for all $1<\alpha \leq (n+4)/[n-4]_+$. We also show that the latter upper bound is optimal, since we prove that there exist data such that a non-existence result for local weak solutions holds when $\alpha > (n+4)/[n-4]_+$.

We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of high-impact weather events and aid in data assimilation for numerical weather prediction over the United States. Compared to convolutional approaches, which have limited receptive fields, our results show improved sharpness and higher accuracy across various composite reflectivity thresholds. Additional case studies over specific atmospheric phenomena support our quantitative findings, while a novel attribution method is introduced to guide domain experts in understanding model outputs., Comment: Published as a workshop paper at "Machine Learning for Earth System Modeling", ICML 2024; added acknowledgements and github link

`scores` is a Python package containing mathematical functions for the verification, evaluation and optimisation of forecasts, predictions or models. It supports labelled n-dimensional (multidimensional) data, which is used in many scientific fields and in machine learning. At present, `scores` primarily supports the geoscience communities; in particular, the meteorological, climatological and oceanographic communities. `scores` not only includes common scores (e.g., Mean Absolute Error), it also includes novel scores not commonly found elsewhere (e.g., FIxed Risk Multicategorical (FIRM) score, Flip-Flop Index), complex scores (e.g., threshold-weighted continuous ranked probability score), and statistical tests (such as the Diebold Mariano test). It also contains isotonic regression which is becoming an increasingly important tool in forecast verification and can be used to generate stable reliability diagrams. Additionally, it provides pre-processing tools for preparing data for scores in a variety of formats including cumulative distribution functions (CDF). At the time of writing, `scores` includes over 50 metrics, statistical techniques and data processing tools. All of the scores and statistical techniques in this package have undergone a thorough scientific and software review. Every score has a companion Jupyter Notebook tutorial that demonstrates its use in practice. `scores` supports `xarray` datatypes, allowing it to work with Earth system data in a range of formats including NetCDF4, HDF5, Zarr and GRIB among others. `scores` uses Dask for scaling and performance. Support for `pandas` is being introduced. The `scores` software repository can be found at https://github.com/nci/scores/, Comment: Minor revisions to text and table. Updated title. 6 pages, 1 table. Software repository at https://github.com/nci/scores/

In [1], the linked loop code (LLC) is presented as a promising code for the unsourced A-channel with erasures (UACE). The UACE is an unsourced multiple access channel in which active users' transmitted symbols are erased with a given probability and the channel output is obtained as the union of the non-erased symbols. In this paper, we extend the UACE channel model to the unsourced B-channel with erasures (UBCE). The UBCE differs from the UACE in that the channel output is the multiset union, or bag union, of the non-erased input symbols. In other words, the UBCE preserves the symbol multiplicity of the channel output while the UACE does not. Both the UACE and UBCE find applications in modeling aspects of unsourced random access. The LLC from [1] is enhanced and shown to outperform the tree code over the UBCE. Findings are supported by numerical simulations., Comment: 5 pages, 2 figures, accepted by ICASSP 2024

The encounter between the Jovian co-rotating plasma and Ganymede gives rise to electromagnetic waves that propagate along the magnetic field lines and accelerate particles by resonant or non-resonant wave-particle interaction. They ultimately precipitate into Jupiter's atmosphere and trigger auroral emissions. In this study, we use Juno/JADE, Juno/UVS data, and magnetic field line tracing to characterize the properties of electrons accelerated by the Ganymede-magnetosphere interaction in the far-field region. We show that the precipitating energy flux exhibits an exponential decay as a function of downtail distance from the moon, with an e-folding value of 29{\deg}, consistent with previous UV observations from the Hubble Space Telescope (HST). We characterize the electron energy distributions and show that two distributions exist. Electrons creating the Main Alfv\'en Wing (MAW) spot and the auroral tail always have broadband distribution and a mean characteristic energy of 2.2 keV while in the region connected to the Transhemispheric Electron Beam (TEB) spot the electrons are distributed non-monotonically, with a higher characteristic energy above 10 keV. Based on the observation of bidirectional electron beams, we suggest that Juno was located within the acceleration region during the 11 observations reported. We thus estimate that the acceleration region is extended, at least, between an altitude of 0.5 and 1.3 Jupiter radius above the 1-bar surface. Finally, we estimate the size of the interaction region in the Ganymede orbital plane using far-field measurements. These observations provide important insights for the study of particle acceleration processes involved in moon-magnetosphere interactions., Comment: Accepted for publication in JGR: Space Physics

Forecast verification is critical for continuous improvement in meteorological organizations. The Jive verification system was originally developed to assess the accuracy of public weather forecasts issued by the Australian Bureau of Meteorology. It started as a research project in 2015 and gradually evolved to be a Bureau operational verification system in 2022. The system includes daily verification dashboards for forecasters to visualize recent forecast performance and "Evidence Targeted Automation" dashboards for exploring the performance of competing forecast systems. Additionally, Jive includes a Jupyter Notebook server with the Jive Python library which supports research experiments, case studies, and the development of new verification metrics and tools. This paper describes the Jive verification system and how it helped bring verification to the forefront at the Bureau of Meteorology, leading to more accurate, streamlined forecasts. Jive has provided evidence to support forecast automation decisions and has helped to understand the evolving role of meteorologists in the forecast process. It has given operational meteorologists tools for evaluating forecast processes, including identifying when and how manual interventions lead to superior predictions. Work on Jive led to new verification science, including novel metrics that are decision-focused, including diagnostics for extreme conditions. Jive also provided the Bureau with an enterprise-wide data analysis environment and has prompted a clarification of forecast definitions. These collective impacts have resulted in more accurate forecasts, ultimately benefiting society, and building trust with forecast users. These positive outcomes highlight the importance of meteorological organizations investing in verification science and technology.

Induced by an ultra-short laser pulse, the electronic structure of a material undergoes strong modifications leading to a fast demagnetization in magnetic materials. Induced spin-flip transitions are one of the reasons for demagnetization, that is discussed in the literature as a Stoner-like mechanism. On the other hand, demagnetization due to transverse spin fluctuations is usually discussed on the basis of the Heisenberg Hamiltonian and hardly accounts for the modification of the electronic structure. In this work we demonstrate a strong impact of the laser-induced electron transitions, both spin-flip and spin-conserving, on the exchange coupling parameters. For this, a simple two-step scheme is suggested. As a first step, the electronic structure time evolution during the ultra-short laser pulse is described accurately within time-dependent density-functional theory (TD-DFT) calculations. As a next step, the information on the time-dependent electronic structure is used for calculations of the parameters of the Heisenberg Hamiltonian. A strong modification of the exchange coupling parameters is found in response to the applied ultra-short laser pulse. The most important reason for this modification is played by the laser induced repopulation of the electronic states. Although the changes of the exchange parameters are most prominent during the laser pulse, they may be important also for the magnetic relaxation. The same concerns the spin-lattice interactions playing a central role for the relaxation process. A strong impact of the laser-induced modification of the electronic structure on the spin-lattice coupling parameters is also shown in this work.

We study radio emissions from positive streamers in air using 3D simulations, from which the radiated electric field is computed by solving Jefimenko's equations. The simulations are performed at 0.5 bar using two photoionization methods: the Helmholtz approximation for a photon density and a Monte Carlo method using discrete photons, with the latter being the most realistic. We consider cases with single streamers, streamer branching, streamers interacting with preionization and streamer-streamer encounters. We do not observe a strong VHF radio signal during or after branching, which is confirmed by lab experiments. This indicates that the current inside a streamer discharges evolves approximately continuously during branching. On the other hand, stochastic fluctuations in streamer propagation due to Monte Carlo photoionization lead to more radio emission being emitted at frequencies of 100 MHz and above. Another process that leads to such high-frequency emission is the interaction of a streamer with a weakly preionized region, which can be present due to a previous discharge. In agreement with previous work, we observe the strongest and highest-frequency emission from streamer encounters. The amount of total energy that is radiated seems to depend primarily on the background electric field, and less on the particular streamer evolution. Finally, we present approximations for the maximal current along a streamer channel and a fit formula for a streamer's current moment.

The holographic duality conjectures a relation between strongly coupled quantum systems and quantum gravity in higher-dimensional spacetimes. Gravitational theories in two and three dimensions are meaningful examples for classical and quantum exploration due to their unique characteristics, notably the absence of propagating bulk degrees of freedom and the presence of only boundary degrees of freedom, distinguishing them from higher-dimensional counterparts. These gravitational theories exhibit complex interactions when the bulk spacetime has a finite size, regulated by Zamolodchikov's double-trace irrelevant $T\overline{T}$ operator. This thesis aims to gain a holographic understanding of $\mathrm{AdS}_3$ and JT gravity under the influence of the $T\overline{T}$ deformation. Under a finite radial cutoff, these theories exhibit perturbative behavior that implies the emergence of the Nambu-Goto action for the corresponding boundary graviton action. We also conducted semi-classical calculations of observables related to finite-cutoff gravity and its dual $T\overline{T}$-deformed CFT description, including correlation functions involving stress tensors and gravitational Wilson lines, along with an analysis of their supersymmetric extensions. Additionally, we explored the implications of general stress tensor deformations within field-theoretic and holographic settings. This thesis integrates previously adapted publications while also pioneering new ground, notably exploring the definition of a quantum $T\overline{T}$ operator beyond two dimensions with $\frac{1}{N}$ corrections, investigating quantum-corrected higher point correlators for a planar boundary, and offering insights into a two-dimensional spherical boundary at a finite cutoff. Furthermore, throughout the thesis, we show more details in calculations at various points., Comment: PhD thesis; 379 pages and appendices

We investigate the East-West asymmetry in energetic storm particle (ESP) heavy ion intensities at interplanetary shocks driven by coronal mass ejections (CMEs) during solar cycles (SCs) 23 and 24. We use observations from NASA's ACE and STEREO missions of helium (He), oxygen (O), and iron (Fe) intensities from ~0.13 to 3 MeV/nucleon. We examine the longitudinal distribution of ESP intensities and the correlation of ESP intensities with the near-Sun CME speed and the average transit CME speed for eastern and western events. We observed an East-West asymmetry reversal of ESP heavy ion intensities from SC 23 to 24. We have determined that this change in asymmetry is caused by a shift in the heliolongitude distribution of the CME speed ratio (the ratio of CME near-Sun speed to CME average transit speed) from west to east.

We study interacting theories of $N$ left-moving and $\overline{N}$ right-moving Floreanini-Jackiw bosons in two dimensions. A parameterized family of such theories is shown to enjoy (non-manifest) Lorentz invariance if and only if its Lagrangian obeys a flow equation driven by a function of the energy-momentum tensor. We discuss the canonical quantization of such theories along classical stress tensor flows, focusing on the case of the root-$T \overline{T}$ deformation, where we obtain perturbative results for the deformed spectrum in a certain large-momentum limit. In the special case $N = \overline{N}$, we consider the quantum effective action for the root-$T \overline{T}$-deformed theory by expanding around a general classical background, and we find that the one-loop contribution vanishes for backgrounds with constant scalar gradients. Our analysis can also be interpreted via dual $U(1)$ Chern-Simons theories in three dimensions, which might be used to describe deformations of charged $\mathrm{AdS}_3$ black holes or quantum Hall systems., Comment: 108 pages, LaTeX; v3: references added, version accepted for publication in PRD

For a bundle of oriented closed smooth $n$-manifolds $\pi: E \to X$, the tautological class $\kappa_{\mathcal{L}_k} (E) \in H^{4k-n}(X;\mathbb{Q})$ is defined by fibre integration of the Hirzebruch class $\mathcal{L}_k (T_v E)$ of the vertical tangent bundle. More generally, given a discrete group $G$, a class $u \in H^p(B G;\mathbb{Q})$ and a map $f:E \to B G$, one has tautological classes $\kappa_{\mathcal{L}_k ,u}(E,f) \in H^{4k+p-n}(X;\mathbb{Q})$ associated to the Novikov higher signatures. For odd $n$, it is well-known that $\kappa_{\mathcal{L}_k}(E)=0$ for all bundles with $n$-dimensional fibres. The aim of this note is to show that the question whether more generally $\kappa_{\mathcal{L}_k,u}(E,f)=0$ (for odd $n$) depends sensitively on the group $G$ and the class $u$. For example, given a nonzero cohomology class $u \in H^2 (B \pi_1 (\Sigma_g);\mathbb{Q})$ of a surface group, we show that always $\kappa_{\mathcal{L}_k,u}(E,f)=0$ if $g \geq 2$, whereas sometimes $\kappa_{\mathcal{L}_k,u}(E,f)\neq 0$ if $g=1$. The vanishing theorem is obtained by a generalization of the index-theoretic proof that $\kappa_{\mathcal{L}_k}(E)=0$, while the nontriviality theorem follows with little effort from the work of Galatius and Randal-Williams on diffeomorphism groups of even-dimensional manifolds., Comment: typos corrected