Search NASA⌕ Search

SEARCH · Search NASA

Results for “anomaly localization”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6

Simultaneous Development of Antiferromagnetism and Local Symmetry Breaking in a Kagome Magnet (Co 0.45 Fe 0.55 )Sn

CoSn and FeSn, two kagome-lattice metals, have recently attracted significant attention as hosts of electronic flat bands and emergent physical properties. However, current understandings of their physical properties are limited to knowledge of the average crystal structure. Here, we report the Fe-doping induced coemergence of the antiferromagentic (AFM) order and local symmetry breaking in (Co 0.45 Fe 0.55 )Sn. Rietveld analysis on the neutron and synchrotron X-ray diffraction data indicates A-type antiferromagnetic order with the moment pointing perpendicular to the kagome layers, associated with the anomaly in the MSn(1) 2 Sn(2) 4 (M = Co/Fe) octahedral distortion and the lattice constant c. Reverse Monte Carlo (RMC) modeling of the synchrotron X-ray total scattering results captured the subtle local orthorhombic distortion involving off-axis displacements of Sn(2). Our results indicate that the stable hexagonal lattice above T N becomes unstable once the A-type AFM order is formed below T N . Here we argue that the local symmetry breaking has a magnetic origin, since the spatially varied M–Sn(2) bond lengths arise from out-of-plane magnetic exchange coupling J c via the exchange pathway M–Sn(2)–M. Our study provides comprehensive information on the crystal structure in both long-range scale and local scale, unveiling unique coupling between AFM order, octahedral distortion, and hidden local symmetry breaking.

36 MATERIALS SCIENCE↗

Weather Systems Connecting Modes of Climate Variability to Regional Hydroclimate Extremes

Abstract Weather system clustering provides a high‐level summary of regional meteorological conditions. Most quantitative clustering schemes focus on precipitation alone, which does not sufficiently describe the meteorological conditions driving hydroclimate variability. This study presents the Weather Anomaly Clustering (WAC‐hydro), which extends the existing capability of predicting weather systems to predicting hydroclimate variability. Focusing on both precipitation and temperature predictions, WAC‐hydro identifies 12 clusters of daily weather anomaly modes in the US Pacific Northwest Puget Sound region during 1981–2020. The influence of El Niño‐Southern Oscillation and Madden‐Julian Oscillation on regional precipitation can be well approximated by their modulation on the weather clusters. Within each weather cluster, local factors such as topography only play a secondary role in the hydrologic variability. The weather clusters highlight two types of flood‐inducing regional weather conditions, one causing floods by inducing positive precipitation anomalies and the other causing floods through combined precipitation and temperature‐induced rain‐on‐snow effect.

54 ENVIRONMENTAL SCIENCES↗

A Cyber-Physical Anomaly Detection for Wide-Area Protection Using Machine Learning

Wide-area protection scheme (WAPS) provides system-wide protection by detecting and mitigating small and large-scale disturbances that are difficult to resolve using local protection schemes. As this protection scheme is evolving from a substation-based distributed remedial action scheme (DRAS) to the control center-based centralized RAS (CRAS), it presents severe challenges to their cybersecurity because of its heavy reliance on an insecure grid communication, and its compromise would lead to system failure. This article presents an architecture and methodology for developing a cyber-physical anomaly detection system (CPADS) that utilizes synchrophasor measurements and properties of network packets to detect data integrity and communication failure attacks on measurement and control signals in CRAS. The proposed machine leaning-based methodology applies a rules-based approach to select relevant input features, utilizes variational mode decomposition (VMD) and decision tree (DT) algorithms to develop multiple classification models, and performs final event identification using a rules-based decision logic. Here, we have evaluated the proposed methodology of CPADS using the IEEE 39 bus system for several performance measures (accuracy, recall, precision, and F-measure) in a cyber-physical testbed environment. Furthermore, our experimental results reveal that the proposed algorithm (VMD-DT) of CPADS outperforms the existing machine learning classifiers during noisy and noise-free measurements while incurring an acceptable processing overhead.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Emergence of Local Magnetic Moment in Ternary TaWSe 2 Single Crystal via Atomic Clustering

Ternary transition metal dichalcogenides (TMDs) provide a versatile platform to explore novel electronic and magnetic ground states via compositional substitution and local structural modulations. Using a combination of scanning tunneling microscopy and spectroscopy (STM/S), magnetic property measurements, and density functional theory (DFT) calculations, the emergence of local magnetic moments driven by the clustering of Ta atoms in ternary TaWSe 2 single crystals is analyzed. STM topography reveals triangular clusters of Ta atoms embedded within W-rich regions of TaWSe 2 . These clusters exhibit a consistent shape and an orderly arrangement throughout the surfaces. DFT calculations show that these Ta clusters induce local strain, giving rise to localized magnetic moments. The magnetic behavior is further corroborated by temperature-dependent magnetization measurements, which exhibit a magnetic anomaly at ∼50 K. In conclusion, this study offers a pathway to engineer magnetism in TMD systems with potential applications in spintronic and quantum materials.

DFT↗

Reaching percolation and conformal limits in neutron stars

Generating an ensemble of equations of state that fulfill multimessenger constraints, we statistically determine the properties of dense matter found inside neutron stars (NSs). We calculate the speed of sound and trace anomaly and demonstrate that they are driven towards their conformal values at the center of maximally massive NSs. The local peak of the speed of sound is shown to be located at values of the energy and particle densities, which are consistent with deconfinement and percolation conditions in QCD matter. Here, we also analyze fluctuations of the net-baryon number density in the context of possible remnants of critical behavior. We find that the global maxima of the variance of these fluctuations emerge at densities beyond those found in the interiors of NSs.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep medical image analysis with representation learning and neuromorphic computing

Deep learning is increasingly used in medical imaging, improving many steps of the processing chain, from acquisition to segmentation and anomaly detection to outcome prediction. Yet significant challenges remain: (i) image-based diagnosis depends on the spatial relationships between local patterns, something convolution and pooling often do not capture adequately; (ii) data augmentation, the de facto method for learning three-dimensional pose invariance, requires exponentially many points to achieve robust improvement; (iii) labelled medical images are much less abundant than unlabelled ones, especially for heterogeneous pathological cases; and (iv) scanning technologies such as magnetic resonance imaging can be slow and costly, generally without online learning abilities to focus on regions of clinical interest. To address these challenges, novel algorithmic and hardware approaches are needed for deep learning to reach its full potential in medical imaging.

60 APPLIED LIFE SCIENCES↗

Background Adaptive Radiation Detection (BARD) v1.0.0

The Background Adaptive Radiation Software can be deployed with static sensors in urban environments. It provides a real-time robust radiation detection based on a unique adaptive learning approach. Local radiation background models are automatically learnt for various environmental conditions, and monitored/re-trained, and selected over time for optimal radiation anomaly detection, informed by source templates directly derived from the data.

Abgrall, Nicolas↗

Idaho National Laboratory Integrated Multisite SSHAC Level 3: Probabilistic Volcanic Hazards Assessment

The Idaho National Laboratory (INL) resides on the eastern Snake River Plain (ESRP), part of the Snake River Plain (SRP) with a complex origin and geologic history of volcanism. Much of the Quaternary (last 2.58 million years) volcanism within 400 km of INL is genetically associated with a major thermal anomaly referred to as the Yellowstone hotspot, which is currently located more than 180 km northeast of INL. Near INL, local volcanic sources include silicic domes near its southern border, and numerous dike-fed basaltic vents of the ESRP, some of which are near or within the INL boundaries. Quantitative probabilistic assessments of screened-in volcanic hazardous phenomena for nine different facility complexes at the INL are presented for a Senior Seismic Hazard Analysis Committee (SSHAC) Level 3 (SL3) study. The comprehensive, integrated multisite SSHAC study consists of a single regional Probabilistic Volcanic Hazards Assessment (PVHA) that pertains to all nine INL facility complexes, with site-specific information developed at each respective area of interest (AOI), referred to as the "INL facility AOI" (Figure ES-1). Hazard products are generated for specified INL facility AOIs for use by multiple stakeholders from different agencies in risk-informed decision-making regarding site selection, operations, and design of nuclear facilities at INL, consistent with U.S. Department of Energy (DOE) and U.S. Nuclear Regulatory Commission (NRC) regulatory guidance. The study also serves as the basis for future periodic safety assessments required for existing DOE facilities, such as 10-year evaluations of natural-phenomena hazards. Elements of the INL PVHA including initial characterization, screening, quantitative assessments of eruption and hazard potential, and consideration of facility needs are conducted using the three phases of the SSHAC process: evaluation, integration, and documentation. As per regulatory guidance, the SSHAC framework provided the necessary processes and procedures for the PVHA Technical Integration (TI) team, at three workshops, five formal working meetings and many TI team remote meetings, to conduct initial characterization, screen the volcanic hazards, create PVHA model inputs, exercise those models in the PVHA, consider facility-specific volcanic hazard needs, and perform final hazard calculations. The Participatory Peer Review Panel (PPRP) provided independent oversight and performed process and technical reviews of the PVHA throughout its duration. The study included an extensive New Data Collection and Analyses (NDCA) program developed by the PVHA TI team to reduce uncertainties in hazard-significant elements in the PVHA model. NDCA activities generated 20 reports providing important contributory datasets and results to the project database for characterizing the ESRP. For example, a report compiling the dimensions of ESRP shield volcanoes and lava fields was used to construct volcanic footprints (areas of impact), was compared with data from INL subsurface cores, and was used to validate the results of lava-flow inundation modeling on the contemporary terrain. Another example is the acquisition of aeromagnetic data over INL and its surrounding area, with maps of buried magmatic features (e.g., subsurface volcanoes and swarms of feeder dikes) that informed the PVHA conceptual model of volcanism. The SSHAC evaluation process was used to conduct all elements of the PVHA including initial characterization and screening. Existing data and NDCA activities provided the foundation to develop the tectonomagmatic conceptual model of volcanism for the region of geographical interest in the SRP and Yellowstone hotspot volcanic system, and for considering volcanoes in the western US. Considering Quaternary volcanic sources active during this period, the screening approach identified and evaluated magma compositions, types of eruptive and intrusive phenomena, types of hazardous phenomena, and proximity of sources to INL. The PVHA TI team evaluated 18 types of magmatic sources in terms of 20 potentially hazardous phenomena, resulting in 360 screening decisions. The screening process resulted in 140 screened-in hazardous volcanic phenomena for Quaternary volcanic sources 1) proximal to INL facility complexes in the ESRP (64 basaltic and 54 silicic), 2) regional sources associated with the Yellowstone caldera system and Blackfoot Reservoir volcanic field (7), and 3) more distal sources from thirteen Cascade volcanoes and two volcanoes at Long Valley caldera (CA).

58 GEOSCIENCES↗

Discovering Blind Geothermal Systems in the Great Basin Region: An Integrated Geologic and Geophysical Approach for Establishing Geothermal Play Fairways: All Phases

Most geothermal resources in the Great Basin region of the western USA are blind, and thus the discovery of new commercial-grade systems requires synthesis of favorable characteristics for geothermal activity. The geothermal play fairway concept involves integration of multiple parameters indicative of geothermal activity to identify promising areas for new development. This project integrated multiple datasets to apply the play fairway concept and assess geothermal potential in a large region of the Great Basin in Nevada. It is therefore referred to as the Nevada play fairway project. This project was a strong collaborative effort between several organizations, led by the Nevada Bureau of Mines and Geology at the University of Nevada, Reno, but with key support from the U.S. Geological Survey, ATLAS Geosciences, Inc,, Hi-Q Geophysical, Inc., Lawrence Berkeley National Laboratory, Utah Geological Survey, and Innovative Geothermal Ltd. In Budget Period 1 of this project, available data for nine geologic, geochemical, and geophysical parameters were initially synthesized to produce a new detailed geothermal potential map of 96,000 km2 from west-central to eastern Nevada. These parameters were grouped into subsets and individually weighted to delineate rankings for local permeability, intermediate permeability, regional permeability, and thermal potential, which collectively defined geothermal play fairways (i.e., most likely locations for significant geothermal fluid flow). This initial work was aimed at reducing the risks in regional exploration and therefore facilitating discovery of new commercial-grade systems in blind settings, as well as in areas with surface expressions of geothermal activity. Budget Period 2 of the project involved detailed analysis of some of the most promising areas identified in Phase 1. Twenty-four highly prospective areas, including both known undeveloped systems and previously undiscovered potential blind systems, were identified for further analysis. After reconnaissance of these areas, five of the most promising sites were selected for detailed studies. Multiple techniques were employed in the detailed studies, including geologic mapping, shallow temperature surveys, gravity surveys, Lidar, geochemical studies, seismic reflection analysis, and 3D modeling. The goal of the detailed studies was to identify specific areas with the highest likelihood for high permeability and thermal fluids, such that drill sites could be targeted. Three main sets of predictive maps were generated for each detailed study area: 1) play fairway maps, 2) play fairway error maps, and 3) direct evidence maps. Local- and intermediate-scale permeability models were revised to reflect results of the detailed geologic, geophysical, and geochemical analyses. Budget Period 3 of the project involved more detailed geophysical analyses and temperature-gradient (TG) drilling in southeastern Gabbs Valley and northern Granite Springs Valley, deemed the two most promising sites, with the goal of providing preliminary validation of the play fairway methodology. In southeastern Gabbs Valley, the collocation of a favorable structural setting (displacement transfer zone and fault intersections), Quaternary faults, intersecting and terminating gravity gradients, magnetic low, shallow (2 m) temperature anomaly, low resistivity anomaly, and promising geothermometry from nearby water wells provided evidence for a blind system. Drilling of six TG holes defines an apparent geothermal system at this locality with temperatures as high as 124°C at 152 m. This system is blind, with no surface hot springs, fumaroles, or paleo-geothermal deposits. For northern Granite Springs Valley, a favorable structural setting (termination of a major Quaternary normal fault), terminating gravity gradient, magnetic gradient, newly discovered sinter deposits, nearby warm water wells, previously drilled TG holes in the vicinity, and promising geothermometry suggest a hidden system. Drilling of six new TG holes yields temperatures of ~96°C at ~250 m, suggesting the presence of a geothermal system. Major lessons learned in the course of this project include: 1) initially identified sites commonly include multiple favorable structural settings at a finer scale; 2) promising sites in Cenozoic basins cannot be recognized without detailed geophysical surveys; and 3) play fairway analysis should be refined as the exploration program vectors into the most promising sites and finer-scale data are acquired. In addition to producing copious amounts of data, this project resulted in 16 published papers, 10 abstracts, more than 40 presentations across the U.S. and abroad (including several keynote addresses), 2 Masters theses, and 7 media reports.

15 GEOTHERMAL ENERGY↗

Cy-Phy ADS: Cyber Physical Anomaly Detection Framework for EV Charging Systems

Today’s large-scale Electric Vehicle (EV) infrastructures are heavily dependent on information communication technologies to maintain their operation and to support communication within sub-system components as well as the outside world. These technologies are vulnerable to various cyber and physical threats. Timely identification and mitigation of these threats are critical for improving human safety, avoiding economic losses, and preventing catastrophic system failures. By addressing this, our work presents a ResNet Autoencoder (AE) based Cyber-Physical Anomaly Detection System (Cy-Phy ADS) for detecting anomalies in EV Controller Area Network (CAN) protocol communication. It consists of four main components: Cyber-Physical Feature Extractor, ResNet AE-based Anomaly Detection Framework, Cyber-Physical Health Metric (CPHM), and Visualization Dashboard. The presented framework was trained and tested using CAN data collected from the EV charging system testbed at the Idaho National Laboratory. The presented Cy-Phy ADS compared against six widely used unsupervised anomaly detection algorithms: One Class Support Vector Machine (OCSVM), Variational Autoencoder (VAE), LSTM Autoencoder (LSTM AE), Isolation Forest (IForest), Principle Component Analysis (PCA) and Local Outlier Factor (LOF). Here the presented approach showed the highest accuracy among the compared methods. Further, the proposed approach showed comparable performance in terms of precision, F1, and False positive rate. It also showed the lowest training and inference time compared to the neural network-based baseline algorithms compared against with. Additionally, the Cy-Phy ADS has advantages such as unsupervised training, the ability to provide a holistic metric for system health characterization, and non-linear feature extraction.

99 GENERAL AND MISCELLANEOUS↗

Celestial holography meets twisted holography: 4d amplitudes from chiral correlators

We propose a new program for computing a certain integrand of scattering amplitudes of four-dimensional gauge theories which we call the form factor integrand, starting from 6d holomorphic theories on twistor space. We show that the form factor integrands can be expressed as sums of products of 1.) correlators of a 2d chiral algebra, related to the algebra of asymptotic symmetries uncovered recently in the celestial holography program, and 2.) OPE coefficients of a 4d non-unitary CFT. We prove that conformal blocks of the chiral algebras are in one-to-one correspondence with local operators in 4d. We use this bijection to recover the Parke-Taylor formula, the CSW formula, and certain one-loop scattering amplitudes. Along the way, we explain and derive various aspects of celestial holography, incorporating techniques from the twisted holography program such as Koszul duality. This perspective allows us to easily and efficiently recover the infinite-dimensional chiral algebras of asymptotic symmetries recently extracted from scattering amplitudes of massless gluons and gravitons in the celestial basis. We also compute some simple one-loop corrections to the chiral algebras and derive the three-dimensional bulk theories for which these 2d algebras furnish an algebra of boundary local operators.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Generalized global symmetries of T[ M ] theories. Part I

We study reductions of 6d theories on a d-dimensional manifold Md, focusing on the interplay between symmetries, anomalies, and dynamics of the resulting (6 – d)-dimensional theory T[M d ]. We refine and generalize the notion of “polarization” to polarization on Md, which serves to fix the spectrum of local and extended operators in T[M d ]. Another important feature of theories T[M d ] is that they often possess higher-group symmetries, such as 2-group and 3-group symmetries. We study the origin of such symmetries as well as physical implications including symmetry breaking and symmetry enhancement in the renormalization group flow. To better probe the IR physics, we also investigate the ’t Hooft anomaly of 5d Chern-Simons matter theories. The present paper focuses on developing the general framework as well as the special case of d = 0 and 1, while an upcoming paper will discuss the case of d = 2, 3 and 4.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Influence of sea-ice anomalies on Antarctic precipitation using source attribution in the Community Earth System Model

Abstract. We conduct sensitivity experiments using a general circulation model that has an explicit water source tagging capability forced by prescribed composites of pre-industrial sea-ice concentrations (SICs) and corresponding sea surface temperatures (SSTs) to understand the impact of sea-ice anomalies on regional evaporation, moisture transport and source–receptor relationships for Antarctic precipitation in the absence of anthropogenic forcing. Surface sensible heat fluxes, evaporation and column-integrated water vapor are larger over Southern Ocean (SO) areas with lower SICs. Changes in Antarctic precipitation and its source attribution with SICs have a strong spatial variability. Among the tagged source regions, the Southern Ocean (south of 50° S) contributes the most (40 %) to the Antarctic total precipitation, followed by more northerly ocean basins, most notably the South Pacific Ocean (27%), southern Indian Ocean (16 %) and South Atlantic Ocean (11 %). Comparing two experiments prescribed with high and low pre-industrial SICs, respectively, the annual mean Antarctic precipitation is about 150 Gt yr-1 (or 6 %) more in the lower SIC case than in the higher SIC case. This difference is larger than the model-simulated interannual variability in Antarctic precipitation (99 Gt yr-1). The contrast in contribution from the Southern Ocean, 102 Gt yr-1, is even more significant compared to the interannual variability of 35 Gt yr-1 in Antarctic precipitation that originates from the Southern Ocean. The horizontal transport pathways from individual vapor source regions to Antarctica are largely determined by large-scale atmospheric circulation patterns. Vapor from lower-latitude source regions takes elevated pathways to Antarctica. In contrast, vapor from the Southern Ocean moves southward within the lower troposphere to the Antarctic continent along moist isentropes that are largely shaped by local ambient conditions and coastal topography. This study also highlights the importance of atmospheric dynamics in affecting the thermodynamic impact of sea-ice anomalies associated with natural variability on Antarctic precipitation. Our analyses of the seasonal contrast in changes of basin-scale evaporation, moisture flux and precipitation suggest that the impact of SIC anomalies on regional Antarctic precipitation depends on dynamic changes that arise from SIC–SST perturbations along with internal variability. The latter appears to have a more significant effect on the moisture transport in austral winter than in summer.

54 ENVIRONMENTAL SCIENCES↗

Heat capacity and thermodynamic functions of transition metal ion (Cu 2+ , Fe 2+ , Mn 2+ ) exchanged, partially dehydrated zeolite $\mathrm{A}$ ($\mathrm{LTA}$)

Here we have measured the heat capacity from 1.8 to 300 K of partially dehydrated zeolite A (LTA), fully exchanged with Cu 2+ , Fe 2+ , and Mn 2+ ions. The samples have a broad excess heat capacity contribution centered around 4 K, which we attribute to local electric fields splitting the magnetic moments of the cations. The excess heat capacity is modelled using a sum of several Schottky anomalies. From these models, we conclude that the cations in the Cu 2+ zeolite reside in at least four distinct coordination environments, and that some of the coordination environments in all three zeolites are highly asymmetric. We also report theoretical fits of the heat capacity data, and values of the standard thermodynamic functions C P,m , Δ 0K T S m ° , Δ 0K T H m ° , and Φ m ° at smooth temperatures. The standard molar entropies at 298.15 K are 71.8 J·K -1 ·mol -1 for Cu-zeolite A (Cu 0.22 Al 0.49 Si 0.51 O 2 1.04 H 2 O), 71.1 J·K -1 ·mol -1 for Fe-zeolite A (Na 0.01 Fe 0.23 Al 0.50 Si 0.51 O 2 ∙0.77 H 2 O), and 66.0 J·K -1 ·mol -1 for Mn-zeolite A (Mn 0.26 Al 0.49 Si 0.50 O 2 ∙0.53 H 2 O).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Data-driven and model-agnostic approach to solving combinatorial assignment problems in searches for new physics

We present a novel approach to solving combinatorial assignment problems in particle physics. The correct assignment of decay products to parent particles is achieved in a model-agnostic fashion by introducing a neural network architecture, asswd-, which combines a custom layer based on attention mechanisms and dual autoencoders. We demonstrate how the network, trained purely on background events in an unsupervised setting, is capable of reconstructing correctly hypothetical new particles regardless of their mass, decay multiplicity, and substructure, and produces simultaneously an anomaly score that can be used to efficiently suppress the background. This model allows the extension of the suite of searches for localized excesses to include nonresonant particle pair production where the reconstruction of the two resonant masses is thwarted by combinatorics. Published by the American Physical Society 2024

Astronomy & Astrophysics↗

Understanding Predictability of Daily Southeast U.S. Precipitation Using Explainable Machine Learning

Abstract We investigate the predictability of the sign of daily southeastern U.S. (SEUS) precipitation anomalies associated with simultaneous predictors of large-scale climate variability using machine learning models. Models using index-based climate predictors and gridded fields of large-scale circulation as predictors are utilized. Logistic regression (LR) and fully connected neural networks using indices of climate phenomena as predictors produce neither accurate nor reliable predictions, indicating that the indices themselves are not good predictors. Using gridded fields as predictors, an LR and convolutional neural network (CNN) are more accurate than the index-based models. However, only the CNN can produce reliable predictions that can be used to identify forecasts of opportunity. Using explainable machine learning we identify which variables and grid points of the input fields are most relevant for confident and correct predictions in the CNN. Our results show that the local circulation is most important as represented by maximum relevance of 850-hPa geopotential heights and zonal winds to making skillful, high-probability predictions. Corresponding composite anomalies identify connections with El Niño–Southern Oscillation during winter and the Atlantic multidecadal oscillation and North Atlantic subtropical high during summer.

Pegion, Kathy↗

Predicting September Arctic Sea Ice: A Multimodel Seasonal Skill Comparison

This study quantifies the state of the art in the rapidly growing field of seasonal Arctic sea ice prediction. A novel multimodel dataset of retrospective seasonal predictions of September Arctic sea ice is created and analyzed, consisting of community contributions from 17 statistical models and 17 dynamical models. Prediction skill is compared over the period 2001–20 for predictions of pan-Arctic sea ice extent (SIE), regional SIE, and local sea ice concentration (SIC) initialized on 1 June, 1 July, 1 August, and 1 September. This diverse set of statistical and dynamical models can individually predict linearly detrended pan-Arctic SIE anomalies with skill, and a multimodel median prediction has correlation coefficients of 0.79, 0.86, 0.92, and 0.99 at these respective initialization times. Regional SIE predictions have similar skill to pan-Arctic predictions in the Alaskan and Siberian regions, whereas regional skill is lower in the Canadian, Atlantic, and central Arctic sectors. The skill of dynamical and statistical models is generally comparable for pan-Arctic SIE, whereas dynamical models outperform their statistical counterparts for regional and local predictions. The prediction systems are found to provide the most value added relative to basic reference forecasts in the extreme SIE years of 1996, 2007, and 2012. SIE prediction errors do not show clear trends over time, suggesting that there has been minimal change in inherent sea ice predictability over the satellite era. Overall, this study demonstrates that there are bright prospects for skillful operational predictions of September sea ice at least 3 months in advance.

54 ENVIRONMENTAL SCIENCES↗

Enhancing Network Anomaly Detection Using Graph Neural Networks

In the world of Internet of Things (IoT) networks, where devices are constantly communicating, keeping them secure from cyber threats is critical. This paper introduces a novel approach to detecting unusual and potentially harmful activities in these networks using graph neural networks (GNNs). We combine two specific types of GNNs-GraphSAGE and graph attention networks (GAT)-to create a model that understands and represents the behaviors and interactions in a network. GraphSAGE creates an embedding of network activities by examining local data interactions, while GAT directs the model's focus to the most critical interactions. By integrating these two methods in a single model that considers different types of interactions (both host and flow nodes), we aim to create a system that accurately represents the current state of a network and can also spot anomalies effectively while reducing false positives and negatives. Our innovative approach has demonstrated promising results, achieving an accuracy of 98% on the UNSW-NB15 dataset, significantly outperforming standalone GraphSAGE and GAT models. This underscores its potential as a robust framework for securing IoT networks against cyber threats and anomalies.

Marfo, William↗