Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 1,099 records · Page 61

Unveiling the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear. We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for >700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits. While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R 2 (0.12–0.49, 0.15–0.42, and 0.25–0.56) and increased NRMSE (3.58–18.24%, 6.27–11.55%, and 7.0–33.12%) compared with nonspatial random cross-validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability. These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

59 BASIC BIOLOGICAL SCIENCES↗

LAFD: TA-3 NISC & SCC Facility Familiarization Tour, OJT #53356

Los Alamos National Laboratory (LANL, the Laboratory, or the Lab) conducts familiarization tours for Los Alamos County Fire Department (LAFD) personnel at the Strategic Computing Complex (SCC), TA-03-2327, and the Nonproliferation & International Security Complex (NISC), TA-03-2322. These tours are official LANL business; their purpose is to orient the firefighters to the SCC and the NISC so that they can respond efficiently and quickly to a variety of emergency situations. The tour includes ingress and egress of the buildings, layout and organization of the buildings, evacuation procedures, and areas of concern to emergency responders within these buildings. LAFD firefighters have the training, skills, and abilities to perform these emergency responder tasks; other LANL personnel who have the required clearance level cannot perform these tasks. This handout provides details of the information, along with maps and diagrams, to be presented during the familiarization tours. The report will be distributed to the trainees at the time of the tour. A corresponding checklist will also be used as guidance during the familiarization tours to ensure that all required information is presented to the LAFD personnel.

99 GENERAL AND MISCELLANEOUS↗

A Probabilistic Autoencoder for Type Ia Supernova Spectral Time Series

We construct a physically parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of Type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an autoencoder that is interpreted probabilistically after training using a normalizing flow. We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multistage training setup alongside our physically parameterized network, we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including the automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an rms of 0.091 ± 0.010 mag, which corresponds to 0.074 ± 0.010 mag if peculiar velocity contributions are removed.

79 ASTRONOMY AND ASTROPHYSICS↗

Spatially Distributed Ramp Reversal Memory in VO 2

Ramp‐reversal memory has recently been discovered in several insulator‐to‐metal transition materials where a non‐volatile resistance change can be set by repeatedly driving the material partway through the transition. This study uses optical microscopy to track the location and internal structure of accumulated memory as a thin film of VO 2 is temperature cycled through multiple training subloops. These measurements reveal that the gain of insulator phase fraction between consecutive subloops occurs primarily through front propagation at the insulator‐metal boundaries. By analyzing transition temperature maps, it is found, surprisingly, that the memory is also stored deep inside both insulating and metallic clusters throughout the entire sample, making the metal‐insulator coexistence landscape more rugged. This non‐volatile memory is reset after heating the sample to higher temperatures, as expected. Diffusion of point defects is proposed to account for the observed memory writing and subsequent erasing over the entire sample surface. By spatially mapping the location and character of non‐volatile memory encoding in VO 2 , this study results enable the targeting of specific local regions in the film where the full insulator‐to‐metal resistivity change can be harnessed in order to maximize the working range of memory elements for conventional and neuromorphic computing applications.

36 MATERIALS SCIENCE↗

An experimental comparison of triggered and random pulse train uncertainties

In this paper we present an experimental comparison of signal-triggered and randomly triggered based analysis algorithms of neutron multiplicity data. Traditional shift register type signal-triggered multiplicity analysis of singles, doubles and triples rates is compared with analysis using randomly triggered gates. Two methods of random gate generation are explored - non-overlapping gates (Feyrunan approach) and periodic overlapping gates (fast accidentals). Using californium sources with low, medium and high rate in combination with AmLi sources (as a surrogate for plutonium) we investigate relative standard deviation (RSD) of data in order to determine if there are parameter spaces in which one of the measurement methods should be preferred. Neutron correlation analysis is a commonly used NDA technique to assay plutonium mass. The data can be collected in two distinct ways: using signal-triggered or randomly triggered counting gates. Analysis algorithms were developed for both approaches to determine singles (S), doubles (D) and triples (7) rates from the measured sample. Currently the most commonly implemented technique to collect neutron coincidence data utilizes shift register based electronics. Shift register uses signal-triggered counting gates to generate foreground multiplicity distribution of correlated+accidental events and a random gate (opened after a predefined long delay following the signal trigger) to generate background multiplicity distribution of accidental events. Modern shift registers include fast accidental option to sample data with a fixed clock frequency. This way a set of overlapping gates is used to generate background multiplicity distributions in order to improve the measurement precision. In parallel to shift register approach the Feynman variance technique is frequently used, which utilizes set of consecutive non-overlapping gates. In general, different user communities (e.g. safeguards, nuclear material accountancy, emergency response) have used only one of the two analysis methods for the nuclear material assay. The aim of this study is to provide a systematic comparison of the precision of the measured S, D, T rates and {sup 240}Pu effective mass obtained using the above mentioned pulse train sampling techniques. In order to perform this task, a LANL developed list mode based data acquisition system is used, where the entire pulse train is recorded and subsequently analyzed. The list mode acquisition brings an essential advantage for this type of comparison, since the very same pulse train can be analyzed using signal-triggered as well as randomly triggered counting gates. The aim of this study is not only to compare the precision of signal-triggered versus random triggered sampling techniques, but also to investigate the influence of fast accidental sampling on the precision of signal-triggered results. In addition the different random sampling techniques used in safeguards are investigated. For this purpose we implement two types of random sampling - non-overlapping gates (Feynrnan approach) and periodic overlapping gates (fast accidentals). In the following sections the equations utilized in the pulse train analysis are described, experimental setup and measurement techniques are discussed and finally the results are summarized and discussed.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

An Overview of Issues Related to IEEE Std 1547-2018 Requirements Regarding Voltage and Reactive Power Control

The revised Institute of Electrical and Electronics Engineers (IEEE) 1547 Standard for Interconnection and Interoperability of Distributed Energy Resources with Associated Electric Power Systems Interfaces (IEEE Std 1547-2018) was published in April 2018. This standard is one of the foundational documents in the United States needed for integrating distributed energy resources (DERs), including solar energy systems, with the electric distribution grid. The revised standard contains 11 chapters (clauses) and 8 annexes that comprise 136 pages. The revision is significantly different from the 2003 version, and it contains new concepts and new technical requirements. Each clause specifies information or requirements that apply to certain aspects important to the interconnection of DERs to the electric power system. Implementing the requirements necessitates a careful study of the underlying technical concept and requires the appropriate information required to calculate relevant settings and configurations. Various stakeholders have different roles in implementing the standard, and portions of the standard are directed toward a specific audience who must possess specialized information and technical training to use and apply the requirements. This document aims to (1) summarize a specific portion of the standard as concisely as possible and (2) provide the reader with introductory knowledge and information to support the utilization of the requirements.

14 SOLAR ENERGY↗

Dispersal and fallout simulations for urban consequences management (u)

Hazardous chemical, biological, or radioactive releases from leaks, spills, fires, or blasts, may occur (intentionally or accidentally) in urban environments during warfare or as part of terrorist attacks on military bases or other facilities. The associated contaminant dispersion is complex and semi-chaotic. Urban predictive simulation capabilities can have direct impact in many threat-reduction areas of interest, including, urban sensor placement and threat analysis, contaminant transport (CT) effects on surrounding civilian population (dosages, evacuation, shelter-in-place), education and training of rescue teams and services. Detailed simulations for the various processes involved are in principle possible, but generally not fast. Predicting urban airflow accompanied by CT presents extremely challenging requirements. Crucial technical issues include, simulating turbulent fluid and particulate transport, initial and boundary condition modeling incorporating a consistent stratified urban boundary layer with realistic wind fluctuations, and post-processing of the simulation results for practical consequences management. Relevant fluid dynamic processes to be simulated include, detailed energetic and contaminant sources, complex building vortex shedding and flows in recirculation zones, and modeling of particle distributions, including particulate fallout, as well as deposition, re-suspension and evaporation. Other issues include, modeling building damage effects due to eventual blasts, addressing appropriate regional and atmospheric data reduction.

54 ENVIRONMENTAL SCIENCES↗

Scaling Deep Learning on GPU and Knights Landing clusters

The speed of deep neural networks training has become a big bottleneck of deep learning research and development. For example, training GoogleNet by ImageNet dataset on one Nvidia K20 GPU needs 21 days. To speed up the training process, the current deep learning systems heavily rely on the hardware accelerators. However, these accelerators have limited on-chip memory compared with CPUs. To handle large datasets, they need to fetch data from either CPU memory or remote processors. We use both self-hosted Intel Knights Landing (KNL) clusters and multi-GPU clusters as our target platforms. From an algorithm aspect, current distributed machine learning systems are mainly designed for cloud systems. These methods are asynchronous because of the slow network and high fault-tolerance requirement on cloud systems. We focus on Elastic Averaging SGD (EASGD) to design algorithms for HPC clusters. Original EASGD used round-robin method for communication and updating. The communication is ordered by the machine rank ID, which is inefficient on HPC clusters. First, we redesign four efficient algorithms for HPC systems to improve EASGD's poor scaling on clusters. Async EASGD, Async MEASGD, and Hogwild EASGD are faster \textcolor{black}{than} their existing counterparts (Async SGD, Async MSGD, and Hogwild SGD, resp.) in all the comparisons. Finally, we design Sync EASGD, which ties for the best performance among all the methods while being deterministic. In addition to the algorithmic improvements, we use some system-algorithm codesign techniques to scale up the algorithms. By reducing the percentage of communication from 87% to 14%, our Sync EASGD achieves 5.3x speedup over original EASGD on the same platform. We get 91.5% weak scaling efficiency on 4253 KNL cores, which is higher than the state-of-the-art implementation.

60 APPLIED LIFE SCIENCES↗

Machine Learning Augmented Predictive and Generative Model for Rupture Life in Ferritic and Austenitic Steels

The Larson-Miller parameter (LMP) offers an efficient and fast scheme to estimate the creep rupture life of alloy materials for high temperature applications. However, owing to poor generalizability and dependence on the constant C, which is typically not known a-priori, estimations using the Larson-Miller parameter often result in suboptimal performance for a wide range of materials. At best it is useful in comparing alloys of similar composition. In this work, three machine learning (ML) schemes were developed for rupture life prediction for 9-12% Cr ferritic-martensitic steels and austenitic stainless steels, i.e., a hierarchical model to parameterize LMP using the LMP constant C to compute rupture life, a hierarchical model to parameterize both C and LMP to compute rupture life, and a direct prediction of rupture life. Specifically, we show that the third scheme, using a gradient boosting algorithm, can be used to train ML models for very accurate prediction of rupture life in a variety of alloys (Pear-son Correlation Coefficient > 0.9 for 9-12% Cr and > 0.8 for austenitic stainless steels). In addition, the Shapley value was used to quantify feature importance, making the model interpretable by identifying the effect of various features on the model performance. Furthermore, a variational autoencoder-based generative model was built by conditioning on the experimental dataset to sample hypothetical synthetic candidate alloys from the learnt joint distribution not existing in both 9-12 % Cr ferritic-martensitic steel and austenitic stainless steel datasets. Finally, based on the predictive and generative model, a reinforcement learning strategy has been proposed to guide experimentalists into designing better heat resistant alloys.

Mamun, Md Osman G.↗

Results of the 2005-2008 Association of Residents in Radiation Oncology Survey of Chief Residents in the United States: Clinical Training and Resident Working Conditions

Purpose: To document clinical training and resident working conditions reported by chief residents during their residency. Methods and Materials: During the academic years 2005 to 2006, 2006 to 2007, and 2007 to 2008, the Association of Residents in Radiation Oncology conducted a nationwide survey of all radiation oncology chief residents in the United States. Chi-square statistics were used to assess changes in clinical training and resident working conditions over time. Results: Surveys were completed by representatives from 55 programs (response rate, 71.4%) in 2005 to 2006, 60 programs (75.9%) in 2006 to 2007, and 74 programs (93.7%) in 2007 to 2008. Nearly all chief residents reported receiving adequate clinical experience in commonly treated disease sites, such as breast and genitourinary malignancies; and commonly performed procedures, such as three-dimensional conformal radiotherapy and intensity-modulated radiotherapy. Clinical experience in extracranial stereotactic radiotherapy increased over time (p < 0.001), whereas clinical experience in endovascular brachytherapy (p <0.001) decreased over time. The distribution of gynecologic and prostate brachytherapy cases remained stable, while clinical case load in breast brachytherapy increased (p = 0.006). A small but significant percentage of residents reported receiving inadequate clinical experience in pediatrics, seeing 10 or fewer pediatric cases during the course of residency. Procedures involving higher capital costs, such as particle beam therapy and intraoperative radiotherapy, and infrequent clinical use, such as head and neck brachytherapy, were limited to a minority of institutions. Most residency programs associated with at least one satellite facility have incorporated resident rotations into their clinical training, and the majority of residents at these programs find them valuable experiences. The majority of residents reported working 60 or fewer hours per week on required clinical duties. Conclusions: Trends in clinical training and resident working conditions over 3 years are documented to allow residents and program directors to assess their residency training.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Pileup Mitigation with Machine Learning (PUMML)

Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Convolutional neural network identification of galaxy post-mergers in UNIONS using IllustrisTNG

ABSTRACT The Canada–France Imaging Survey (CFIS) will consist of deep, high-resolution r-band imaging over ∼5000 deg2 of the sky, representing a first-rate opportunity to identify recently merged galaxies. Because of the large number of galaxies in CFIS, we investigate the use of a convolutional neural network (CNN) for automated merger classification. Training samples of post-merger and isolated galaxy images are generated from the IllustrisTNG simulation processed with the observational realism code RealSim. The CNN’s overall classification accuracy is 88 per cent, remaining stable over a wide range of intrinsic and environmental parameters. We generate a mock galaxy survey from IllustrisTNG in order to explore the expected purity of post-merger samples identified by the CNN. Despite the CNN’s good performance in training, the intrinsic rarity of post-mergers leads to a sample that is only ∼6 per cent pure when the default decision threshold is used. We investigate trade-offs in purity and completeness with a variable decision threshold and find that we recover the statistical distribution of merger-induced star formation rate enhancements. Finally, the performance of the CNN is compared with both traditional automated methods and human classifiers. The CNN is shown to outperform Gini–M20 and asymmetry methods by an order of magnitude in post-merger sample purity on the mock survey data. Although the CNN outperforms the human classifiers on sample completeness, the purity of the post-merger sample identified by humans is frequently higher, indicating that a hybrid approach to classifications may be an effective solution to merger classifications in large surveys.

Bickley, Robert W.↗

Ensuring Workforce Readiness for the Energy Industry Through 3D Simulations

In February 2009, during his joint address to Congress, President Obama challenged every American to commit to at least one year of college education and set a goal that the United States should once again have the highest proportion of college graduates in the world by the year 2020. This push by the Obama administration reflected the understanding that while a college degree was becoming a prerequisite to obtain many of the jobs in the 21. century economy; the United States still lagged behind other countries with respect to higher education attainment. Because of this, the U.S. is facing a skills gap between the credentials required for the jobs of today and tomorrow, and the number of skilled workers eligible to fill those jobs. Within the energy industry, the skills gap is compounded by two factors: an expanding domestic industry in energy generation and transmission, and an aging workforce set to retire in large numbers. In fact, a 2013 survey administered by Center for Energy Workforce Development (CEWD) estimates that 36% of the workforce may need to be replaced in the next five years, and nearly 50% will need to be replaced by the year 2023. As a 2014 report by CEWD notes, 'The message for workforce development is clear: qualified and skilled utility technicians and engineers will continue to be in high demand in all types of energy generation, transmission, and distribution jobs'. Simulations provide students the ability to practice proper procedure in a safe environment, test out multiple scenarios to determine an optimal outcome, and repeat practice to solidify learning. Industry currently applies simulation (i.e., 3D Electrical Substation Simulation) as it affords an opportunity for technicians to train in a safe, virtual environment, thus eliminating risks associated with arc flash hazards. The intent of 3D simulation is to enhance the students' understanding of the concepts learned in the course and better prepare students for field work in a related technical discipline. The 3D simulation will reinforce the concepts learned during a specific course and are intended to add real world context to the curriculum. The 3D simulation will be designed such that a student will perform specific job activities incorporating concepts learned during the course. This method of instruction ensures students have an understanding of the concepts and are able to apply the concepts in a real world context. Different scenarios will be developed to ensure a thorough understanding of the concepts with real time feedback when there is a misunderstanding of the concepts. (authors)

97 MATHEMATICS AND COMPUTING↗

OVERVIEW OF THE COOPERATION BETWEEN THE CHERNOBYL CENTER'S INTERNATIONAL RADIOECOLOGY LABORATORY IN SLAVUTYCH, UKRAINE AND U.S. RESEARCH CENTERS BETWEEN 2000-2010

The International Radioecology Laboratory (IRL) located in Slavutych, Ukraine was created in 1999 under the initiative of the United States Government and the Government of Ukraine in the framework of international cooperation on evaluation and minimization of consequences of the Chernobyl nuclear power plant (ChNPP) accident. Since the time the IRL was founded, it has participated in a large number of projects, including the following: (1) study of radionuclide accumulation, distribution, and migration in components of various ecological systems of the Chernobyl Exclusion Zone (ChEZ); (2) radiation dose assessments; (3) study of the effects of radiation influence on biological systems; (4) expert analysis of isotopic and quantitative composition of radioactive contaminants; (5) development of new methods and technologies intended for radioecological research; (6) evaluation of future developments and pathways for potential remediation of the ChEZ areas; (7) assistance in provision of physical protection systems for ionizing irradiation sources at Ukrainian enterprises; (8) reviews of open Russian language publications on issues associated with consequences of the ChNPP accident, radioactive waste management, radioecological monitoring, and ChNPP decommissioning; (9) conduct of training courses on problems of radioecology, radiation safety, radioecological characterization of test sites and environmental media, and on research methods; (10) conduct of on-site scientific conferences and workshops on the ChEZ and radioecology problems; participation in off-site scientific conferences and meetings; and (11) preparation of scientific and popular science publications, and interactions with mass media representatives. This article provides a brief overview of the major achievements resulting from this cooperation between the IRL and U.S. research centers.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗

A statistical approach to combining multisource information in one-class classifiers

A new method is introduced in this paper for combining information from multiple sources to support one-class classification. The contributing sources may represent measurements taken by different sensors of the same physical entity, repeated measurements by a single sensor, or numerous features computed from a single measured image or signal. The approach utilizes the theory of statistical hypothesis testing, and applies Fisher's technique for combining p-values, modified to handle nonindependent sources. Classifier outputs take the form of fused p-values, which may be used to gauge the consistency of unknown entities with one or more class hypotheses. The approach enables rigorous assessment of classification uncertainties, and allows for traceability of classifier decisions back to the constituent sources, both of which are important for high-consequence decision support. Application of the technique is illustrated in two challenge problems, one for skin segmentation and the other for terrain labeling. Finally, the method is seen to be particularly effective for relatively small training samples.

97 MATHEMATICS AND COMPUTING↗

SAXS Assistant: Automated SAXS analysis for structural discovery in biologics and polymeric nanoparticles

Small-angle x-ray scattering (SAXS) is a powerful technique for assessing macromolecular structure. High-throughput SAXS is limited by the time-consuming and, at times, subjective nature of SAXS data interpretation. Here, we present SAXS Assistant, a Python-based script that streamlines SAXS data analysis to extract features for machine learning (ML) and key structural parameters, including the Guinier radius of gyration (R g ), pair distance distribution function (PDDF)-derived R g , maximum particle dimension (D max ), and Kratky plots. The script builds upon BioXTAS RAW and validates reliability via Guinier/PDDF R g agreement, an important indicator of well-measured data sets. For assistance in D max estimation, a multilayer perceptron regressor was trained with 1940 data files from the Small Angle Scattering Biological Data Bank. The model achieved a test set performance R 2 = 0.90 and mean absolute error = 11.7 Å. Training exclusively with experimental data translates analyses from researchers, including experts in the field, to the ML model, which helps assess D max estimations from PDDF. Gaussian mixture model clustering was implemented to classify profiles into structural classes based on entries in the Small Angle Scattering Biological Data Bank. Users may therefore assess the similarity between experimental samples and known biomolecular shapes within the mapped repository entries. This probabilistic clustering aids in quantifying information from Kratky and generating shape-descriptive features. SAXS Assistant accelerates SAXS data analysis through enforced quality control, ML-ready outputs, and flags for low-confidence results. In addition to providing the ability to analyze large data sets at high throughput, this tool is versatile and may serve researchers in both biological and synthetic polymer research fields.

36 MATERIALS SCIENCE↗

Insights into the origin of halo mass profiles from machine learning

ABSTRACT The mass distribution of dark matter haloes is the result of the hierarchical growth of initial density perturbations through mass accretion and mergers. We use an interpretable machine-learning framework to provide physical insights into the origin of the spherically-averaged mass profile of dark matter haloes. We train a gradient-boosted-trees algorithm to predict the final mass profiles of cluster-sized haloes, and measure the importance of the different inputs provided to the algorithm. We find two primary scales in the initial conditions (ICs) that impact the final mass profile: the density at approximately the scale of the haloes’ Lagrangian patch RL ($R\sim 0.7\, R_L$) and that in the large-scale environment (R ∼ 1.7 RL). The model also identifies three primary time-scales in the halo assembly history that affect the final profile: (i) the formation time of the virialized, collapsed material inside the halo, (ii) the dynamical time, which captures the dynamically unrelaxed, infalling component of the halo over its first orbit, (iii) a third, most recent time-scale, which captures the impact on the outer profile of recent massive merger events. While the inner profile retains memory of the ICs, this information alone is insufficient to yield accurate predictions for the outer profile. As we add information about the haloes’ mass accretion history, we find a significant improvement in the predicted profiles at all radii. Our machine-learning framework provides novel insights into the role of the ICs and the mass assembly history in determining the final mass profile of cluster-sized haloes.

79 ASTRONOMY AND ASTROPHYSICS↗