Search NASA⌕ Search

SEARCH · Search NASA

Results for “Ensemble computing.”

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 1,495 records · Page 83

Causes and Implications of Persistent Atmospheric Carbon Dioxide Biases in Earth System Models

The strength of feedbacks between a changing climate and future CO2 concentrations are uncertain and difficult to predict using Earth System Models (ESMs). We analyzed emission-driven simulations--in which atmospheric CO2 levels were computed prognostically--for historical (1850-2005) and future periods (RCP 8.5 for 2006-2100) produced by 15 ESMs for the Fifth Phase of the Coupled Model Intercomparison Project (CMIP5). Comparison of ESM prognostic atmospheric CO2 over the historical period with observations indicated that ESMs, on average, had a small positive bias in predictions of contemporary atmospheric CO2. Weak ocean carbon uptake in many ESMs contributed to this bias, based on comparisons with observations of ocean and atmospheric anthropogenic carbon inventories. We found a significant linear relationship between contemporary atmospheric CO2 biases and future CO2 levels for the multi-model ensemble. We used this relationship to create a contemporary CO2 tuned model (CCTM) estimate of the atmospheric CO2 trajectory for the 21st century. The CCTM yielded CO2 estimates of 600 {plus minus} 14 ppm at 2060 and 947 {plus minus} 35 ppm at 2100, which were 21 ppm and 32 ppm below the multi-model mean during these two time periods. Using this emergent constraint approach, the likely ranges of future atmospheric CO2, CO2-induced radiative forcing, and CO2-induced temperature increases for the RCP 8.5 scenario were considerably narrowed compared to estimates from the full ESM ensemble. Our analysis provided evidence that much of the model-to-model variation in projected CO2 during the 21st century was tied to biases that existed during the observational era, and that model differences in the representation of concentration-carbon feedbacks and other slowly changing carbon cycle processes appear to be the primary driver of this variability. By improving models to more closely match the long-term time series of CO2 from Mauna Loa, our analysis suggests uncertainties in future climate projections can be reduced.

Hoffman, Forrest M↗

Evaluation of two-particle properties within finite-temperature self-consistent one-particle Green’s function methods: Theory and application to GW and GF2

One-particle Green’s function methods can model molecular and solid spectra at zero or non-zero temperatures. One-particle Green’s functions directly provide electronic energies and one-particle properties, such as dipole moment. However, the evaluation of two-particle properties, such as $\langle$S 2 $\rangle$ and $\langle$N 2 $\rangle$, can be challenging because they require a solution of the computationally expensive Bethe–Salpeter equation to find two-particle Green’s functions. We demonstrate that the solution of the Bethe–Salpeter equation can be completely avoided. Applying the thermodynamic Hellmann–Feynman theorem to self-consistent one-particle Green’s function methods, we derive expressions for two-particle density matrices in a general case and provide explicit expressions for GF2 and GW methods. Such density matrices can be decomposed into an antisymmetrized product of correlated one-electron density matrices and the two-particle electronic cumulant of the density matrix. Cumulant expressions reveal a deviation from ensemble representability for GW, explaining its known deficiencies. We analyze the temperature dependence of $\langle$S 2 $\rangle$ and $\langle$N 2 $\rangle$ for a set of small closed-shell systems. Interestingly, both GF2 and GW show a non-zero spin contamination and a non-zero fluctuation of the number of particles for closed-shell systems at the zero-temperature limit.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

High Frequency QPOs due to Black Hole Spin

We present detailed computations of photon orbits emitted by flares at the innermost stable circular orbit (ISCO) of accretion disks around rotating black holes. We show that for sufficiently large spin parameter, i.e. a > 0.94 M, flare a sufficient number of photons arrive at an observer after multiple orbits around the black hole, to produce an "photon echo" of constant lag, i.e. independent of the relative phase between the black hole and the observer, of T approximates 14 M. This constant time delay, then, leads to a power spectrum with a QPO at a frequency nu approximates 1/14M, even for a totally random ensemble of such flares. Observation of such a QPO will provide incontrovertible evidence for the high spin of the black hole and a very accurate, independent, measurement of its mass.

Kazanas, Demos↗

Sequential ensemble transform for Bayesian inverse problems

In this work, we present the Sequential Ensemble Transform (SET) method, an approach for generating approximate samples from a Bayesian posterior distribution. The method explores the posterior distribution by solving a sequence of discrete optimal transport problems to produce a series of transport plans which map prior samples to posterior samples. We prove that the sequence of Dirac mixture distributions produced by the SET method converges weakly to the true posterior as the sample size approaches infinity. Furthermore, our numerical results indicate that, when compared to standard Sequential Monte Carlo (SMC) methods, the SET approach is more robust to the choice of Markov mutation kernels and requires less computational efforts to reach a similar accuracy when used to explore complex posterior distributions. Finally, we describe adaptive schemes that allow to completely automate the use of the SET method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Mechanism and kinetics of peptide partitioning into membranes

Partitioning properties of transmembrane (TM) polypeptide segments directly determine membrane protein folding, stability, and function, and their understanding is vital for rational design of membrane active peptides. However, direct determination of water-to-bilayer transfer of TM peptides has proved difficult. Experimentally, sufficiently hydrophobic peptides tend to aggregate, while atomistic computer simulations at physiological temperatures cannot yet reach the long time scales required to capture partitioning. Elevating temperatures to accelerate the dynamics has been avoided, as this was thought to lead to rapid denaturing. However, we show here that model TM peptides (WALP) are exceptionally thermostable. Circular dichroism experiments reveal that the peptides remain inserted into the lipid bilayer and are fully helical, even at 90 C. At these temperatures, sampling is 50 500 times faster, sufficient to directly simulate spontaneous partitioning at atomic resolution. A folded insertion pathway is observed, consistent with three-stage partitioning theory. Elevated temperature simulation ensembles further allow the direct calculation of the insertion kinetics, which is found to be first-order for all systems. Insertion barriers are Hin = 15 kcal/mol for a general hydrophobic peptide and 23 kcal/mol for the tryptophan-flanked WALP peptides. The corresponding insertion times at room temperature range from 8.5 s to 163 ms. High-temperature simulations of experimentally validated thermostable systems suggest a new avenue for systematic exploration of peptide partitioning properties.

59 BASIC BIOLOGICAL SCIENCES↗

Mountain Basin Controls on the Snow-to-Streamflow Signal: An AIC-Weighted Multiple Linear Regression Framework

A regression-based analysis quantifies how basin characteristics modulate the snow-to-streamflow signal. First, we use the ERA5-Land reanalysis gridded product (European Centre for Medium Range Weather Forecasts reanalysis 5 -Land component) for 4,655 hydrologic unit code - 10 (HUC10) mountain basins across the western United States (US) for water years 1987–2024. Linear regressions are performed for peak snow water equivalent (SWE) and annual streamflow for each mountain basin. Models use ordinary least squares in Python’s statsmodels package. After which, an Akaike Information Criterion (AIC)–weighted ensemble multiple linear regression (MLR) framework with 47 watershed traits is used to predict the linear regression coefficient of determination (r-squared) defining the ability of peak SWE to predict annual streamflow across all mountain basin. Predictor sets are constrained to avoid multicollinearity by excluding models with variance inflation factors (VIF) greater than 5. Mountain basin traits included in the MLR include seasonal climate, topography, vegetation type and structure, and bedrock geology. Accepted models are considered if their AIC is within 2.0 of the model with the minimum AIC, or best model. To compare predictor influence across acceptable models, we computed standardized regression coefficients. To evaluate structural redundancy among models, we constructed binary inclusion vectors for each acceptable model, denoting whether a predictor was present (1) or absent (0). Core predictor variables are defined as occurring in at least 67% of the acceptable models. For this regional analysis, only one model was found acceptable, with higher snow-to-streamflow translation (higher r-squared) occurring in colder mountain basins with higher relative winter precipitation, more snow accumulation and a lower fraction of annual precipitation that falls in the spring and summer. The second component of the data package uses previously published, high-resolution output from an integrated hydrological model of the East River watershed using the U.S. Geological Survey Groundwater and Surface water Flow model (GSFLOW, doi:10.15485/1998576). East River MLR expands upon the approach described above to explore the response of five streamflow metrics—annual streamflow, runoff efficiency, 7-day minimum flow, low-flow duration, and non-perennial stream fraction to snow system indicators including peak SWE, snow-covered area, snow disappearance date, and the fraction of basin area characterized by low-to-no snow, as well as seasonal precipitation and temperature, and annual hydrologic variables representing soil moisture, evapotranspiration (ET), the partitioning of incoming precipitation to evapotranspiration (ET/P), groundwater storage, and groundwater inflow to streams. MLR was done on all water years (P0: 1987-2024) and for each period as determined in the split analysis using pooled regression techniques (P1: 1987-2011 and P2: 2012-2024) to evaluate shifting predictor variable emphasis on streamflow generation. Results indicate that since 2012, peak SWE has lost statistical strength in its prediction of annual streamflow and runoff efficiency, and the indirect influence of spring temperature has emerged as critically important. Low-flow metrics remain largely influenced by soil moisture, vegetation water use and groundwater inflows with summer precipitation becoming a direct influence on minimum summer flow. Together, these data and Python-based analysis tools provide a framework for identifying the key watershed characteristics that control how streamflow responds to snow from year to year. The package also helps quantify uncertainty in statistical models and assess how snow–streamflow relationships vary across regions and over time. This dataset contains comma-separated values files (.csv), text files (.txt), python code files (.py), figure files (.png), and shapefiles (.cpg, .dbf, .prj, .sbn, .sbx, .shp, .xml). Further details on file contents and MLR execution can be found in the readme file and the FLMD files. Work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

54 ENVIRONMENTAL SCIENCES↗

Three-dimensional shock-wave/boundary-layer interactions with bleed through a circular hole

Computations were performed to study three-dimensional (3-D), shock-wave/boundary-layer interactions on a flat plate in which fluid in the boundary layer was bled through a circular hole into a plenum to control shock-wave induced separation. Results are presented which show the details of the 3-D flowfield about the bleed hole and how bleed-hole placement relative to shock-wave impingement affect upstream, spanwise, and downstream influence lengths. This study revealed an underlying mechanisms by which bleed holes can affect shock-wave/boundary-layer interactions. This investigation is based on the ensemble-averaged, "full-compressible" Navier-Stokes equations closed by the Baldwin-Lomax turbulence model. Solutions to these equations were obtained by an implicit finite-volume method based on the partially-split, two-factored algorithm of Steger.

Rimlinger, M. J.↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Four-flavour leading-order hadronic contribution to the muon anomalous magnetic moment

We present a four-flavour lattice calculation of the leading-order hadronic vacuum polarisation contribution to the anomalous magnetic moment of the muon, aμ hvp , arising from quark-connected Feynman graphs. It is based on ensembles featuring N f =2+1+1 dynamical twisted mass fermions generated by the European Twisted Mass Collaboration (ETMC). Several light quark masses are used in order to yield a controlled extrapolation to the physical pion mass. We employ three lattice spacings to examine lattice artefacts and several different volumes to check for finite-size effects. Including the complete first two generations of quarks allows for a direct comparison with phenomenological determinations of a μ hvp . The final result involving an estimate of the systematic uncertainty a μ hvp =6.74 (21)(18) 10 -8 shows a good overall agreement with these computations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Learning emergent partial differential equations in a learned emergent space

We propose an approach to learn effective evolution equations for large systems of interacting agents. This is demonstrated on two examples, a well-studied system of coupled normal form oscillators and a biologically motivated example of coupled Hodgkin-Huxley-like neurons. For such types of systems there is no obvious space coordinate in which to learn effective evolution laws in the form of partial differential equations. In our approach, we accomplish this by learning embedding coordinates from the time series data of the system using manifold learning as a first step. In these emergent coordinates, we then show how one can learn effective partial differential equations, using neural networks, that do not only reproduce the dynamics of the oscillator ensemble, but also capture the collective bifurcations when system parameters vary. The proposed approach thus integrates the automatic, data-driven extraction of emergent space coordinates parametrizing the agent dynamics, with machine-learning assisted identification of an emergent PDE description of the dynamics in this parametrization.

97 MATHEMATICS AND COMPUTING↗

Topological Quantum Hashing with the Icosahedral Group

We study an efficient algorithm to hash any single-qubit gate into a braid of Fibonacci anyons represented by a product of icosahedral group elements. By representing the group elements by braid segments of different lengths, we introduce a series of pseudogroups. Joining these braid segments in a renormalization group fashion, we obtain a Gaussian unitary ensemble of random-matrix representations of braids. With braids of length O(log{sup 2}(1/{epsilon})), we can approximate all SU(2) matrices to an average error {epsilon} with a cost of O(log(1/{epsilon})) in time. The algorithm is applicable to generic quantum compiling.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Postoperative 3D spine reconstruction by navigating partitioning manifolds

Purpose: The postoperative evaluation of scoliosis patients undergoing corrective treatment is an important task to assess the strategy of the spinal surgery. Using accurate 3D geometric models of the patient’s spine is essential to measure longitudinal changes in the patient’s anatomy. On the other hand, reconstructing the spine in 3D from postoperative radiographs is a challenging problem due to the presence of instrumentation (metallic rods and screws) occluding vertebrae on the spine. Methods: This paper describes the reconstruction problem by searching for the optimal model within a manifold space of articulated spines learned from a training dataset of pathological cases who underwent surgery. The manifold structure is implemented based on a multilevel manifold ensemble to structure the data, incorporating connections between nodes within a single manifold, in addition to connections between different multilevel manifolds, representing subregions with similar characteristics. Results: The reconstruction pipeline was evaluated on x-ray datasets from both preoperative patients and patients with spinal surgery. By comparing the method to ground-truth models, a 3D reconstruction accuracy of 2.24 ± 0.90 mm was obtained from 30 postoperative scoliotic patients, while handling patients with highly deformed spines. Conclusions: This paper illustrates how this manifold model can accurately identify similar spine models by navigating in the low-dimensional space, as well as computing nonlinear charts within local neighborhoods of the embedded space during the testing phase. This technique allows postoperative follow-ups of spinal surgery using personalized 3D spine models and assess surgical strategies for spinal deformities.

61 RADIATION PROTECTION AND DOSIMETRY↗

On the practical usefulness of the Hardware Efficient Ansatz

Variational Quantum Algorithms (VQAs) and Quantum Machine Learning (QML) models train a parametrized quantum circuit to solve a given learning task. The success of these algorithms greatly hinges on appropriately choosing an ansatz for the quantum circuit. Perhaps one of the most famous ansatzes is the one-dimensional layered Hardware Efficient Ansatz (HEA), which seeks to minimize the effect of hardware noise by using native gates and connectives. The use of this HEA has generated a certain ambivalence arising from the fact that while it suffers from barren plateaus at long depths, it can also avoid them at shallow ones. In this work, we attempt to determine whether one should, or should not, use a HEA. We rigorously identify scenarios where shallow HEAs should likely be avoided (e.g., VQA or QML tasks with data satisfying a volume law of entanglement). More importantly, we identify a Goldilocks scenario where shallow HEAs could achieve a quantum speedup: QML tasks with data satisfying an area law of entanglement. We provide examples for such scenario (such as Gaussian diagonal ensemble random Hamiltonian discrimination), and we show that in these cases a shallow HEA is always trainable and that there exists an anti-concentration of loss function values. Our work highlights the crucial role that input states play in the trainability of a parametrized quantum circuit, a phenomenon that is verified in our numerics.

97 MATHEMATICS AND COMPUTING↗

Various Numerical Applications on Tropical Convective Systems Using a Cloud Resolving Model

In recent years, increasing attention has been given to cloud resolving models (CRMs or cloud ensemble models-CEMs) for their ability to simulate the radiative-convective system, which plays a significant role in determining the regional heat and moisture budgets in the Tropics. The growing popularity of CRM usage can be credited to its inclusion of crucial and physically relatively realistic features such as explicit cloud-scale dynamics, sophisticated microphysical processes, and explicit cloud-radiation interaction. On the other hand, impacts of the environmental conditions (for example, the large-scale wind fields, heat and moisture advections as well as sea surface temperature) on the convective system can also be plausibly investigated using the CRMs with imposed explicit forcing. In this paper, by basically using a Goddard Cumulus Ensemble (GCE) model, three different studies on tropical convective systems are briefly presented. Each of these studies serves a different goal as well as uses a different approach. In the first study, which uses more of an idealized approach, the respective impacts of the large-scale horizontal wind shear and surface fluxes on the modeled tropical quasi-equilibrium states of temperature and water vapor are examined. In this 2-D study, the imposed large-scale horizontal wind shear is ideally either nudged (wind shear maintained strong) or mixed (wind shear weakened), while the minimum surface wind speed used for computing surface fluxes varies among various numerical experiments. For the second study, a handful of real tropical episodes (TRMM Kwajalein Experiment - KWAJEX, 1999; TRMM South China Sea Monsoon Experiment - SCSMEX, 1998) have been simulated such that several major atmospheric characteristics such as the rainfall amount and its associated stratiform contribution, the Qlheat and Q2/moisture budgets are investigated. In this study, the observed large-scale heat and moisture advections are continuously applied to the 2-D model. The modeled cloud generated from such an approach is termed continuously forced convection or continuous large-scale forced convection. A third study, which focuses on the respective impact of atmospheric components on upper Ocean heat and salt budgets, will be presented in the end. Unlike the two previous 2-D studies, this study employs the 3-D GCE-simulated diabatic source terms (using TOGA COARE observations) - radiation (longwave and shortwave), surface fluxes (sensible and latent heat, and wind stress), and precipitation as input for the Ocean mixed-layer (OML) model.

Shie, C.-L.↗

Applied Uses of MERRA Reanalyses: Current and Future Prospects

During the initial planning of the Modern Era Retrospective-analysis for Research and Applications (MERRA), the project was envisioned to become a tool for applied sciences and decision makers, as well as weather and climate research. MERRA was the first reanalysis to provide data at 1 hourly frequencies. After discussions with wind energy users, 50m above the surface winds were included in the data collection to begin to represent the environment at the turbine height. MERRA-2 was the first reanalysis to include interactive and assimilated aerosols. From these, PM 1, 2.5 and 10 records have been computed and contribute to the climate and health sector. The US Center for Disease Control is accessing MERRA-2 data for comparison along with their health data. MERRA-2 Extreme Indices have been computed from the high frequency data (e.g. precipitation maxima, heat waves and fire weather). These have been used to characterize the changing extremes in the United States and around the globe as well as the weather associated with the extremes. The next-generation, MERRA-21C, includes increased resolution (25km) and continues to provide innovative Earth system data. For example, a boundary layer collection will provide constant height level data starting at 100m, continuing up to 4000m. This will provide detailed information about the boundary layer processes that greatly affect the biosphere. Chemical tracers for constituents are included in the system. The ensemble data assimilation is run with 32 members, and the variance for critical variables are stored. We will explore the use of this variance as one measure of uncertainty relevant for applied uses, which has not been included in any MERRA reanalysis. We will discuss use case scenarios developed to engage with the energy and financial sectors, to better understand their needs for climate data. Prospects for further downscaling of reanalyses will also be explored.

Michael Bosilovich↗

Canonical and microcanonical ensemble descriptions of thermal pairing within BCS and quasiparticle random-phase approximation

We propose a description of pairing properties in finite systems within the canonical and microcanonical ensembles. The approach is derived by solving the BCS and self-consistent quasiparticle random-phase approximation with the Lipkin-Nogami particle-number projection at zero temperature. The obtained eigenvalues are embedded into the canonical and microcanonical ensembles. The results obtained are found in quite good agreement with the exact solutions of the doubly-folded equidistant multilevel pairing model as well as the experimental data for {sup 56}Fe nucleus. The merit of the present approach resides in its simplicity and its application to a wider range of particle number, where the exact solution is impracticable.

97 MATHEMATICS AND COMPUTING↗

DLSIA: Deep Learning for Scientific Image Analysis

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

97 MATHEMATICS AND COMPUTING↗