SEARCH · Search NASA

Results for “Sequencing data”

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.

SourceResearch connectionFrom yearThrough year

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

At least 289 records · Page 16

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Decayheatml

This code is designed to predict and analyze the decay heat generated in molten salt reactors (MSRs) using a hybrid approach that combines machine learning and segmented polynomial fitting. The accurate prediction of decay heat is essential for reactor safety and the optimization of spent fuel storage. The code operates through several key components: 1) Data Architecture: It incorporates a modular data architecture that handles various MSR-specific operational parameters such as power density, humidity content, and air ingress. These parameters are sampled using Sobol sequences to ensure comprehensive coverage of operational uncertainties. 2) Machine Learning Framework: The code employs a diverse set of machine learning models, including polynomial regression, decision trees, random forests, gradient boosting, support vector regression, k-nearest neighbors, multi-layer perceptrons, and symbolic regression. These models are trained to predict decay heat over a wide temporal range, from immediate shutdown up to 10,000 years. 3) Region-Optimized Training: The temporal domain is divided into multiple regions, each modeled separately to capture distinct decay heat characteristics across different time scales. This approach significantly improves the accuracy and interpretability of predictions. 4) Segmented Polynomial Interpretation (SPI): The SPI method translates machine learning predictions into piecewise polynomial equations. These equations are physically interpretable and can be directly integrated into existing engineering workflows and safety analyses. 5) Front-End Interfaces: The code includes both a Jupyter notebook interface for research development and a Streamlit web application for operational deployment. These interfaces allow users to interactively explore decay heat predictions, adjust operational parameters, and visualize results in real-time. 6) Applications: The framework supports various applications, including safety system validation and spent fuel container optimization. It enables real-time evaluation of worst-case decay heat scenarios, informing the design of passive safety systems and optimizing container designs for long-term storage. Overall, this code provides a robust, accurate, and user-friendly tool for predicting decay heat in MSRs, enhancing reactor safety, and optimizing spent fuel management.

Retamales, Mauricio Eduardo Tano [Idaho National L↗

DOE OSTI2025

Geometric Interpretation of the Cluster Location Problem Part II: Application to the Pahala, Hawaii, Earthquake Sequence

In the companion “Theory” article, we presented a new framing of the seismic location problem in terms of differential geometry (Harris et al., 2025). From that viewpoint, we developed a “project and correct” approach for estimating the relative locations of earthquakes. Here, in this study, we use project and correct to estimate high-precision relative locations of events from an earthquake sequence beneath the town of Pahala, Hawaii, using high-precision correlation-derived picks. The sequence was active from 2020 through 2022 and produced many highly correlated signals at Hawaii Volcano Observatory (HVO) stations on the island of Hawaii. The data we inverted consisted of 2882 events with observations at 5 HVO stations. For comparison with the travel-time image, we also produced conventional hypocenter solutions using both the Bayesloc program (Myers et al., 2007, 2009) and a purpose-built double-difference code. There were obvious structural elements in the resulting image, the resolution of which we used to test the performance of the project and the correct algorithm. For the projection step, we first produced a 3D local basis using an singular value decomposition (SVD) of the 2882 groups of times. Projection of the travel-time vectors into this basis resulted in an image with structures similar to those produced by our conventional locators, but with distortion as predicted by theory. Removing the distortion requires an inverse operator generated from the metric tensor at the geometric centroid of the events. We compared two approaches to obtaining such an inverse operator. The first uses an estimate of the geographic centroid of the event cloud from the centroid of the travel-time data. The second approach uses the centroid of the conventionally produced locations. The first approach produces a corrected image very similar to the conventional results, but with a rotation. The corrected image produced using the conventionally derived centroid is a near-exact match to the conventional locations.

Dodge, Douglas A. [Lawrence Livermore National Lab↗

DOE OSTI2025

Hazard Detection Detector Cards

This report presents a comprehensive summary of five advanced anomaly detection tools developed and deployed by Oak Ridge National Laboratory in support of the VA’s Health Information Technology modernization. These detectors—Order Path Tracker, Trend Watcher, Pain Pointer, Performance Monitor, and Patient Record Flag Detector—leverage statistical and machine learning methods to monitor workflow disruptions, detect anomalies in care sequences and volumes, identify bottlenecks, and track system-level performance metrics across VistA and Millennium systems. All detectors have been integrated into the Health Data Analytics Platform (HDAP), with most having completed deployment and testing using live data from targeted stations in cardiology and oncology domains. This work enhances VA’s capacity for proactive system surveillance, promotes patient safety, and informs data-driven operational improvements across the EHR ecosystem.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Identifying impacts of contact tracing on HIV epidemiological inference from phylogenetic data

Abstract Robust sampling methods are foundational to inferences using phylogenies. Yet the impact of using contact tracing, a type of non-uniform sampling used in public health applications such as infectious disease outbreak investigations, has not been investigated in the molecular epidemiology field. To understand how contact tracing influences a recovered phylogeny, we developed a new simulation tool called SEEPS (Sequence Evolution and Epidemiological Process Simulator) that allows for the simulation of contact tracing and the resulting transmission tree, pathogen phylogeny, and corresponding virus genetic sequences. Importantly, SEEPS takes within-host evolution into account when generating pathogen phylogenies and sequences from transmission histories. Using SEEPS, we demonstrate that contact tracing can significantly impact the structure of the resulting tree, as described by popular tree statistics. Contact tracing generates phylogenies that are less balanced than the underlying transmission process, less representative of the larger epidemiological process, and affects the internal/external branch length ratios that characterize specific epidemiological scenarios. We also examined real data from a 2007–2008 Swedish HIV-1 outbreak and the broader 1998–2010 European HIV-1 epidemic to highlight the differences in contact tracing and expected phylogenies. Aided by SEEPS, we show that the data collection of the Swedish outbreak was strongly influenced by contact tracing even after downsampling, while the broader European Union epidemic showed little evidence of universal contact tracing, agreeing with the known epidemiological information about sampling and spread. Overall, our results highlight the importance of including possible non-uniform sampling schemes when examining phylogenetic trees. For that, SEEPS serves as a useful tool to evaluate such impacts, thereby facilitating better phylogenetic inferences of the characteristics of a disease outbreak. SEEPS is available at https://github.com/MolEvolEpid/SEEPS.

Virology↗

DOE OSTI2024

Missing microbial eukaryotes and misleading meta-omic conclusions

Meta-omics is commonly used for large-scale analyses of microbial eukaryotes, including species or taxonomic group distribution mapping, gene catalog construction, and inference on the functional roles and activities of microbial eukaryotes in situ. Here, we explore the potential pitfalls of common approaches to taxonomic annotation of protistan meta-omic datasets. We re-analyze three environmental datasets at three levels of taxonomic hierarchy in order to illustrate the crucial importance of database completeness and curation in enabling accurate environmental interpretation. We show that taxonomic membership of sequence clusters estimates community composition more accurately than returning exact sequence labels, and overlap between clusters can address database shortcomings. Clustering approaches can be applied to diverse environments while continuing to exploit the wealth of annotation data collated in databases, and selecting and evaluating these databases is a critical part of correctly annotating protistan taxonomy in environmental datasets. We argue that ongoing curation of genetic resources is crucial in accurately annotating protists in in situ meta-omic datasets. Moreover, we propose that precise taxonomic annotation of meta-omic data is a clustering problem rather than a feasible alignment problem.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Convolutional L2LFlows: generating accurate showers in highly granular calorimeters using convolutional normalizing flows

Abstract In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been among the models with the best fidelity. However, as the latent space in such models is required to have the same dimensionality as the data space, scaling up normalizing flows to high dimensional datasets is not straightforward. The prior L2LFlows approach successfully used a series of separate normalizing flows and sequence of conditioning steps to circumvent this problem. In this work, we extend L2LFlows to simulate showers with a 9-times larger profile in the lateral direction. To achieve this, we introduce convolutional layers and U-Net-type connections, move from masked autoregressive flows to coupling layers, and demonstrate the successful modelling of showers in the ILD Electromagnetic Calorimeter as well as Dataset 3 from the public CaloChallenge dataset.

Instruments & Instrumentation↗

DOE OSTI2025

Statistical estimates of the binary properties of rotational variables

ABSTRACT We present a model to estimate the average primary masses, companion mass ranges, the inclination limit for recognizing a rotational variable, and the primary mass spreads for populations of binary stars. The model fits a population’s binary mass function distribution and allows for a probability that some mass functions are incorrectly estimated. Using tests with synthetic data, we assess the model’s sensitivity to each parameter, finding that we are most sensitive to the average primary mass and the minimum companion mass, with less sensitivity to the inclination limit and little to no sensitivity to the primary mass spread. We apply the model to five populations of binary spotted rotational variables identified in ASAS-SN, computing their binary mass functions using RV data from APOGEE. Their average primary mass estimates are consistent with our expectations based on their CMD locations ($\sim 0.75 \, {\rm M}_{\odot }$ for lower main sequence primaries and $\sim 0.9$–$1.2 \, {\rm M}_{\odot }$ for RS CVn and sub-subgiants). Their companion mass range estimates allow companion masses down to $M_2/M_1\simeq 0.1$, although the main sequence population may have a higher minimum mass fraction ($\sim 0.4$). We see weak evidence of an inclination limit $\gtrsim 50^{\circ }$ for the main sequence and sub-subgiant groups and no evidence of an inclination limit in the other groups. No groups show strong evidence for a preferred primary mass spread. We conclude by demonstrating that the approach will provide significantly better estimates of the primary mass and the minimum mass ratio and reasonable sensitivity to the inclination limit with 10 times as many systems.

Phillips, Anya (ORCID:000900051914974X)↗

DOE OSTI2025

ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling

Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables and geographies and are constrained by the quadratic complexity of Vision Transformer (ViT) self-attention. We introduce ORBIT-2, a scalable foundation model for global, hyper-resolution climate downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 ExaFLOPS sustained throughput and 74–98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with R2 scores in range of 0.98–0.99 against observation data.

Wang, Xiao [ORNL] (ORCID:0000000165451943)↗

DOE OSTI2025

ORBIT-2 Weather and Climate Downscaling Software Repository

ORBIT-2 is a scalable foundation model for global, hyper-resolution climate and weather downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 ExaFLOPS sustained throughput and 74–98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with 𝑅2 scores in range of 0.98–0.99 against observation data.

Wang, Xiao [Oak Ridge National Laboratory]↗

DOE OSTI2024

Chromosome-level genome assemblies and genetic maps reveal heterochiasmy and macrosynteny in endangered Atlantic Acropora

Abstract Background Over their evolutionary history, corals have adapted to sea level rise and increasing ocean temperatures, however, it is unclear how quickly they may respond to rapid change. Genome structure and genetic diversity contained within may highlight their adaptive potential. Results We present chromosome-scale genome assemblies and linkage maps of the critically endangered Atlantic acroporids,Acropora palmataandA. cervicornis. Both assemblies and linkage maps were resolved into 14 chromosomes with their gene content and colinearity. Repeats and chromosome arrangements were largely preserved between the species. The family Acroporidae and the genusAcroporaexhibited many phylogenetically significant gene family expansions. Macrosynteny decreased with phylogenetic distance. Nevertheless, scleractinians shared six of the 21 cnidarian ancestral linkage groups as well as numerous fission and fusion events compared to other distantly related cnidarians. Genetic linkage maps were constructed from oneA. palmatafamily and 16A. cervicornisfamilies using a genotyping array. The consensus maps span 1,013.42 cM and 927.36 cM forA. palmataandA. cervicornis, respectively. Both species exhibited high genome-wide recombination rates (3.04 to 3.53 cM/Mb) and pronounced sex-based differences, known as heterochiasmy, with 2 to 2.5X higher recombination rates estimated in the female maps. Conclusions Together, the chromosome-scale assemblies and genetic maps we present here are the first detailed look at the genomic landscapes of the critically endangered Atlantic acroporids. These data sets revealed that adaptive capacity of Atlantic acroporids is not limited by their recombination rates. The sister species maintain macrosynteny with few genes with high sequence divergence that may act as reproductive barriers between them. In the AtlanticAcropora, hybridization between the two sister species yields an F1 hybrid with limited fertility despite the high levels of macrosynteny and gene colinearity of their genomes. Together, these resources now enable genome-wide association studies and discovery of quantitative trait loci, two tools that can aid in the conservation of these species.

Biotechnology & Applied Microbiology↗

DOE OSTI2025

General Biology 2 Sugar Beet Lab - Spring 24

This module uses the Department of Energy Systems Biology Knowledgebase (KBase) platform to explore topics such as genome assembly, metagenomics, and phylogenomics. Here students will use sequences from DNA that they collected to compare the metagenomes of microbial communities from the rhizosphere of plants grown in fertilized vs. unfertilized soils. Using these data students will evaluate the impact of fertilizer on these communities and how these microbial communities influence soil health and plant growth.

Schirmer, Aaron [Northeastern Illinois University,↗

DOE OSTI2025

General Biology 2 Sugar Beet Lab - SU2025 - Final

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

HSQC spectra of lignin isolated from poplar stems

Here we present a curated dataset of two-dimensional heteronuclear single quantum coherence (HSQC) nuclear magnetic resonance (NMR) spectra of lignin isolated from stems of genetically engineered poplar through auxin signaling gene modification. The plants were grown in greenhouse with temperatures between 21 and 23 °C. Plants were harvested and the aboveground stems were cut off an approximately five-inch-long segment from the bottom end of the plant stem, debarked and air-dried for three weeks. The dried stem samples were Wiley milled (mesh size 20), Soxhlet-extracted with toluene/ethanol for 24 h to remove extractives. The extracted biomass was ball-milled in a Retsch PM100 planetary ball mill using a porcelain jar with ceramic balls at 600 rpm for 2 h (in 5 min on and 5 min off cycles to avoid excessive sample heating). The ball-milled materials were then subjected to enzymatic hydrolysis for 48 h followed by centrifugation and washing with deionized water. The solid residue was freeze-dried to recover the lignin. The dry stem lignin samples were dissolved in deuterated dimethyl sulfoxide (d6) and transferred into a 5 mm tube. 13C–1H HSQC experiments were performed in a Bruker Avance III HD 500 MHz NMR spectrometer operating at a frequency of 125.12 MHz for the 13C nucleus using a standard Bruker pulse sequence on a Prodigy platform cryoprobe. The NMR spectra were acquired under the following acquisition conditions: 230 ppm spectral width in F1 (13C) dimension with 256 data points and 12 ppm spectral width in F2 (1H) dimension with 2048 data points, a 90° pulse, a one bond C–H coupling constant of 145 Hz, a 1.0 s pulse delay, and 64 scans. Spectra were processed using the Bruker TopSpin 3.6 software. Additional meta data is embedded in the raw spectra figures.

HSQC, lignin, poplar, stems, CBI↗

DOE OSTI2024

HSQC spectra of lignin isolated from poplar roots

Here we present a curated dataset of two-dimensional heteronuclear single quantum coherence (HSQC) nuclear magnetic resonance (NMR) spectra of lignin isolated from roots of a greenhouse grown natural population of an energy crop poplar (Populus trichocarpa). Dormant cuttings of field-grown poplar were grown in 6-liter pots in a peat-based media containing bark, perlite, vermiculite, dolomite lime and a wetting agent in an environmentally controlled greenhouse. Temperatures were between 21 and 23 °C, with supplemental lighting to support a 16-h day length using 1000-watt high-pressure sodium lights in greenhouse. Once established, all plants were cut-back, allowed to regrow and harvested at the same time following an eight-month long growth period. Plants were harvested and the belowground roots were washed off soils, blotted, dried in an oven at 70 °C for 3 days, and Wiley milled (mesh size 20). The roots were Soxhlet-extracted with toluene/ethanol for 24 h to remove extractives. The extracted roots were ball-milled in a Retsch PM100 planetary ball mill using a porcelain jar with ceramic balls at 600 rpm for 2 h (in 5 min on and 5 min off cycles to avoid excessive sample heating). The ball-milled materials were then subjected to enzymatic hydrolysis for 48 h followed by centrifugation and washing with deionized water. The solid residue was extracted twice with 96% (v/v) 1,4-dioxane/water mixture at room temperature overnight. The extracts were combined, rotary evaporated, and freeze-dried to recover lignin. The dry lignin samples were dissolved in deuterated dimethyl sulfoxide (d6) and transferred into a 5 mm tube. 13C–1H HSQC experiments were performed in a Bruker Avance III HD 500 MHz NMR spectrometer operating at a frequency of 125.12 MHz for the 13C nucleus using a standard Bruker pulse sequence on a Prodigy platform cryoprobe. The NMR spectra were acquired under the following acquisition conditions: 220 ppm spectral width in F1 (13C) dimension with 256 data points and 12 ppm spectral width in F2 (1H) dimension with 1024 data points, a 90° pulse, a one bond C–H coupling constant of 145 Hz, a 1.0 s pulse delay, and 64 scans. Spectra were processed using the Bruker TopSpin software. Additional meta data is embedded in the raw spectra figures.

HSQC, lignin, poplar, roots, CBI↗

DOE OSTI2026

Benchtop Autonomous Electrochemical Characterization System for Combinatorial Thin-Film Solid Oxide Electrodes

The design of materials for electrochemical energy conversion is complicated by a vast search space of candidate materials and multifaceted property requirements: multicarrier conductivity, stability, and catalytic activity are all necessary but rarely intersect. Although self-driving laboratories are rapidly rising to address such material optimization problems, the required infrastructure for integrated, large-scale robotic facilities can be cost-prohibitive. Here we develop and evaluate a closed-loop measurement system for efficient screening of proton-conducting oxide electrodes for ceramic fuel cells and electrolyzers, building on top of an existing benchtop instrument and integrating techniques for rapid impedance measurement and automated analysis. This system exemplifies a “minimum viable” self-driving implementation that can deliver substantial benefits with relatively simple infrastructure. Combinatorial thin-film microelectrode libraries are characterized with a recently developed joint time-domain and frequency-domain impedance measurement technique, which provides an order-of-magnitude acceleration relative to conventional impedance spectroscopy. The distribution of relaxation times is extracted from impedance data and analyzed without human intervention. These results feed an active learning and Bayesian optimization process that learns to predict electrochemical impedance as a function of material composition, measurement temperature, oxygen partial pressure, and electrical bias, which further reduces the screening time by tenfold with optimized experimental sequences. We apply this system to Ba⁡(Co,Fe,Zr,Y)⁢O 3−𝛿 combinatorial libraries and evaluate its effectiveness for learning material property trends and optimizing expensive-to-evaluate properties such as activation energy. This offers insights into key methodological aspects of practical autonomous experimentation, including surrogate model validation, cost-aware acquisition functions, and high-throughput data interpretation. Our results demonstrate the efficacy of the system for rapidly gathering information, but also highlight real-world experimental challenges of thin-film degradation and numerical instability in surrogate models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Two-dimensional heteronuclear single quantum coherence (HSQC) NMR spectra of lignin isolated from field grown transgenic poplar

Here we present a curated dataset of a series of two-dimensional heteronuclear single quantum coherence (HSQC) nuclear magnetic resonance (NMR) spectra of lignin isolated from a field grown transgenic poplar engineered with a monolignol 4-O-methyltransferase (MOMT4). The poplar was collected from a 2-year-old rotation trees within a three-year field trial experiment. The poplar was Soxhlet-extracted with toluene/ethanol and the extractives-free poplar was then ball-milled in a Retsch PM100 planetary ball mill using a porcelain jar with ceramic balls at 600 rpm for 2 h (in 5 min on and 5 min off cycles to avoid excessive sample heating). The ball-milled materials were then subjected to enzymatic hydrolysis for 48 h followed by centrifugation and washing with deionized water. The solid residue was extracted twice with 96:4 (v/v) 1,4-dioxane/water mixture at room temperature overnight. The extracts were combined, rotary evaporated, and freeze-dried to recover the lignin. The dry lignin samples were dissolved in deuterated dimethyl sulfoxide for NMR experiments. 13C–1H HSQC experiments were performed in a Bruker Avance III HD 500 MHz NMR spectrometer operating at a frequency of 125.12 MHz for the 13C nucleus using a standard Bruker pulse sequence (hsqcetgpsisp2.2) on a Prodigy platform cryoprobe. The NMR spectra were acquired under the following acquisition conditions: 220 ppm spectral width in F1 (13C) dimension with 256 data points and 12 ppm spectral width in F2 (1H) dimension with 1024 data points, a 90° pulse, a one bond C–H coupling constant of 145 Hz, a 1.0 s pulse delay, and 64 scans. All the data was processed using the Bruker’s TopSpin 3.6 software. The NMR spectra provides structural characteristics information about lignin in field grown transgenic MOMT4 poplar. Additional meta data is embedded in the raw spectra figures.

Lignin structure, HSQC, poplar, field trial, MOMT4↗

DOE OSTI2025

EP 250108a/SN 2025kg: Observations of the Most Nearby Broad-line Type Ic Supernova Following an Einstein Probe Fast X-Ray Transient

With a small sample of fast X-ray transients (FXTs) with multiwavelength counterparts discovered to date, their progenitors and connections to γ-ray bursts (GRBs) and supernovae (SNe) remain ambiguous. Here, we present photometric and spectroscopic observations of SN 2025kg, the SN counterpart to the FXT EP 250108a. At z = 0.17641, this is the closest known SN discovered following an Einstein Probe (EP) FXT. We show that SN 2025kg’s optical spectra reveal the hallmark features of a broad-lined Type Ic SN. Its light-curve evolution and expansion velocities are comparable to those of GRB-SNe, including SN 1998bw, and two past FXT-SNe. We present JWST/NIRSpec spectroscopy taken around SN 2025kg’s maximum light, and find weak absorption due to He I 1.0830 μm and 2.0581 μm and a broad, unidentified emission feature at ∼4–4.5 μm. Further, we observe broadened Hα in optical data at 42.5 days that is not detected at other epochs, indicating interaction with H-rich material. From its light curve, we derive a 56 Ni mass of 0.2–0.6 M ⊙ . Together with our companion Letter, our broadband data are consistent with a trapped or low-energy (≲10 51 erg) jet-driven explosion from a collapsar with a zero-age main-sequence mass of 15–30 M ⊙ . Finally, we show that the sample of EP FXT-SNe supports past estimates that low-luminosity jets seen through FXTs are more common than successful (GRB) jets, and that similar FXT-like signatures are likely present in at least a few percent of the brightest Type Ic-BL SNe.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Differentiable hybrid neural network approach for enhancing reactor dynamics simulations

Reactor dynamics simulations provide essential insights into the time-dependent behavior of nuclear reactors under various operating conditions. However, high-fidelity simulations can be computationally intensive, requiring significant computational resources. Here, to address this challenge, this study employs a differentiable hybrid model that utilizes neural networks as a corrector to enhance the performance of a low-fidelity simulation, aligning its predictions with those of a high-fidelity simulation. Low-fidelity and high-fidelity simulations were obtained by adjusting the mesh size in the System Dynamics Analysis Tool. The differentiable hybrid model was trained in two approaches: time-step-wise and sequence-wise. It was then applied to simulate various transients in a molten salt reactor. Its performance was evaluated by comparing its responses to transients against those of the high-fidelity simulation. An additional approach was performed using a data-driven model to correct the low-fidelity simulation. In comparison, the differentiable hybrid model showed significant improvements in transient prediction, effectively addressing the limitations of the low-fidelity simulations. The results highlighted the robustness of the differentiable hybrid model in both training approaches. It delivered simulations that were at least 3.8 times faster than high-fidelity models. In the time-step-wise approach, it achieved at least a 39% improvement in accuracy. In the sequence-wise approach, it showed at least an 81% accuracy improvement over the full transient. This approach offers a promising path for improving computational efficiency without compromising accuracy in nuclear reactor simulations, making it suitable for real-time digital twin applications.

42 - ENGINEERING↗