Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “benchmark dataset”

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 505 records · Page 28

Sampling Within k-Means Algorithm to Cluster Large Datasets

Due to current data collection technology, our ability to gather data has surpassed our ability to analyze it. In particular, k-means, one of the simplest and fastest clustering algorithms, is ill-equipped to handle extremely large datasets on even the most powerful machines. Our new algorithm uses a sample from a dataset to decrease runtime by reducing the amount of data analyzed. We perform a simulation study to compare our sampling based k-means to the standard k-means algorithm by analyzing both the speed and accuracy of the two methods. Results show that our algorithm is significantly more efficient than the existing algorithm with comparable accuracy. Further work on this project might include a more comprehensive study both on more varied test datasets as well as on real weather datasets. This is especially important considering that this preliminary study was performed on rather tame datasets. Also, these datasets should analyze the performance of the algorithm on varied values of k. Lastly, this paper showed that the algorithm was accurate for relatively low sample sizes. We would like to analyze this further to see how accurate the algorithm is for even lower sample sizes. We could find the lowest sample sizes, by manipulating width and confidence level, for which the algorithm would be acceptably accurate. In order for our algorithm to be a success, it needs to meet two benchmarks: match the accuracy of the standard k-means algorithm and significantly reduce runtime. Both goals are accomplished for all six datasets analyzed. However, on datasets of three and four dimension, as the data becomes more difficult to cluster, both algorithms fail to obtain the correct classifications on some trials. Nevertheless, our algorithm consistently matches the performance of the standard algorithm while becoming remarkably more efficient with time. Therefore, we conclude that analysts can use our algorithm, expecting accurate results in considerably less time.

99 GENERAL AND MISCELLANEOUS↗

The ePIC Simulation Campaign Workflow on the Open Science Grid

The ePIC collaboration is realizing the first experiment of the future Electron-Ion Collider (EIC) at the Brookhaven National Laboratory that will allow for a precision study of the nucleons and the nucleus at the scale of sea quarks and gluons through the study of electron-proton/ion collisions. This paper will discuss the current workflow for running centralized simulation campaigns for ePIC on the Open Science Grid (OSG) infrastructure. This involves monthly releases of ePIC software and container deployments to CVMFS, generation of input datasets in HepMC format according to collaboration-defined policy, using Snakemake in CI/CD for validation and benchmarking, and submitting jobs to the OSG condor scheduler for opportunistic running on available resources. File transfers utilize XrootD, and Rucio is used for data management. The workflow is continuously refined to improve daily throughput (currently 50-100k core hours per day) and minimize job failures. Since May 2023, monthly simulation campaigns employing the workflow have cumulatively used over 20 million core hours on the OSG and produced over 350 TB of simulation data. The campaigns incorporate simulations for the broad science program of the EIC and are actively used for the detector and physics studies in preparation of the Technical Design Report (TDR).

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Ptychographic phase retrieval by proximal algorithms

We derive a set of ptychography phase-retrieval iterative engines based on proximal algorithms originally developed in convex optimization theory, and discuss their connections with existing ones. The use of proximal operator creates a simple frame work that allows us to incorporate the effect of noise from a maximum-likelihood (ML) principle. We focus on three particular algorithms, namely proximal minimization, alternating direction method of multiplier and accelerated proximal gradient (APG). We benchmark their performance with numerical simulations, and discuss their optimal conditions for convergence and accuracy. An experimental dataset is used to demonstrate their effectiveness as well, in which case an array of cubic Au nanoparticles with a size of 50 nm is imaged. We show that with the presence of Poisson noise, a dataset with photon counts up to 10 4 at one detector pixel already requires ML-based methods to achieve a stable convergence. Among the three algorithms derived in this work, APG method is reported first time for its application in ptychographic reconstruction and shows superior performance in terms of both accuracy and convergence rate with a noisy dataset.

36 MATERIALS SCIENCE↗

Wind power forecasting: IEA Wind Task 36 & future research issues

Here, this paper presents the new International Energy Agency Wind Task 36 on Forecasting, and invites to collaborate within the group. Wind power forecasts have been used operatively for over 20 years. Despite this fact, there are still several possibilities to improve the forecasts, both from the weather prediction side and from the usage of the forecasts. The new International Energy Agency (IEA) Task on Forecasting for Wind Energy tries to organise international collaboration, among national meteorological centres with an interest and/or large projects on wind forecast improvements (NOAA, DWD, MetOffice, met.no, DMI,...), operational forecaster and forecast users. The Task is divided in three work packages: Firstly, a collaboration on the improvement of the scientific basis for the wind predictions themselves. This includes numerical weather prediction model physics, but also widely distributed information on accessible datasets. Secondly, we will be aiming at an international pre-standard (an IEA Recommended Practice) on benchmarking and comparing wind power forecasts, including probabilistic forecasts. This WP will also organise benchmarks, in cooperation with the IEA Task WakeBench. Thirdly, we will be engaging end users aiming at dissemination of the best practice in the usage of wind power predictions. As first results, an overview of current issues for research in short-term forecasting of wind power is presented.

17 WIND ENERGY↗

Transformative Materials for High-Efficiency Thermochemical Production of Solar Fuels (Final Report)

Metal oxide-based two-step solar thermochemical (STC) H 2 O and CO 2 -splitting cycles are a promising route to convert solar thermal energy into fuels. The metal oxide materials are reduced at high temperatures (Step 1), and then at low (but still elevated) temperatures, the reduced oxide is used to split H 2 O or CO 2 (Step 2). However, current applications of these cycles are limited by the efficiency of the metal oxide materials. A lower temperature for reduction is desirable, but that brings a concomitant reduction in the driving force for gas splitting. So, designing novel, high-efficiency materials is challenging. Here, we devised and performed a joint computational-experimental project, combined with materials design strategies and high-throughput approaches with the goal to quickly discover and demonstrate novel thermochemical materials with superior properties. Our approach involves an active feedback loop between experimental and computational research. We have use our previously developed materials design map, to efficiently screen results from high-throughput first- principles computation to predict new compositions and subsequently to experimentally study the properties of novel, predicted materials. Experimental measurements of the thermodynamic properties of selected materials serve as a critical benchmark, not only in evaluating the STCH properties of synthesized compounds, but also serving as a validation dataset for computational approaches. We experimentally explored a set of predicted ABO3 perovskites and focus on obtaining high quality thermodynamic properties for validation of computational prediction of enthalpy and entropy of reduction. These thermodynamic quantities play a major role in designing materials with reduced temperatures of reduction but sufficient gas-splitting rates. Finding good validation between experimental and computational data for enthalpies of reduction, we turn to promising ABO3 materials modified by A and B site substitutions, opening an enormous combinatorial space of materials. We use our high-throughput approach to “tune in” the desired solar thermochemical (STC) properties for STC. This vast composition space can only be reasonably explored using the high-throughput approaches, both computational and experimental, of this proposal. Several promising novel oxide materials have been predicted, synthesized, and verified using our materials design approach.

08 HYDROGEN↗

Can We Use the QA4ECV Black-sky Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) using AVHRR Surface Reflectance to Assess Terrestrial Global Change?

NOAA platforms provide the longest period of terrestrial observation since the 1980s. The progress in calibration, atmospheric corrections and physically based land retrieval offers the opportunity to reprocess these data for extending terrestrial product time series. Within the Quality Assurance for Essential Climate Variables (QA4ECV) project, the black-sky Joint Research Centre (JRC)-fraction of absorbed photosynthetically active radiation (FAPAR) algorithm was developed for the AVHRR sensors on-board NOAA-07 to -16 using the Land Surface Reflectance Climate Data Record. The retrieval algorithm was based on the radiative transfer theory, and uncertainties were included in the products. We proposed a time and spatial composite for providing both 10-day and monthly products at 0.05º × 0.05º. Quality control and validation were achieved through benchmarking against third-party products, including Sea-Viewing Wide Field-of-View Sensor (SeaWiFS) datasets produced with the same retrieval algorithm. Past ground-based measurements, providing a proxy of FAPAR, showed good agreement of seasonality values over short homogeneous canopies and mixed vegetation. The average difference between SeaWiFS and QA4ECV monthly products over 2002–2005 is about 0.075 with a standard deviation of 0.091. We proposed a monthly linear bias correction that reduced these statistics to 0.02 and 0.001. The complete harmonized long-term time series was then used to address its fitness for the purpose of analysis of global terrestrial change.

AVHRR↗

Automating Anharmonic Lattice Thermal Conductivity Calculations using Compressed Sensing Lattice Dynamics [Poster]

Engineering heat transfer is critical for applications in heat exchangers, semiconductor devices, thermoelectrics and more. This demand motivates a high-throughput computational methodology for systematically designing materials with improved thermal properties. One emerging method which can rapidly and explicitly consider phonon-phonon interactions even for highly anharmonic materials is Compressive Sensing Lattice Dynamics (CSLD). In fact, CSLD accurately predicts 2nd (harmonic) and 3rd+ order (anharmonic) interatomic force constants (IFCs) with orders of magnitude fewer Density Functional Theory (DFT) calculations than conventional methods. However, doing CSLD can be an exhaustive, many-step process requiring an intimate knowledge of its sensitivity to parameters. Consequently, this work implements an automatic CSLD workflow capable of obtaining the thermal conductivity of potentially thousands of materials, benchmarks the stability of the workflow against materials with a range of anharmonicity, and begins constructing a dataset of thermal conductivity values and phonon dispersion curves to be stored in the Materials Project for public use.

Chang, Rees↗

Data Driven Commercial Building Energy Code Compliance and Technology Inventory for New York City

Building Performance Standards (BPS) are gaining national traction. A BPS will require new processes in the design, construction, and operation of buildings that take the occupants into account and enable predictive analysis to ensure compliance with current and future GHG emissions caps. In New York City, most buildings over 25,000 square feet will be regulated by a BPS starting in 2024, regardless of whether it is new construction permitted under current energy codes or an existing building. This research is one of the first to begin the evaluation of a long-term series of building policies in the context of an open data ecosystem, in cooperation with city agencies. Existing building policies enacted in NYC have ranged from building energy benchmarking and labeling to energy audits to the regulation of GHG emission in buildings. Through the development of a dataset related to building technologies and energy consumption, this project can help to evaluate if meaningful conclusions can be drawn for the data that has been largely self-reported in compliance with city regulations. This project will also provide lessons learned from a deep dive into these types of datasets to provide best practices for municipalities or states seeking to embark on policies like those enacted in NYC. In addition, a Building Automation System (BAS) Stretch Standard of Care (SSOC) for owners, designers, and building operators will enable the measurement and predictive analysis of energy consumption and GHG emissions at the plant, system, or component level, in anticipation of regulated GHG limits on buildings based on energy use. The SSOC is expected to be suitable for use on a national level. The primary feature of an SSOC is a standardized format for a set of BAS points that can be used to control and to gather data from individual plants, systems, or components that are related to building energy consumption. This project examined how measurements compare to prescriptive or simulation-based energy code targets, finding little correlation between predictive 8760-hour energy modeling and actual energy consumption for a small sample (n=27) of buildings constructed after 2015. Other analysis found that, while large multifamily housing (MFH) buildings showed a general trend similar to predicted reductions in energy use from the implementation of model commercial energy codes, this trend was not evident in the office, K-12 school, and hotel use groups in NYC. No upward or downward trends in energy consumption were found when buildings were grouped by size. Energy audit data were analyzed and it appears that there is bias by audit company on measures recommended to clients. Further research should be performed to cross-analyze this with other attributes, such as building size, vintage, and number of stories. Analysis found that for 281 buildings that were permitted and completed after 2015 and had submitted benchmarking data in 2022, between 81% and 96% (by use group) were found to be in compliance with the 2024 to 2029 NYC BPS emission caps, and between 55% and 89% were in compliance with the 2030-2034 caps. This work is beneficial to the public in helping policymakers and building stakeholders better understand the wide-ranging implications of a BPS.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Is the assumption of normality or log-normality for continuous response data critical for benchmark dose estimation?

Continuous responses (e.g. body weight) are widely used in risk assessment for determining the benchmark dose (BMD) which is used to derive a U.S. EPA reference dose. One critical question that is not often addressed in dose–response assessments is whether to model the continuous data as normally or log-normally distributed. Additionally, if lognormality is assumed, and only summarized response data (i.e., mean ± standard deviation) are available as is usual in the peer-reviewed literature, the BMD can only be approximated. In this study, using the “hybrid” method and relative deviation approach, we first evaluate six representative continuous dose–response datasets reporting individual animal responses to investigate the impact on BMD/BMDL estimates of (1) the distribution assumption and (2) the use of summarized versus individual animal data when a log-normal distribution is assumed. We also conduct simulation studies evaluating model fits to various known distributions to investigate whether the distribution assumption has influence on BMD/BMDL estimates. Our results indicate that BMDs estimated using the hybrid method are more sensitive to the distribution assumption than counterpart BMDs estimated using the relative deviation approach. The choice of distribution assumption has limited impact on the BMD/BMDL estimates when the within dose-group variance is small, while the lognormality assumption is a better choice for relative deviation method when data are more skewed because of its appropriateness in describing the relationship between mean and standard deviation. Additionally, the results suggest that the use of summarized data versus individual response data to characterize log-normal distributions has minimal impact on BMD estimates. - Highlights: • We investigate to what extent the distribution assumption can affect BMD estimates. • Both real data analysis and simulation study are conducted. • BMDs estimated using hybrid method are more sensitive to distribution assumption. • Summarized continuous data are adequate for BMD estimation.

60 APPLIED LIFE SCIENCES↗

A two-stage optical fusion framework for wildfire severity mapping across the conterminous United States

Accurate wildfire severity mapping (WSM) is essential for post-fire recovery planning, erosion risk assessment, ecosystem monitoring, and disaster risk reduction. Although Landsat and Sentinel optical imagery have been widely used for burn severity assessment, the added value of fusing multiple optical sensors has not been sufficiently quantified across diverse fire events, particularly since the launch of Landsat-9. This study evaluates whether multisensor optical fusion improves wildfire severity mapping relative to single-sensor baselines using Sentinel-2, Landsat-8, and Landsat-9 imagery across 40 wildfire events in the conterminous United States. We tested a two-stage fusion framework that combines feature-level fusion with pixel-level dimensionality reduction. First, feature-level fused datasets were created through early fusion by combining standardized post-fire bands from each sensor into a single predictor stack. Both raw reflectance bands and pairwise spectral transforms were retained to capture within- and cross-sensor spectral interactions. Second, Linear Discriminant Analysis was applied to both single-sensor and fused datasets to produce comparable low-dimensional feature spaces. Six machine-learning classifiers were then used to benchmark model performance with repeated spatially buffered train–test splits. Results show that Landsat-9 was the strongest single-sensor baseline. Among the fusion strategies, Sentinel-2 + Landsat-9 produced the most consistent improvement and reduced performance variability. Landscape-condition analysis further showed that this fusion was most beneficial in shrubland-dominated and high-terrain fires, where it achieved the highest overall mean accuracy and the fewest failures. In contrast, its benefits were less reliable in evergreen forests, mixed vegetation, and low- to moderate-elevation terrain. In operational settings, the Sentinel-2 + Landsat-9 configuration offers a practical solution for post-fire recovery planning, erosion-risk assessment, watershed management, and ecological monitoring when field observations are available and timely satellite-based information is needed.

Landsat↗

dRep: a tool for fast and accurate genomic comparisons that enables improved genome recovery from metagenomes through de-replication

The number of microbial genomes sequenced each year is expanding rapidly, in part due to genome-resolved metagenomic studies that routinely recover hundreds of draft-quality genomes. Rapid algorithms have been developed to comprehensively compare large genome sets, but they are not accurate with draft-quality genomes. We present dRep, a program that reduces the computational time for pairwise genome comparisons by sequentially applying a fast, inaccurate estimation of genome distance, and a slow, accurate measure of average nucleotide identity. dRep achieves a 28 × increase in speed with perfect recall and precision when benchmarked against previously developed algorithms. We demonstrate the use of dRep for genome recovery from time-series datasets. Each metagenome was assembled separately, and dRep was used to identify groups of essentially identical genomes and select the best genome from each replicate set. Finally, this resulted in recovery of significantly more and higher-quality genomes compared to the set recovered using co-assembly.

59 BASIC BIOLOGICAL SCIENCES↗

TransPolymer: a Transformer-based language model for polymer property predictions

Accurate and efficient prediction of polymer properties is of great significance in polymer design. Conventionally, expensive and time-consuming experiments or simulations are required to evaluate polymer functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance in natural language processing. However, such methods have not been investigated in polymer sciences. Herein, we report TransPolymer, a Transformer-based language model for polymer property prediction. Our proposed polymer tokenizer with chemical awareness enables learning representations from polymer sequences. Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer. Moreover, we show that TransPolymer benefits from pretraining on large unlabeled dataset via Masked Language Modeling. Experimental results further manifest the important role of self-attention in modeling polymer sequences. We highlight this model as a promising computational tool for promoting rational polymer design and understanding structure-property relationships from a data science view.

36 MATERIALS SCIENCE↗

Reactive Transport Simulation of Fracture Channelization and Transmissivity Evolution

Underground fractures serve as flow conduits, and they may produce unwanted migration of water and other fluids in the subsurface. An example is the migration and leakage of greenhouse gases in the context of geologic carbon sequestration. This study has generated new understanding about how acids erode carbonate fracture surfaces and the positive feedback between reaction and flow. A two-dimensional reactive transport model was developed and used to investigate the extent to which geochemical factors influence fracture permeability and transmissivity evolution in carbonate rocks. The only mineral modeled as reactive is calcite, a fast-reacting mineral that is abundant in subsurface formations. The X-ray computed tomography dataset from a previous experimental study of fractured cores exposed to carbonic acid served as a testbed to benchmark the model simulation results. The model was able to capture not only erosion of fracture surfaces but also the specific phenomenon of channelization, which produces accelerating transmissivity increase. Results corroborated experimental findings that higher reactivity of the influent solution leads to strong channelization without substantial mineral dissolution. Simulations using mineral maps of calcite in a specimen of Amherstburg limestone demonstrated that mineral heterogeneity can either facilitate or suppress the development of flow channels depending on the spatial patterns of reactive mineral. In these cases, fracture transmissivity may increase rapidly, increase slowly, or stay constant, and for all these possibilities, the calcite mineral continues to dissolve. Collectively, these results illustrate that fluid chemistry and mineral spatial patterns need to be considered in predictions of reaction-induced fracture alteration and risks of fluid migration.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Supersplat--spliced RNA-seq alignment

Motivation: High-throughput sequencing technologies have recently made deep interrogation of expressed transcript sequences practical, both economically and temporally. Identification of intron/exon boundaries is an essential part of genome annotation, yet remains a challenge. Here, we present supersplat, a method for unbiased splice-junction discovery through empirical RNA-seq data. Results: Using a genomic reference and RNA-seq high-throughput sequencing datasets, supersplat empirically identifies potential splice junctions at a rate of ~11.4 million reads per hour. We further benchmark the performance of the algorithm by mapping Illumina RNA-seq reads to identify introns in the genome of the reference dicot plant Arabidopsis thaliana and we demonstrate the utility of supersplat for de novo empirical annotation of splice junctions using the reference monocot plant Brachypodium distachyon. Availability: Implemented in C++, supersplat source code and binaries are freely available on the web at http://mocklerlabtools.cgrb.oregonstate.edu/

59 BASIC BIOLOGICAL SCIENCES↗

A Chlorophyll-a Algorithm for Landsat-8 Based on Mixture Density Networks

Retrieval of aquatic biogeochemical variables, such as the near-surface concentration of chlorophyll-a (Chla) in inland and coastal waters via remote observations, has long been regarded as a challenging task. This manuscript applies Mixture Density Networks (MDN) that use the visible spectral bands available by the Operational Land Imager (OLI) aboard Landsat-8 to estimate Chla. We utilize a database of co-located in situ radiometric and Chla measurements (N = 4,354), referred to as Type A data, to train and test an MDN model (MDN(A)). This algorithm’s performance, having been proven for other satellite missions, is further evaluated against other widely used machine learning models (e.g., support vector machines), as well as other domain-specific solutions (OC3), and shown to offer significant advancements in the field. Our performance assessment using a held-out test data set suggests that a 49% (median) accuracy with near-zero bias can be achieved via the MDN(A) model, offering improvements of 20 to 100% in retrievals with respect to other models. The sensitivity of the MDN(A) model and benchmarking methods to uncertainties from atmospheric correction (AC) methods, is further quantified through a semi-global matchup dataset (N = 3,337), referred to as Type B data. To tackle the increased uncertainties, alternative MDN models (MDN(B)) are developed through various features of the Type B data (e.g., Rayleigh-corrected reflectance spectra ρ(s)). Using held-out data, along with spatial and temporal analyses, we demonstrate that these alternative models show promise in enhancing the retrieval accuracy adversely influenced by the AC process. Results lend support for the adoption of MDN(B) models for regional and potentially global processing of OLI imagery, until a more robust AC method is developed. Index Terms—Chlorophyll-a, coastal water, inland water, Landsat-8, machine learning, ocean color, aquatic remote sensing.

Brandon Smith↗

Recognizing Unrecognized Sources of Uncertainty (USU) in Nuclear Data

Historically, time-of-flight (TOF) nuclear cross section measurements on different nuclides are assumed to be uncorrelated if they were recorded in different facilities with identical methods, identical facilities with different methods, and even identical facilities with identical methods. Ideally, measurements of different nuclides would truly be uncorrelated thus providing independent assessments of some cross section. In reality, correlations exist between measurements but are simply assumed to be unimportant. To eliminate these qualitative assumptions, in this paper we make a counter-intuitive suggestion to perform an intentionally correlated measurement of energy-differential fission and capture reactions for nuclides in a single criticality safety benchmark during a single experimental campaign. While this would introduce undesirable correlations, it would fully quantify correlations between datasets, rather than assume that the correlations do not exist.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Neural Architecture Search Benchmarks: Insights and Survey

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.

97 MATHEMATICS AND COMPUTING↗

Reinforcement Learning for Anomaly Detection in Nuclear Power Plant Operation and Maintenance

In nuclear power plants (NPPs), timely identification of sensor and human errors is critical to ensure safe and efficient plant operations. Anomaly detection models can be employed for this task. However, traditional anomaly detection approaches may have high dependency on labeled datasets and struggle with adaptability in complex, dynamic environments. Reinforcement learning (RL) has demonstrated significant potential in fault diagnosis and anomaly detection; however, its application to anomaly detection in NPPs remains a relatively underexplored research direction. Hence, to address this gap, in this study, we present a novel physics-informed reinforcement learning model, PIRL-AD: Physics-Informed Reinforcement Learning for Anomaly Detection, that integrates domain knowledge from calorimetric equations into the RL framework for enhanced sensor and human error anomaly detection. We evaluate the performance of PIRL-AD against a non-physics informed RL benchmark and a support vector machine (SVM) on data collected from a forced flow loop testbed. Experimental results suggest that PIRL-AD outperforms other baselines on a range of anomalous datasets that include both sensor and human-induced anomalies across key performance metrics, statistically outperforming the RL and SVM benchmarks with respect to geometric mean (respectively, 92.96% vs. 91.06% vs. 83.01%) and F1-score (respectively, 89.23% vs. 86.98% vs. 77.01%). Furthermore, the findings suggest the potential of physics-integrated reinforcement learning models for enhanced anomaly detection performance in NPPs.

Reinforcement learning↗